WO2024076918A1

WO2024076918A1 - Smart patient monitoring device for predicting patient temperature

Info

Publication number: WO2024076918A1
Application number: PCT/US2023/075724
Authority: WO
Inventors: Jeremy T DABROWIAK; Roland Krause; George L WALLS; Richard A HELKOWSKI; Masoumeh Mafi; Frederick W FORESTER
Original assignee: Zoll Circulation, Inc.
Priority date: 2022-10-03
Filing date: 2023-10-02
Publication date: 2024-04-11

Abstract

In an illustrative embodiment, a patient monitoring device for predicting patient temperature includes a user interface and a temperature prediction engine. The temperature prediction engine comprises hardware logic and/or software logic configured for execution on processing circuitry. The temperature prediction engine is configured to receive patient data; take into account at least one therapeutic intervention, wherein the at least one therapeutic intervention comprises a therapy that affects the patient's temperature; predict a first temperature of the patient for a first scenario in which the patient undergoes the at least one therapeutic intervention; prepare for presentation at the user interface the prediction of the first temperature; and provide the prediction of the first temperature to the user interface.

Description

PATENT Docket No.: Z20821WO-01 SMART PATIENT MONITORING DEVICE FOR PREDICTING PATIENT TEMPERATURE CROSS-REFERENCE TO RELATED APPLICATION(S) [0001] This application claims the benefit of and priority to U.S. Provisional Patent Application No.63/378,149, filed on October 3, 2022, the entire disclosure of which is incorporated herein by reference. TECHNICAL FIELD [0002] The present disclosure relates generally to the fields of medicine and engineering and, more particularly, to devices, systems, and methods for predicting and monitoring a patient's body temperature. BACKGROUND [0003] In various clinical situations, it is desirable to warm, cool or otherwise control the body temperature of a subject. For example, hypothermia can be induced in humans and some animals for the purpose of protecting various organs and tissues (e.g., heart, brain, kidneys) against the effects of ischemic, anoxic or toxic insult. For example, animal studies and/or clinical trials suggest that mild hypothermia can have neuroprotective and/or cardioprotective effects in animals or humans who suffer from ischemic cardiac events (e.g., myocardial infarction or acute coronary syndromes), postanoxic coma after cardiopulmonary resuscitation, traumatic brain injury, stroke, subarachnoid hemorrhage, fever and neurological injury. [0004] One method for inducing hypothermia is by intravascular or endovascular temperature management wherein a heat exchange catheter is inserted into a blood vessel and a thermal exchange fluid is circulated through a heat exchanger positioned on the portion of the catheter that is inserted in the blood vessel. As the thermal exchange fluid circulates through the catheter's heat exchanger, it exchanges heat with blood flowing past the heat exchanger in the blood vessel. Such technique can be used to cool the subject's flowing blood thereby resulting in a lowering of the subject's core body temperature to some desired target temperature. Endovascular temperature management is also capable of warming the body and/or of controlling body temperature to maintain a monitored body temperature at some selected temperature. If PATENT Docket No.: Z20821WO-01 a controlled rate of re-warming or re-cooling from the selected target temperature is desired, that too can be accomplished by carefully controlling the amount of heat added or removed from the body and thereby controlling the temperature change of the patient. SUMMARY [0005] The present disclosure describes a smart patient monitoring system for predicting temperature of a patient. The smart patient monitoring system may be operatively coupled to a temperature management system to provide temperature management treatment or therapy to the patient based on the predicted patient temperature by the smart patient monitoring system. The prediction provided by the smart patient monitoring system enables the clinician to actively manage the temperature of the patient and optionally provide suitable therapy to the patient. In this manner, the decision to administer therapy or intervention to the patient may be made earlier in the treatment process compared to a treatment that does not include the smart patient monitoring system, in which case the clinician reacts to a change in patient’s temperature. In addition, by providing the early prediction of the patient temperature, the clinician may efficiently manage and allocate the necessary resources to manage the patient’s temperature in, e.g., a hospital, setting. [0006] In addition, the smart patient monitoring system may provide an alert or prompt in response to the prediction of temperature that exceeds a temperature threshold set by the clinician. This allows the clinician to provide optimal care and treat the patient as needed depending on the patient’s status, early in the treatment. The smart patient monitoring system may provide a non-graphical or a graphical visual representation or audio indication of a prediction of the temperature of the patient under the assumption of receiving a therapy or intervention. This allows the clinician to predict the effects of the therapeutic intervention on the patient’s temperature prior to an actual application of the intervention. Alternatively, the smart patient monitoring system may provide a non-graphical or a graphical visual representation or audio indication of a prediction of the temperature of the patient over a period of time, where there is no assumption of receiving a therapeutic intervention. PATENT Docket No.: Z20821WO-01 [0007] The implementations described herein may include one or more of the following aspects or embodiments. In accordance with an aspect of the present disclosure there is provided a patient monitoring device for predicting patient temperature includes a user interface and a temperature prediction engine comprising hardware logic and/or software logic configured for execution on processing circuitry. The temperature prediction engine is configured to receive patient data, apply at least one therapeutic intervention to the patient data, predict a first temperature of the patient assuming the patient undergoes the at least one therapeutic intervention, prepare for presentation at the user interface the prediction of the first temperature, and provide the prediction of the first temperature to the user interface. The at least one therapeutic intervention comprises a therapy that affects the patient’s temperature. In accordance with an aspect of the present disclosure there is provided a patient monitoring device for predicting patient temperature includes a user interface and a temperature prediction engine comprising hardware logic and/or software logic configured for execution on processing circuitry. The temperature prediction engine is configured to receive patient data, manipulate the patient data to account for at least one therapeutic intervention, predict a first temperature of the patient for a first scenario in which the patient undergoes the at least one therapeutic intervention, prepare for presentation at the user interface the prediction of the first temperature, and provide the prediction of the first temperature to the user interface. The at least one therapeutic intervention comprises a therapy that affects the patient’s temperature. [0008] In some embodiments, the temperature prediction engine may use regression curve fitting to predict the first temperature of the patient. [0009] In some embodiments, the prediction of the first temperature may include prediction of a first temperature trajectory over a period of time. [0010] In some embodiments, the temperature prediction engine may receive historical data of patient under the at least one therapeutic intervention. [0011] In some embodiments, the historical data of the patient under the at least one therapeutic intervention may include historical temperature data, historical SaO2 (or SaO2) data, historical SpO2 (or SpO2) data, historical blood pressure data, historical heart rate data, or historical respiratory rate data. PATENT Docket No.: Z20821WO-01 [0012] In some embodiments, the temperature prediction engine may receive historical temperature data of patients without the at least one therapeutic intervention. [0013] In some embodiments, the temperature prediction engine may receive historical oxygen saturation data of patients. [0014] In some embodiments, the at least one therapeutic intervention may include intravascular cooling. [0015] In some embodiment, the at least one therapeutic intervention may include surface cooling. [0016] In some embodiments, the patient data may include at least one physiologic or anthropometric parameters of the patient. [0017] In some embodiments, the temperature prediction engine may be configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. [0018] In some embodiments, the temperature prediction engine may be configured to predict a second temperature by applying a second therapeutic intervention to the patient data. [0019] In some embodiments, the temperature prediction engine may be configured to predict a second temperature by manipulating the patient data to account for a second therapeutic intervention. [0020] In some embodiments, the temperature prediction engine may be configured to prepare for presentation at the user interface a second graph of the patient temperature versus time, based on the prediction of the second temperature. [0021] In some embodiments, the second and third graphs may be contiguous at time t. [0022] In some embodiments, the temperature prediction engine may be configured to provide the first and second graphs in a superposed relation. [0023] In some embodiments, the temperature prediction engine may be further configured to predict a third temperature from time t when the at least one therapeutic intervention is discontinued at time t. [0024] In some embodiments, the temperature prediction engine may be configured to predict the first temperature based on historical patient temperature data. [0025] In some embodiments, the patient data may include patient temperature. PATENT Docket No.: Z20821WO-01 [0026] In some embodiments, the patient data may include patient temperature data over a period of about 120 minutes. [0027] In some embodiments, the patient data may include SaO2, SpO2, heart rate, or blood pressure of the patient. [0028] In some embodiments, the temperature prediction engine may be configured to receive a user input for a threshold temperature. [0029] In some embodiments, the threshold temperature may be about 38 degrees Celsius. [0030] The patient monitoring device may further include an alert engine that is configured to receive the threshold temperature value and create an alert for the user when the prediction of the first temperature of the patient crosses the threshold temperature. [0031] In some embodiments, the temperature prediction engine may be configured to receive the patient data from at least one sensor. [0032] In some embodiments, the at least one sensor may be a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. [0033] In some embodiments, the temperature prediction engine may be configured to receive the patient data from a patient monitor. The patient monitor may be coupled to one or more patient data sensors. [0034] In some embodiments, the user interface may include a display or audio device. [0035] In some embodiments, the temperature prediction engine may be configured to create data including the prediction of the first temperature of the patient. [0036] In some embodiments, the data may be stored in a cloud storage database. [0037] In some embodiments, the temperature prediction engine may be configured to communicate with a patient temperature management device. [0038] In some embodiments, the temperature prediction engine may be configured to transmit the data to the patient temperature management device. [0039] In some embodiments, the temperature prediction engine may be configured to provide temperature related events to the user interface. [0040] In some embodiments, the temperature related events may include an occurrence of shivering of the patient. PATENT Docket No.: Z20821WO-01 [0041] In some embodiments, the temperature prediction engine may be configured to predict the first temperature of the patient based on the temperature related events. [0042] In some embodiments, the user interface may be configured to be detachable from the patient monitoring device. [0043] In some embodiments, the user interface may be configured to be wirelessly coupled to a patient temperature management device. [0044] In some embodiments, the patient temperature management device may include an evaporative cooling device. [0045] In some embodiments, the patient temperature management device may include a wearable device. [0046] In some embodiments, the temperature prediction engine may be configured to communicate with a portable device. [0047] In some embodiments, the temperature prediction engine may be configured to communicate with a defibrillation hardware. [0048] In some embodiments, the temperature prediction engine may be configured to predict the first temperature of the patient based on the received patient data and taking into account the at least one therapeutic intervention. [0049] In some embodiments, the temperature prediction engine may be configured to apply the patient data to a model that takes into account the at least one therapeutic intervention. [0050] In some embodiments, the temperature prediction engine may use machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. In some embodiments, the temperature prediction engine may be configured to manipulate the patient data to account for the at least one therapeutic intervention. [0051] In some embodiments, the temperature prediction engine may be configured to predict a temperature trajectory of the patient based on the regression curve fit. [0052] In some embodiments, the temperature prediction engine may be configured to manipulate the predicted temperature trajectory of the patient to account for the at least one therapeutic intervention. [0053] In some embodiments, the temperature prediction engines may apply the patient data to a model that takes into account the at least one therapeutic intervention. PATENT Docket No.: Z20821WO-01 [0054] In accordance with another aspect of the present disclosure there is provided a patient monitoring device for predicting patient temperature includes a user interface and a temperature prediction engine comprising hardware logic and/or software logic configured for execution on processing circuitry configured to receive patient data over a period of time; manipulate the patient data prior to a first time; extrapolate temperature of the patient over a period of time after the first time based on the manipulated patient data to provide a predicted patient temperature trajectory; prepare for presentation at the user interface predicted patient temperature trajectory; and provide the predicted patient temperature trajectory to the user interface. [0055] In some embodiments, the temperature prediction engine may use regression curve fitting processes to predict the first temperature of the patient. [0056] In some embodiments, the temperature prediction engine may receive historical temperature data of patients under at least one therapeutic intervention. [0057] In some embodiments, the temperature prediction engine may receive historical oxygen saturation data of patients. [0058] In some embodiments, the patient data may include at least one physiologic or anthropometric parameters of the patient. [0059] In some embodiments, the temperature prediction engine may be configured to be communicatively coupled to an external temperature management device. [0060] In some embodiments, the temperature prediction engine may be configured to manipulate the patient data to account for at least one therapeutic intervention to predict a second temperature. [0061] In some embodiments, the temperature prediction engine may be configured to manipulate the patient data to account for at least one therapeutic intervention to predict a second temperature. [0062] In some embodiments, the at least one therapeutic intervention may include intravascular cooling. [0063] In some embodiments, the at least one therapeutic intervention may include surface cooling. [0064] In some embodiments, the temperature prediction engine may be configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. PATENT Docket No.: Z20821WO-01 [0065] In some embodiments, the temperature prediction engine may be configured to prepare for presentation at the user interface a second graph of the patient temperature versus time, based on the prediction of the second temperature. [0066] In some embodiments, the first and second graphs may be contiguous at the first time. [0067] In some embodiments, the temperature prediction engine may be configured to provide the first and second graphs in a superposed relation. [0068] In some embodiments, the temperature prediction engine may be configured to predict a third temperature by manipulating the patient data to account for a second therapeutic intervention. [0069] In some embodiments, the temperature prediction engine may be configured to predict a third temperature by applying a second therapeutic intervention to the patient data. [0070] In some embodiments, the temperature prediction engine may be further configured to predict a fourth temperature from the first time when the at least one therapeutic intervention is discontinued at the first time. [0071] In some embodiments, the temperature prediction engine may be configured to predict the first temperature based on historical patient data. [0072] In some embodiments, the historical patient data may include historical temperature data, historical SaO2 data, historical SPO2 data, historical blood pressure data, historical heart rate data, or historical respiratory rate data. [0073] In some embodiments, the patient data may include patient temperature data over a period of about 120 minutes. [0074] In some embodiments, the patient data may include patient temperature. [0075] In some embodiments, the patient data may include SaO2, SpO2, heart rate, or blood pressure of the patient. [0076] In some embodiments, the temperature prediction engine may be configured to receive a user input for a threshold temperature. [0077] In some embodiments, the threshold temperature may be about 38 degrees Celsius. The patient monitoring device may further include an alert engine that is configured to receive the threshold temperature value and create an alert for the user PATENT Docket No.: Z20821WO-01 when the prediction of the first temperature of the patient crosses the threshold temperature value. [0078] In some embodiments, the temperature prediction engine may be configured to receive the patient data from at least one sensor. [0079] In some embodiments, the at least one sensor may be a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. [0080] In some embodiments, the temperature prediction engine may be configured to receive the patient data from a patient monitor. The patient monitor may be coupled to one or more patient data sensors. [0081] In some embodiments, the temperature prediction engine may be configured to provide temperature related events to the user interface. [0082] In some embodiments, the temperature related events may include an occurrence of shivering of the patient. [0083] In some embodiments, the temperature prediction engine may be configured to predict the first temperature of the patient based on the temperature related events. [0084] In some embodiments, the temperature prediction engine may be configured to create data including the prediction of the first temperature of the patient. [0085] In some embodiments, the data may be stored in a cloud storage database. [0086] In some embodiments, the temperature prediction engine may be configured to communicate with a patient temperature management device. [0087] In some embodiments, the temperature prediction engine may be configured to transmit the data to the patient temperature management device. [0088] In some embodiments, the user interface may include a display. [0089] In some embodiments, the user interface may be configured to be detachable from the patient monitoring device. [0090] In some embodiments, the user interface may be configured to be wirelessly coupled to a patient temperature management device. [0091] In some embodiments, the patient temperature management device may include an evaporative cooling device. [0092] In some embodiments, the patient temperature management device may include a wearable device. PATENT Docket No.: Z20821WO-01 [0093] In some embodiments, the temperature prediction engine may be configured to communicate with a portable device. [0094] In some embodiments, the temperature prediction engine may be configured to communicate with a defibrillation hardware. [0095] In some embodiments, the predicted patient temperature trajectory may include a prediction for the onset of fever. [0096] In some embodiments, the prediction of the first temperature may include a prediction for the onset of fever. [0097] In some embodiments, the temperature prediction engine may be configured to predict the first temperature of the patient based on the received patient data and taking into account the at least one therapeutic intervention. [0098] In some embodiments, the temperature prediction engine may be configured to take into account a temperature difference associated with the therapeutic intervention. [0099] In some embodiments, the model of the temperature prediction engine may be a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. [00100] In some embodiments, the prior patient data sets of physiological parameters may include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. [00101] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00102] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters without the at least one therapeutic intervention to identify temperature prediction of the patient without the at least one therapeutic intervention. [00103] In some embodiments, the machine learning model may be trained to adjust the temperature prediction of the patient without the at least one therapeutic intervention, to identify the first temperature of the patient by taking into account prior PATENT Docket No.: Z20821WO-01 patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00104] In some embodiments, the temperature prediction engine may use machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. [00105] In some embodiments, the temperature prediction engine may be configured to manipulate the patient data to account for the at least one therapeutic intervention. [00106] In some embodiments, the temperature prediction engine may be configured to predict a temperature trajectory of the patient based on the regression curve fit. [00107] In some embodiments, the temperature prediction engine may be configured to manipulate the predicted temperature trajectory of the patient to account for the at least one therapeutic intervention. [00108] In accordance with another aspect of the present disclosure there is provided a temperature management system for delivery of a temperature management therapy to a patient includes a temperature management device configured to control temperature of the patient, at least one patient sensor configured to generate data indicative of a physiologic parameter history of the patient, a user interface, and a controller communicatively coupled to the user interface. The controller includes a processor configured to receive patient data from the at least one patient sensor; predict a first temperature of the patient based on the patient data; based on the prediction of the first temperature of the patient, prepare, for presentation at the user interface the prediction of the first temperature of the patient; provide the prediction of the first temperature of the patient to the user interface; and based on the prediction of the first temperature of the patient, control the temperature management device to adjust or maintain the temperature of the patient. [00109] In some embodiments, the processor may implement regression curve fitting processes to predict a first temperature of the patient. [00110] In some embodiments, the prediction of the first temperature may include prediction of a first temperature trajectory over a period of time. [00111] In some embodiments, the temperature prediction engine may receive historical temperature data of patients under at least one therapeutic intervention. PATENT Docket No.: Z20821WO-01 [00112] In some embodiments, the temperature prediction engine may receive historical oxygen saturation data of patients. [00113] In some embodiments, the at least one therapeutic intervention to the patient may include intravascular cooling of the patient. [00114] In some embodiments, the at least one therapeutic intervention to the patient may include surface cooling of the patient. [00115] In some embodiments, the processor may be configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. [00116] In some embodiments, the processor may be configured to predict a second temperature of the patient by manipulating the patient data to account for a second therapeutic intervention. [00117] In some embodiments, the processor may be configured to prepare for presentation at the user interface a second graph of the patient temperature versus time, based on the prediction of the second temperature of the patient. [00118] In some embodiments, the first and second graphs may be contiguous at a first time. In some embodiments, the processor may be configured to provide the first and second graphs in a superposed relation. [00119] In some embodiments, the processor may be configured to predict a third temperature by applying a second temperature management therapy to the patient data. [00120] In some embodiments, the processor may further be configured to predict a third temperature of the patient from the first time if the at least one therapeutic intervention were discontinued at the first time. [00121] In some embodiments, the processor may be configured to predict the first temperature of the patient based on historical patient temperature data. [00122] In some embodiments, the patient data may include patient temperature. [00123] In some embodiments, the patient data may include patient temperature data over a period of about 120 minutes. [00124] In some embodiments, the patient data may include SaO2, SpO2, heart rate, or blood pressure. [00125] In some embodiments, the processor may be configured to receive a user input for a threshold temperature. PATENT Docket No.: Z20821WO-01 [00126] In some embodiments, the threshold temperature may be about 38 degrees Celsius. [00127] In some embodiments, the processor may be configured to create an alert for the user when the prediction of the first or second temperatures of the patient crosses the threshold temperature. [00128] In some embodiments, the at least one patient sensor may be a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. [00129] In some embodiments, the processor may be configured to provide temperature related events to the user interface. [00130] In some embodiments, the temperature related events may include an occurrence of shivering of the patient. [00131] In some embodiments, the processor may be configured to predict the first temperature of the patient based on the temperature related events. [00132] In some embodiments, the processor may be configured to create data including the prediction of the first, second, or third temperatures. [00133] In some embodiments, the data may be stored in a cloud storage database. [00134] In some embodiments, the user interface may be configured to be detachable from the temperature management device. [00135] In some embodiments, the user interface may be configured to be wirelessly coupled to the temperature management device. [00136] In some embodiments, the user interface includes a display. [00137] In some embodiments, the temperature prediction engine may be configured to predict the first temperature of the patient based on the received patient data and taking into account the at least one therapeutic intervention. [00138] In some embodiments, the temperature prediction engine may be configured to take into account a temperature difference associated with the therapeutic intervention. [00139] In some embodiments, the temperature prediction engine may be configured to apply the patient data to a model that takes into account the at least one therapeutic intervention. PATENT Docket No.: Z20821WO-01 [00140] In some embodiments, the model of the temperature prediction engine may be a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. [00141] In some embodiments, the prior patient data sets of physiological parameters may include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. [00142] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00143] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters without the at least one therapeutic intervention to identify temperature prediction of the patient without the at least one therapeutic intervention. [00144] In some embodiments, the machine learning model may be trained to adjust the temperature prediction of the patient without the at least one therapeutic intervention, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00145] In some embodiments, the temperature prediction engine may use machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. [00146] In some embodiments, the temperature prediction engine may be configured to manipulate the patient data to account for the at least one therapeutic intervention. [00147] In some embodiments, the temperature prediction engine may be configured to predict a temperature trajectory of the patient based on the regression curve fit. [00148] In some embodiments, the temperature prediction engine may be configured to manipulate the predicted temperature trajectory of the patient to account for the at least one therapeutic intervention. [00149] In accordance with another aspect of the present disclosure there is provided a patient monitoring device for predicting patient temperature includes at least one sensor and a controller communicatively coupled to the at least one sensor. The PATENT Docket No.: Z20821WO-01 controller includes a processor configured to receive patient data from the at least one sensor, predict a first temperature of the patient from a first time with temperature management therapy applied to the patient prior to the first time, based on the received patient data, predict a second temperature of the patient from the first time without the temperature management therapy applied to the patient from the first time, and transmit the prediction of the first or second temperatures to a temperature management device. [00150] In some embodiments, the temperature prediction engine may use regression curve fitting processes to predict the first temperature of the patient. [00151] In some embodiments, the prediction of the first temperature may include a prediction of a first temperature trajectory over a period of time. [00152] In some embodiments, the processor may receive historical temperature data of patients under the temperature management therapy. [00153] In some embodiments, the processor may receive historical oxygen saturation data of patients. [00154] In some embodiments, the temperature management therapy to the patient may include intravascular cooling of the patient. [00155] In some embodiments, the temperature management therapy to the patient may include surface cooling of the patient. [00156] In some embodiments, the processor may be configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. [00157] In some embodiments, the processor may be configured to prepare for presentation at the user interface a second graph of the patient temperature versus time, based on the prediction of the second temperature of the patient. [00158] In some embodiments, the first and second graphs may be contiguous at time t. [00159] In some embodiments, the processor may be configured to provide the first and second graphs in a superposed relation. [00160] In some embodiments, the processor may be configured to predict a third temperature by manipulating the patient data to account for a second temperature management therapy. [00161] In some embodiments, the patient data may include patient temperature. PATENT Docket No.: Z20821WO-01 [00162] In some embodiments, the patient data may include SaO2, SpO2, heart rate, or blood pressure. [00163] In some embodiments, the processor may be configured to receive a user input for the threshold temperature. [00164] In some embodiments, the threshold temperature may be about 38 degrees Celsius. [00165] In some embodiments, the processor may be configured to receive the patient data from at least one sensor. [00166] In some embodiments, the patient data may include patient temperature data over a period of about 120 minutes. [00167] In some embodiments, the at least one sensor may be a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. [00168] In some embodiments, the processor may be configured to receive the patient data from a patient monitor. The patient monitor may be coupled to one or more patient data sensors. [00169] In some embodiments, the processor may be configured to create data including the prediction of the first temperature of the patient. [00170] In some embodiments, the data may be stored in a cloud storage database. [00171] In some embodiments, the user interface may be configured to be detachable from the patient monitoring device. [00172] In some embodiments, the user interface may be configured to be wirelessly coupled to the temperature management device. [00173] In some embodiments, the processor may be configured to communicate with a portable device. [00174] In some embodiments, the patient temperature management device may include a wearable device. [00175] In some embodiments, the processor may be configured to provide temperature related events. [00176] In some embodiments, the temperature related events may include an occurrence of shivering of the patient. [00177] In some embodiments, the processor may be configured to predict the first temperature of the patient based on the temperature related events. PATENT Docket No.: Z20821WO-01 [00178] In some embodiments, the processor may be configured to create an alert for a user when the prediction of the first or second temperatures crosses a threshold temperature to enable operation of the temperature management device to be adjusted. [00179] In some embodiments, the patient monitoring device may further include a user interface configured to be communicatively coupled to a temperature management device. [00180] In some embodiments, the temperature prediction engines may apply the patient data to a model that takes into account the temperature management therapy. [00181] In some embodiments, the model of the temperature prediction engine may be a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. [00182] In some embodiments, the prior patient data sets of physiological parameters may include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. [00183] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters associated with the temperature management therapy. [00184] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters without the temperature management therapy to identify temperature prediction of the patient without the temperature management therapy. [00185] In some embodiments, the machine learning model may be trained to adjust the temperature prediction of the patient without the temperature management therapy, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the temperature management therapy. [00186] In some embodiments, the temperature prediction engine may use machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. [00187] In some embodiments, the temperature prediction engine may be configured to manipulate the patient data to account for the temperature management therapy. PATENT Docket No.: Z20821WO-01 [00188] In some embodiments, the temperature prediction engine may be configured to predict a temperature trajectory of the patient based on the regression curve fit. [00189] In some embodiments, the temperature prediction engine may be configured to manipulate the predicted temperature trajectory of the patient to account for the temperature management therapy. [00190] In accordance with another aspect of the present disclosure there is provided a method of predicting patient temperature includes receiving, by processing circuitry, patient data from at least one sensor, the patient data representing physiologic parameters of the patient; applying, by the processing circuitry, at least one therapeutic intervention to the patient data to predict a first temperature; preparing, by the processing circuitry, for presentation at a user interface, the prediction of the first temperature; and providing, by the processing circuitry, the prediction of the first temperature of the patient to the user interface. The at least one therapeutic intervention comprises a therapy that affects the patient’s temperature. In accordance with another aspect of the present disclosure there is provided a method of predicting patient temperature includes receiving, by processing circuitry, patient data from at least one sensor, the patient data representing physiologic parameters of the patient; taking into account, by the processing circuitry, at least one therapeutic intervention to predict a first temperature; preparing, by the processing circuitry, for presentation at a user interface, the prediction of the first temperature; and providing, by the processing circuitry, the prediction of the first temperature of the patient to the user interface. The at least one therapeutic intervention comprises a therapy that affects the patient’s temperature. [00191] In accordance with another aspect of the present disclosure there is provided a patient monitoring device for predicting patient temperature. The patient monitoring device comprises a user interface and a temperature prediction engine. The temperature prediction engine may comprise hardware logic and/or software logic configured for execution on processing circuitry. The temperature prediction engine is configured to: receive patient data; take into account at least one therapeutic intervention; predict a first temperature of the patient for a first scenario in which the patient undergoes the at least one therapeutic intervention; prepare for presentation at the user interface the PATENT Docket No.: Z20821WO-01 prediction of the first temperature; and provide the prediction of the first temperature to the user interface. [00192] In some embodiments, applying the at least one therapeutic intervention may include predicting the first temperature trajectory over a period of time. [00193] In some embodiments, taking into account the at least one therapeutic intervention comprises processing or manipulating the patient data to account for the at least one therapeutic intervention to predict a first temperature trajectory over a period of time. [00194] In some embodiments, the method may further include inputting a threshold temperature to create an alert when the prediction of the first temperature crosses the threshold temperature. [00195] In some embodiments, receiving patient data may include generating patient data from a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. [00196] In some embodiments, the method may further include, based on the prediction of the first temperature, preparing for presentation at the user interface, a first graph of the patient temperature versus time. [00197] In some embodiments, the method may further include processing or manipulating the patient data to account for a second therapeutic intervention to predict a second temperature of the patient. [00198] In some embodiments, the method may further include, based on the prediction of the second temperature, preparing for presentation at the user interface, a second graph of the patient temperature versus time. [00199] In some embodiments, the method may further include providing the first and second graphs to the user interface in a superposed relation. [00200] In some embodiments, the patient data may include applying the patient data to a model that takes into account the at least one therapeutic intervention. [00201] In some embodiments, the model may be a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. [00202] In some embodiments, the prior patient data sets of physiological parameters may include at least one of measured historical temperature, historical PATENT Docket No.: Z20821WO-01 SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. [00203] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00204] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters without the temperature management therapy to identify temperature prediction of the patient without the at least one therapeutic intervention. [00205] In some embodiments, the machine learning model may be trained to adjust the temperature prediction of the patient without the temperature management therapy, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00206] In some embodiments, the machine learning model may use machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. [00207] In accordance with another aspect of the present disclosure there is provided a method of predicting patient temperature includes receiving, by processing circuitry, patient data from at least one sensor, the patient data representing physiologic parameters of the patient; processing or manipulating, by processing circuitry, the patient data prior to a first time to extrapolate temperature of the patient over a period of time after the first time as a first temperature prediction of the patient; preparing, by processing circuitry, for presentation at a user interface, the first temperature prediction; and providing, by processing circuitry, the first temperature prediction of the patient to the user interface. [00208] In some embodiments, the method may further include transmitting the first temperature prediction of the patient to an external temperature management device. [00209] In some embodiments, receiving patient data may include generating patient data from a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. PATENT Docket No.: Z20821WO-01 [00210] In some embodiments, the method may further include inputting a threshold temperature value by a user to create an alert when the first temperature prediction crosses the threshold temperature value. [00211] In some embodiments, the method may further include, based on the first temperature prediction, preparing for presentation at the user interface, a first graph of the patient temperature versus time. [00212] In some embodiments, the method may further include manipulating the patient data to account for a therapeutic intervention to derive a second temperature prediction. [00213] In some embodiments, based on the second temperature prediction, preparing for presentation at the user interface, a second graph of the patient temperature versus time. [00214] In some embodiments, the method may further include providing the first and second graphs to the user interface, in a superposed relation. [00215] In some embodiments, manipulating the patient data may include applying the patient data to a model that takes into account the at least one therapeutic intervention. [00216] In some embodiments, the model may be a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. [00217] In some embodiments, the prior patient data sets of physiological parameters may include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. [00218] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00219] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters without the temperature management therapy to identify temperature prediction of the patient without the at least one therapeutic intervention. PATENT Docket No.: Z20821WO-01 [00220] In some embodiments, the machine learning model may be trained to adjust the temperature prediction of the patient without the temperature management therapy, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00221] In accordance with another aspect of the present disclosure there is provided a temperature management system for delivery of a temperature management therapy to a patient includes a patient monitoring device. The patient monitoring device includes at least one sensor and a controller communicatively coupled to the at least one sensor. The controller includes a processor configured to receive patient data from the at least one sensor; predict a first temperature of the patient from a first time with temperature management therapy applied to the patient, based on the received patient data; and transmit the prediction of the first temperature to the temperature management device. [00222] In some embodiments, the temperature management system may further include a temperature management device operatively coupled to the patient monitoring device. [00223] In some embodiments, the temperature management device may be configured to adjust or maintain the temperature of the patient based on the prediction of the first temperature of the patient monitoring device. [00224] In some embodiments, the processor may be configured to predict a second temperature of the patient from the first time without the temperature management therapy applied to the patient from the first time. [00225] In some embodiments, the patient monitoring device may further include a user interface. [00226] In some embodiments, the temperature prediction engine may be configured to take into account a temperature difference associated with the therapeutic intervention. [00227] In some embodiments, the model of the temperature prediction engine may be a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. PATENT Docket No.: Z20821WO-01 [00228] In some embodiments, the prior patient data sets of physiological parameters may include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. [00229] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00230] In some embodiments, the machine learning model may be trained on prior patient data sets of physiological parameters without the at least one therapeutic intervention to identify temperature prediction of the patient without the at least one therapeutic intervention. [00231] In some embodiments, the machine learning model may be trained to adjust the temperature prediction of the patient without the at least one therapeutic intervention, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. [00232] According to a further aspect of the invention, there is provided a patient monitoring device including a processor configured to: receive patient data from at least one sensor; account for at least one therapy intervention and predict a temperature of the patient. According to a further aspect of the invention, there is provided a patient monitoring device including a processor configured to: receive patient data from at least one sensor; and determine a predicted temperature of the patient based on the received patient data and accounting for a temperature change that would be expected from application of at least one therapy intervention. [00233] The processor may be configured to determine the temperature change that would be caused by application of at least one therapy intervention as part of the prediction. The temperature change may be determined empirically. The temperature change may be determined in accordance with one or more parameters of a device delivering the therapy intervention. The temperature change may be accounted for by applying a model or machine learning algorithm to the patient data. The processor may be configured to determine a raw predicted temperature of the patient based on the received patient data and modify the raw predicted temperature to provide the predicted PATENT Docket No.: Z20821WO-01 temperature using the temperature change. Alternatively, the processor may determine a predicted temperature directly without determining the raw temperature. [00234] The patient monitoring device may comprise the one or more sensors. The patient monitoring device may comprise a user interface for providing the predicted temperature to a user. The monitoring device may be configured to provide the patient temperature to a therapy device. [00235] According to a further aspect of the invention, there is provided a method including receive patient data from at least one sensor and determining a predicted temperature of the patient based on the received patient data and accounting for a temperature change that would be expected from application of at least one therapy intervention. [00236] In general, a patient monitoring device may comprise, or may be configured to communicate with, a patient therapy device. In general, there may be provided a system comprising a patient monitoring device and a patient therapy device. In general, a patient monitoring device may comprise, or may be configured to communicate with, a sensor for obtaining patient sensor data. In general, a patient therapy device may be provided in addition to, or as an alternative to, a user interface. [00237] The details of one or more embodiments are set forth in the accompanying drawings and the description below. Other features and advantages will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE DRAWINGS [00238] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate one or more embodiments and, together with the description, explain these embodiments. The above and other aspects and features of this disclosure will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings wherein like reference numerals identify similar or identical elements. The heat exchange catheters disclosed herein are described in detail with reference to the drawings, in which like reference numerals designate identical or corresponding elements in each of the several views. The terms parallel and perpendicular are understood to include relative configurations that are substantially parallel and substantially perpendicular up to about + or – 10 PATENT Docket No.: Z20821WO-01 degrees from true parallel and true perpendicular. Further, to the extent consistent, any or all of the aspects detailed herein may be used in conjunction with any or all of the other aspects detailed herein. The accompanying drawings have not necessarily been drawn to scale. Any values dimensions illustrated in the accompanying graphs and figures are for illustration purposes only and may or may not represent actual or preferred values or dimensions. Where applicable, some or all features may not be illustrated to assist in the description of underlying features. [00239] FIG. 1 is a schematic diagram of a smart patient monitoring system in accordance with an embodiment of the disclosure. [00240] FIG.1A is a schematic diagram of a smart patient monitoring system and a cloud server, illustrating data communication therebetween. [00241] FIG. 2 is a schematic diagram of the smart patient monitoring system of FIG. 1, an extracorporeal control console of a temperature management system, and a patient monitor, illustrating data communication therebetween. [00242] FIG. 3 is a perspective view of an intravascular temperature management system for use with the smart patient monitoring system of FIG.1. [00243] FIG. 3A is a partial perspective view of an extracorporeal control console of the intravascular temperature management system of FIG.3, illustrating a hardware for cooling and circulating a working fluid. [00244] FIG. 4 is a perspective view of a temperature management system for use with the smart patient monitoring system of FIG. 1, illustrating a concurrent intravascular cooling therapy and a surface cooling therapy. [00245] FIG. 4A is a perspective view of the temperature management system of FIG.4, illustrating surface cooling therapy. [00246] FIG. 5 is a perspective view of an evaporative cooling device for use with the smart patient monitoring system of FIG.1. [00247] FIG. 5A is a perspective view of the evaporative cooling device of FIG. 5, illustrating use on a patient. [00248] FIG.6 is a perspective view of a portable defibrillator hardware for use with the smart patient monitoring system of FIG.1. [00249] FIG.7 is a perspective view of a wearable temperature management device for use with the smart patient monitoring system of FIG.1. PATENT Docket No.: Z20821WO-01 [00250] FIG.8 is a schematic diagram of a portable smart patient monitoring system in accordance with another embodiment of the present disclosure. [00251] FIG. 8A is a schematic diagram of a portable smart patient monitoring system in accordance with another embodiment of the present disclosure, illustrating use of the portable smart patient monitoring system with a pulse oximeter sensor. [00252] FIG. 9 is a schematic diagram of a smart patient monitoring system in accordance with yet another embodiment of the disclosure. [00253] FIG. 10 is a schematic diagram of an extracorporeal control console of a temperature management system and a cloud server, illustrating data communication therebetween. [00254] FIG. 11 is a schematic diagram of an extracorporeal control console of a temperature management system in accordance with yet another embodiment of the present disclosure, illustrating a smart patient monitoring system integrated therein. [00255] FIG. 12 is a schematic diagram of an evaporative cooling device in accordance with yet another embodiment of the present disclosure, illustrating a smart patient monitoring system integrated therein. [00256] FIG. 13 is a schematic diagram of a portable defibrillator hardware in accordance with yet another embodiment, illustrating a smart patient monitoring system integrated therein. [00257] FIG. 14 is a schematic diagram of a wearable temperature management device in accordance with yet another embodiment, illustrating a smart patient monitoring system integrated therein. [00258] FIG.15 is an example of a user interface illustrating a predicted temperature trajectory of the patient without any therapeutic intervention. [00259] FIG. 16 is an example of a user interface illustrating predicted temperature trajectories of a patient assuming the patient undergoes various therapeutic interventions. [00260] FIG.17 is an example of a user interface illustrating a predicted temperature trajectory of a patient after the patient undergoing different therapeutic interventions. [00261] FIG.18 is an example of a user interface illustrating a predicted temperature trajectory of a patient under an open-loop therapeutic intervention. PATENT Docket No.: Z20821WO-01 [00262] FIG.19 is an example of a user interface illustrating a predicted temperature trajectory of the patient with additional patient information entered by a clinician. [00263] FIG. 20 is a flow chart of a method of predicting patient temperature in accordance with an embodiment of the present disclosure. [00264] FIG. 21 is a flow chart of a method of predicting patient temperature in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION [00265] The description set forth below in connection with the appended drawings is intended to be a description of various, illustrative embodiments of the disclosed subject matter. Specific features and functionalities are described in connection with each illustrative embodiment; however, it will be apparent to those skilled in the art that the disclosed embodiments may be practiced without each of those specific features and functionalities. [00266] Reference throughout the specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the subject matter disclosed. Thus, the appearance of the phrases “in one embodiment” or “in an embodiment” in various places throughout the specification is not necessarily referring to the same embodiment. Further, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. Further, it is intended that embodiments of the disclosed subject matter cover modifications and variations thereof. [00267] It must be noted that, as used in the specification and the appended claims, the singular forms “a,” “an,” and “the” include plural referents unless the context expressly dictates otherwise. That is, unless expressly specified otherwise, as used herein the words “a,” “an,” “the,” and the like carry the meaning of “one or more.” Additionally, it is to be understood that terms such as “left,” “right,” “top,” “bottom,” “front,” “rear,” “side,” “height,” “length,” “width,” “upper,” “lower,” “interior,” “exterior,” “inner,” “outer,” and the like that may be used herein merely describe points of reference and do not necessarily limit embodiments of the present disclosure to any particular orientation or configuration. Furthermore, terms such as “first,” “second,” PATENT Docket No.: Z20821WO-01 and “third,” merely identify one of a number of portions, components, steps, operations, functions, and/or points of reference as disclosed herein, and likewise do not necessarily limit embodiments of the present disclosure to any particular configuration or orientation. [00268] Furthermore, the terms “approximately,” “about,” “proximate,” “minor variation,” and similar terms generally refer to ranges that include the identified value within a margin of 20%, 10% or preferably 5% in certain embodiments, and any values therebetween. [00269] All of the functionalities described in connection with one embodiment are intended to be applicable to the additional embodiments described below except where expressly stated or where the feature or function is incompatible with the additional embodiments. For example, where a given feature or function is expressly described in connection with one embodiment but not expressly mentioned in connection with an alternative embodiment, it should be understood that the inventors intend that that feature or function may be deployed, utilized or implemented in connection with the alternative embodiment unless the feature or function is incompatible with the alternative embodiment. [00270] Described herein is a smart patient monitoring system for predicting temperature of a patient. The smart patient monitoring system may be operatively coupled to a temperature management system to provide temperature management treatment or therapy to the patient based on the predicted patient temperature by the smart patient monitoring system. The prediction provided by the smart patient monitoring system enables the clinician to actively manage the temperature of the patient and optionally provide suitable therapy to the patient. In this manner, the decision to administer therapy or intervention to the patient may be made earlier in the treatment process compared to a treatment that does not include the smart patient monitoring system, in which case the clinician reacts to a change in patient’s temperature. In addition, by providing the early prediction of the patient temperature, the clinician may efficiently manage and allocate the necessary resources to manage the patient’s temperature in, e.g., a hospital, setting. [00271] In addition, the smart patient monitoring system may provide an alert or prompt in response to the prediction of temperature that exceeds a temperature PATENT Docket No.: Z20821WO-01 threshold set by the clinician. This allows the clinician to provide optimal care and treat the patient as needed depending on the patient’s status, early in the treatment. The smart patient monitoring system may provide a non-graphical or a graphical visual representation or audio indication of a prediction of the temperature of the patient under the assumption of receiving a therapy or intervention. This allows the clinician to predict the effects of the therapeutic intervention on the patient’s temperature prior to an actual application of the intervention. Alternatively, the smart patient monitoring system may provide a non-graphical or a graphical visual representation or audio indication of a prediction of the temperature of the patient over a period of time, where there is no assumption of receiving a therapeutic intervention. [00272] FIG. 1 shows a schematic diagram of the smart patient monitoring system 1000. The smart patient monitoring system 1000 includes a sensor reading hardware 1100 for detecting patient data, and at least one patient sensor 1150 for measuring a physiologic parameter of the patient. The system may include a temperature prediction engine TPE including hardware logic and/or software logic configured for execution on processing circuitry, and a user interface 1300. A processor 1200 and/or a memory 1250 (e.g., a non-transitory processor readable storage medium) may provide the hardware logic and/or the software logic of the temperature prediction engine. The sensor reading hardware 1100 is configured to accept one or more patient sensor connections, read and convert the sensor’s, e.g., resistance values, into digital values, and transmit these values to the temperature prediction engine 1200. For example, the patient sensor 1150 may be a temperature sensor, e.g., a thermistor or thermocouple or temperature probe, positioned on or in the patient. In another example, the patient sensor 1150 may be a pulse oximetry sensor or other sensor for measuring oxygen levels in a patient’s blood. The sensor reading hardware 1100 may be configured to read patient parameters such as SaO₂, SpO₂, blood pressure, and heart rate, for the purposes of being utilized by an algorithm of the smart patient monitoring system 1000 to predict patient temperature. [00273] In particular, the smart patient monitoring system 1000 comprises a temperature prediction engine including a processor 1200 and one or more algorithms implemented by a processor1200. The temperature prediction engine predicts whether a future temperature event may occur. For example, the clinician may be concerned PATENT Docket No.: Z20821WO-01 about fever, and the smart patient monitoring system 1000 may notify the clinician if the temperature prediction engine predicts a fever will occur or is likely to occur. The temperature prediction engine may further predict the future temperature event of the patient under the assumed therapeutic intervention that affects the patient’s temperature. For example, therapeutic intervention may include, e.g., pharmacological intervention such as antipyretics, use of a fan, ice, a cooling or heating blanket, wrap or vest containing a thermal mass or a circulating fluid, evaporative cooling device, or intravascular temperature management. [00274] The temperature prediction engine may include software and/or hardware logic for performing the operations of each program, algorithm, or application. For example, in some embodiments, one or more engines include at least a portion of its functionality as hardware logic encoded into a programmable logic chip or reprogrammable processor. In some embodiments, at least portions of one or more engines perform their functions through executing software on processing circuitry, such as a server or multi-processor cloud computing environment. [00275] With continued reference to FIG. 1, the smart patient monitoring system 1000 may further include a communication hardware 1400 for receiving patient data e.g., data representing physiological parameters of the patient from, e.g., a patient monitor 1600, a hospital network 1700, or other smart monitors 1770 or data representing anthropometric parameters of the patient. In this manner, the communication hardware 1400 may be configured to receive the data representing physiologic parameters of the patient such as, e.g., oxygen saturation, blood pressure, heart rate, or respiratory rate, or anthropometric parameters such as, e.g., weight, height, and body mass index, for the purposes of being utilized by the temperature prediction algorithm of the temperature prediction engine. The connection may be made by Ethernet, RS-232, or other common communication protocols such as, e.g., Wi-Fi communications, Bluetooth®, cellular, USB, or other wireless connection or link. [00276] In addition, patient data may be transmitted or streamed in real time or near real time by the communication hardware 1400 via a wired, RS-232 streaming output on the smart patient monitoring system 1000 to a remote processor or computer, e.g., to an electronic medical record (EMR) data hub 1750 or the hospital network 1700. The hospital network 1700 may be connected to a cloud server 1800 via the Internet PATENT Docket No.: Z20821WO-01 1900 to upload the patient data. In addition, the connection may also be used to download updated algorithms from the cloud server 1800 to the smart patient monitoring system 1000. In an embodiment, the cloud server 1800 may include the temperature prediction engine, and the smart patient monitoring system 1000 may be connected to the cloud server 1800 to provide the patient data to the cloud server 1800. The cloud server 1800 may provide temperature prediction of the patient to the smart patient monitoring device 1000, as shown in FIG. 1A. The smart patient monitoring system 1000 may be a standalone device. [00277] This connection could be made by, e.g., Wi-Fi, Bluetooth®, Ethernet, or cellular communication hardware which connects to the Internet through a cellular data provider. In an embodiment, the smart patient monitoring system 1000 may further include a temperature output hardware 1500 for sending patient temperature data received by the smart patient monitoring system 1000 from a patient temperature sensor 1150 to the patient monitor 1600 via, e.g., the YSI-400 standard. [00278] With reference now to FIG. 2, in an embodiment, the smart patient monitoring system 1000 may receive patient data from a temperature management system 100 and/or the patient monitor 1600. The smart patient monitoring system 1000 may include the temperature prediction engine, whereby, based on the patient data, the smart patient monitoring system 1000 may provide patient temperature prediction to the temperature management system 100. [00279] With reference now to FIG. 3, the temperature management system 100 includes generally an extracorporeal control console 104 and additional hardware for _{managing the patient temperature.} ^{The extracorporeal control console 104 contains} active patient temperature management hardware including a cooling engine and a pump which may circulate fluid through a heat exchange device. For example, the heat exchange device may be an intravascular heat exchange device 110 which may be coupled to the temperature management system 100. In certain embodiments, the extracorporeal control console 104 of the temperature management system 100 may be configured for use with a plurality of different types of heat exchange devices such as various heat exchange catheters (catheters that may be used include those commercially available from ZOLL Circulation, Inc., San Jose, Calif., such as the Cool Line® Catheter, Icy® Catheter, Quattro® Catheter, and Solex 7® Catheter), or body surface PATENT Docket No.: Z20821WO-01 heat exchangers. The body surface heat exchangers may include heat exchanging blankets, pads, or garments. Exemplary temperature management systems and extracorporeal control consoles include the Thermogard XP® and Thermogard HQ™ manufactured by ZOLL Circulation. Reference may be made to U.S. Patent Application Serial No. 17/561,512, the entire disclosure of which is incorporated herein by reference, for a detailed discussion of an example of an extracorporeal control console 14 and the tubing assembly. Further reference may be made to U.S. Patent No. 11,185,440, the entire disclosure of which is incorporated herein by reference. The temperature management system 100 includes, for example, a fluid loop including a heat exchange device, e.g., an intravascular heat exchange catheter 110, and a tubing assembly 108 which facilitates connection of the heat exchange device to the extracorporeal control console 104. One or more temperature sensors 120a, 120b may be located on or in the heat exchange device 110, and/or may be located on a separate device or probe positioned elsewhere in the body, e.g., in the esophagus or rectum. In an embodiment, the heat exchange device 110, the tubing assembly 108 of the fluid loop and/or the temperature sensors 120a, b may be disposable items intended for a single use, while the control console 104 may be a non-disposable device intended for multiple uses. [00280] In the embodiment shown in FIG.3, the intravascular heat exchange catheter 110 comprises an elongate catheter body 122 and a heat exchanger 123a-c positioned on a distal portion of the catheter body 122. The heat exchanger 123a-c may be, e.g., an inflatable cylindrical balloon, as shown in FIG.3, or a serpentine or helical balloon or tubing, through which a thermal exchange fluid circulates. Inflow and outflow lumens (not shown) are present within the catheter body 122 to facilitate circulation of the thermal exchange fluid (e.g., sterile 0.9% sodium chloride solution or other suitable thermal exchange fluid) through the elongate catheter body 122. Optionally, the catheter body 122 may also include one or more working lumens 124 which extend through the catheter body 122 and terminate distally at one or more openings in the distal end of the catheter body. Such working lumens may serve as a guidewire lumen to facilitate insertion and position of the catheter and/or may be used after insertion of the catheter for delivery of fluids, medicaments or other devices. For example, as shown in FIG. 3, in some embodiments, the temperature sensors 120a-b may be inserted PATENT Docket No.: Z20821WO-01 through the working lumen of the catheter and advanced out of the distal end opening to a location beyond the distal end of the catheter body 122. Various heat exchange catheters may be used in the embodiments described herein. [00281] The extracorporeal control console 104 generally comprises a main housing 126 and a console head having a user interface 106. The main housing 126 contains various apparatuses and circuitry for warming/cooling thermal exchange fluid, e.g., coolant, refrigerant, saline, to controlled temperature(s) and for pumping such warmed or cooled thermal exchange fluid through the heat exchange device 110 to effectively modify and/or control the subject's body temperature. The console head includes a display device or user interface 106, such as a touch screen system, whereby certain information may be input by, and certain information may be displayed to, users of the temperature management system 100. On the housing 126, there may be provided connection ports 130, 132 for connection of additional or alternative types of temperature sensors and/or other apparatuses. A connector 136 can connect the tubing 109 of the tubing assembly 108 from the extracorporeal console 104 to the inflow and outflow tubes of the heat exchange device 110. [00282] FIG. 3A shows further detail of the of the extracorporeal control console 104. The extracorporeal control console 104 has an openable/closable access cover 202 that enables access to hardware elements, a heat exchange bath 216, an air trap receptacle 230, and a pump 204, e.g., a peristaltic pump. The heat exchange bath 216 is filled with a coolant and is configured to receive a coil (not shown) that is fluidly coupled to the heat exchange fluid loop. Working fluid (e.g., saline) is pumped through heat exchange fluid loop and through the coil, which is immersed in the coolant within the heat exchange bath. As the working fluid flows through the coil, it is in thermal contact with the coolant and exchanges heat with the coolant, resulting in a cooling or warming of the working fluid to a desired temperature. The temperature of the coolant in the heat exchange bath is controlled by the extracorporeal control console 104, e.g., by exchanging heat with a refrigerant flowing through a refrigerant loop within the console. The coil increases a surface area of the fluid loop that is exposed to the coolant in the heat exchange bath 216 such that the working fluid may be quickly cooled or warmed. A bath cap 214 covers the heat exchange bath 216 to ensure that a desired temperature is maintained in the heat exchange bath. The cap 214 has one or more PATENT Docket No.: Z20821WO-01 openings through which an input port and output port of the coil may extend for connecting the coil with tubing 209 of tubing assembly 208. The heat exchange fluid loop includes an air trap chamber, e.g., the air trap receptacle 230, which is configured for trapping and removing air from the fluid loop when configuring the temperature management system 100 for heating or cooling the patient. [00283] The temperature management system 100 further includes a processor or controller configured to carry out and control the temperature management processes described herein. The processor (e.g., a system controller) of the extracorporeal control console 104 of the temperature management system 100 may receive the patient temperature prediction data from the processor 2200 (FIG. 2) of the smart patient monitoring device 2000. The temperature management system 100 then uses the patient temperature prediction data to control operation of the temperature management system 100 to achieve a desired target temperature of the patient. [00284] FIG. 4 illustrates a temperature management system with a body surface heat exchanger which can be used with the smart patient monitoring system 1000. The temperature management system 100 illustrates use with an endovascular heat exchange catheter 44 and the body surface heat exchanger 46v, 46t. The endovascular heat exchange catheter 44 is connected to a catheter inflow line CI through which temperature controlled heat exchange fluid circulates from the heater/cooler 32 into the endovascular heat exchange catheter 44 and a catheter outflow line CO through which heat exchange fluid circulates from the endovascular heat exchange catheter 44 back into the heater cooler 32. The body surface heat exchanger 46v, 46t is connected to a surface or surface pad inflow line PL and a surface or surface pad outflow line PO. The surface pad inflow line PL and a surface pad outflow line PO are connected to a manifold 42 or other flow dividing apparatus. A portion of the heat exchange fluid from the surface pad inflow line PI is channeled by manifold 42 to the body surface heat exchanger 46v in the form of a vest through line 50. Returning heat exchange fluid then flows back to the manifold 42 from the vest through return line 52. In addition, the body surface heat exchanger 46t in the form of thigh pads are interconnected by tubes 58, 60 to facilitate circulation of heat exchange fluid through both thigh pads. Temperature controlled heat exchange fluid that enters the manifold 42 from surface pad inflow line PI then circulates from the manifold 42 through lines 54 and 58 and PATENT Docket No.: Z20821WO-01 through the thigh pads 46t. Spent heat exchange fluid then returns from the thigh pads 46t, through lines 56 and 60, to manifold 42. The manifold 42 combines the flows of returning heat exchange fluid from lines 52 and 56 and circulates such combined fluid back to the heater/cooler 32 through surface pad outflow line PO. It is further contemplated that the temperature management system 100 may be utilized for body surface temperature management, as shown in FIG. 4A, i.e., without the endovascular heat exchange catheter 44 (FIG.4). [00285] With reference to FIGS. 5 and 5A, it is further contemplated that the smart patient monitoring device 1000 may be configured for use with a portable temperature management device. The portable temperature management device may be mounted to an IV pole, placed on a cart, or secured to a patient’s bed. The portable temperature _{management device may} ^{provide the benefits of being able to move seamlessly with} the patient throughout the emergency department, catheterization lab, and intensive care unit, with little to no effort required by the clinician. In an embodiment, the portable temperature management device may be an evaporative cooling device 400. The evaporative cooling device 400 may include a hardware that actively manages a patient’s temperature by providing a fan or blower, a liquid oxygen tank, or a liquid perfluorocarbon tank which could cool a patient by evaporation and convection. For example, evaporation can take place in the patient’s nasal cavity, thereby cooling the patient. [00286] In another embodiment, the portable temperature management device may be a defibrillation hardware 300, as shown in FIG. 6. The defibrillation hardware 500 may be configured for use with the smart patient monitoring system 1000. [00287] In another embodiment, the smart patient monitoring device 1000 may be used in conjunction with a wearable cooling vest 3100, as shown in FIG. 7. As discussed hereinabove with respect to the temperature management system, the cooling vest 3100 may receive data including prediction of patient temperature from the temperature prediction engine TPE of the smart patient monitoring device 1000. The cooling vest 3100 may utilize the prediction data to adjust or maintain the cooling output of the cooling vest 3100. Optionally, the cooling vest or smart patient monitoring device may provide an alert or notification regarding prediction data such that a caregiver can adjust or maintain the cooling output of the cooling vest in response PATENT Docket No.: Z20821WO-01 thereto. In some embodiments, the cooling vest may not be configured to adjust or maintain cooling output of the cooling vest. For example, a wearable vest may merely hold ice packs. Under such a configuration, the smart patient monitoring device 1000 may be used to predict the patient’s future temperature and optionally alert the patient if the predicted temperature, e.g., trajectory of the temperature, is undesirable. For example, if the patient temperature is predicted to drop below, e.g., 33° C, the clinician could take actions to prevent the patient’s temperature to drop to that level by providing a means of warming the patient such as a blanket. [00288] In certain embodiments, the smart patient monitoring system 1000 may be a wearable device to be worn by a patient, as shown in FIG. 8. The wearable device may be worn on an arm or a wrist of the patient. The wearable device may include a band having buckles and a hook and loop fastener. The user interface 1300 in the form of, e.g., a display, may display the temperature prediction of the patient and also temperature prediction of the patient under the assumption of various modalities of therapeutic intervention. In an embodiment, the smart patient monitoring system 1000 may be a wearable device 9500 configured for use with a pulse oximeter sensor 9550, as shown in FIG.8A. [00289] In another embodiment, the smart patient monitoring device 1000 may include a functionality to transfer patient parameters or predictions data to another smart monitor 1770. This would enable clinicians to have a complete history of the patient temperature profile and predictions data. The data transfer would be achieved through direct device communication or through the cloud server 1800. In this manner, the smart patient monitoring system 1000 would be able to transfer patient parameters or temperature predictions to other smart monitors 1770 (FIG. 1) that may contain different types of treatment hardware such as going from a wearable monitor to a temperature management console with temperature monitoring and/or predicting capability. [00290] As described hereinabove, the temperature prediction engine TPE may include a processor 1200 (FIG. 1) and one or more algorithms implemented by said processor to predict whether a future temperature event may occur, e.g., whether the patient temperature will cross the threshold temperature. The temperature prediction engine may further predict whether a future temperature event, e.g., crossing of the PATENT Docket No.: Z20821WO-01 threshold temperature of the patient assuming the patient undergoes a therapeutic intervention may occur. Based on these predictions, the clinician may proactively treat or apply therapy to the patient prior to the patient reaching the threshold temperatures. For example, the clinician may be concerned about an onset of fever, and the smart patient monitoring system 1000, 2000 may notify the clinician if the temperature prediction engine predicts occurrence of the fever. Moreover, the temperature prediction engine may further predict the temperature of the patient under the assumption of various modalities of therapeutic intervention and illustrate effectiveness of the various modalities of therapeutic intervention against the fever. Based on such findings, the clinician may select the therapeutic intervention that is most suitable for the patient early in the treatment process. [00291] In particular, the temperature prediction engine receives patient data representing at least one physiologic parameter of a patient including temperature, oxygen saturation, partial pressure of oxygen, heart rate, respiratory rate, or blood pressure or anthropometric parameters of the patient, such as, e.g., weight, height, body mass index, body circumference (arm, waist, hip and calf). The temperature prediction may be based on a single parameter or multiple parameters. [00292] In certain embodiments, the temperature prediction engine may manipulate or use the patient data to predict a patient temperature or temperature trajectory. For example, in an embodiment, the temperature prediction engine may create a regression curve fit of a current patient temperature profile over the last 10 to 120 minutes. For example, this could be a second to fifth order polynomial curve. Derivatives of the curve may also be considered. The temperature prediction engine may extrapolate this curve some period of time, e.g., 10 – 60 minutes, into the future, and determine whether any points in the extrapolated curve correspond to a temperature event of interest. For example, the smart patient monitoring device 1000 may determine whether any of the points of the extrapolated curve exceeds the threshold for fever, commonly about 38.0° C. In this case, a corresponding device alert may contain the timeframe in which the temperature event is expected to occur, and this timeframe may be dynamically calculated by the temperature prediction engine depending on the extrapolated curve. [00293] In an embodiment, the temperature of the patient may be predicted by utilizing Equation 1 shown below. PATENT Docket No.: Z20821WO-01 dT = P ^ dt / (m ^ cp) ……………………. Eq.1 wherein dT is change in temperature of the patient, P is the power output of the temperature management device, dt is the time period over which the power output of the temperature management device is measured m is mass of the patient, and cp is the specific heat constant. Based on the power output of the temperature management device such as, e.g., the temperature management system 100 (FIG. 1) over the time period in which the power output of the temperature management device is measured while factoring in the mass of the patient and the specific heat constant, one can derive the change in temperature of the patient. Based on this equation, the temperature of the patient may be predicted through above-identified means, for example, under conditions where the patient’s metabolic heat generation is offset by their heat loss to the ambient environment. [00294] The cooling power output or change in cooling power output of a temperature management device (e.g., an intravascular or surface cooling device) may be a data input or variable utilized in predicting a patient’s temperature, for example, predicting a patient’s temperature under a scenario of continued application of a temperature management therapy or removing a patient from a temperature management therapy. [00295] In an embodiment, the parameters considered for predicting a patient temperature may include prior patient data sets including measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, or historical respiratory rate of patients with and/or without any therapeutic intervention. In certain embodiments, such data may be collected from a plurality of patients and used to develop and train a machine learning based model. In some embodiments, the temperature prediction engine derives insights from the data accessed from a data universe including various databases and stored data, e.g., using machine learning analysis and or other statistic data analysis techniques. The temperature prediction engine, for example, may include machine learning classifiers trained using PATENT Docket No.: Z20821WO-01 historical data to identify patterns in the data of the data universe. The information accessed from the data universe may be arranged in a variety of manners to apply the machine learning analysis such as, in some examples, a convolutional neural network (CNN), deep neural network (DNN), clustering tree, and/or synaptic learning network. The arrangement of data and/or type of learning analysis applied may be based in part upon the type and depth of information accessed, the desired insights to draw from the data, storage limitations, and/or underlying hardware functionality of the temperature prediction engine. In some examples, models may be based on a data science and machine learning framework, such as, but not limited to, TensorFlow, Brain, Keras, or Apache MXNET. [00296] Such a model may be utilized to predict future temperature of the patient over a period of time based on the patient’s current parameters including temperature, oxygen saturation, partial pressure of oxygen, heart rate, respiratory rate, or blood pressure. [00297] In addition to predicting the future temperature of the patient without any therapeutic intervention, based on the patient’s current parameters, the temperature prediction engine may manipulate the patient data to account for at least one therapeutic intervention. The therapeutic intervention may include a therapy that affects the patient’s temperature. In this manner, the temperature prediction engine is configured to predict temperature of the patient. To this end, the parameters for training a machine learning model may include prior patient data sets including measured historical temperature profiles and physiologic parameters of patients who received one or more modalities of therapeutic interventions and the measured historical temperature profiles and physiologic parameters of patients who didn’t receive therapeutic intervention. Therapeutic interventions may include the above-identified temperature management therapy such as, e.g., intravascular cooling or warming, surface cooling or warming, or evaporative cooling. In an embodiment, the parameters, e.g., for training the machine learning model, may further include other measured historical profiles of physiologic parameters of patients such as, e.g., oxygen saturation, partial pressure of oxygen, heart rate, respiratory rate, or blood pressure. It is also contemplated that historical temperature data of the patients obtained through the use of above-identified Equation 1 may be used as a parameter to train the machine learning model. PATENT Docket No.: Z20821WO-01 [00298] In some implementations, historical patient temperature pattern data may be derived from a plurality of patients including a first set of temperature pattern data associated with a group of patients without any therapeutic intervention, and a second set of temperature pattern data associated with a group of patients with therapeutic intervention. Such data may be used to develop and train machine learning based models for prediction of patient temperature projection for patients without therapeutic intervention and models for prediction of patient temperature projection for patients with therapeutic intervention. In some implementations, the patient data may be inputted into the models to obtain prediction of patient temperature. In some embodiments, a gradient boosting classifier may be applied. In some implementations, the gradient boosting classifier may include hyperparameters tuned using a grid search. In some implementations, the inclusion of other measured historical profiles of physiologic parameters of patients such as, e.g., oxygen saturation, partial pressure of oxygen, heart rate, respiratory rate, or blood pressure into the training of a machine learning based model may result in a classifier that performs with greater specificity and/or sensitivity. [00299] In some implementations, the machine learning model may include logistic regression, naïve Bayes, random forest, gradient boosting, neural networks, or learned survival models. The logistic regression, naïve Bayes, random forest, gradient boosting, neural networks, or learned survival models may be trained on data including the historical patient temperature pattern data from patients with or without the therapeutic intervention. The patient data may be manipulated to account for the temperature management therapy. Regression curve fitting may be used to predict the first temperature of the patient. A temperature trajectory of the patient may be predicted based on the regression curve fit. The predicted temperature trajectory of the patient may be manipulated to account for the at least one therapeutic intervention. Machine learning may be trained on prior patient data sets of physiological parameters. Machine learning analysis may include a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. The prior patient data sets may include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, or historical respiratory rate of patients without any therapeutic intervention. PATENT Docket No.: Z20821WO-01 [00300] The prior patient data sets may be obtained from the cloud server 1800 which may include data collected from other smart monitors 1770. However, the data may be obtained from publicly available datasets such as, e.g., eICU Collaborative Research Database. For example, data obtained from RescueNet® CaseReview for temperature management commercially available from ZOLL Circulation, Inc., San Jose, California may be utilized. Such data may be collected and used to develop and train a machine learning based model using, e.g., a TensorFlow software platform. For example, data may include composite population responses to various temperature management therapies. This could include time series descriptive statistics such as mean, median, inter-quartile ranges, or standard deviations. The statistics above could be recorded at regular time intervals (e.g., 1 minute) starting when therapy is applied. Values of these statistics would be normalized to the initial patient temperature (at the time treatment/therapy is initiated). [00301] The temperature prediction engine may provide the temperature prediction of the patient over a period of time where the patient is without any therapeutic intervention and/or assuming the patient undergoes one or more therapeutic interventions. The temperature prediction engine may prepare for presentation at the user interface the first temperature prediction and provide the first temperature prediction to the user interface. It is envisioned that the temperature prediction engine may use regression curve fitting processes to predict the first temperature of the patient; however, other methods or processes may be utilized. [00302] In some implementations, the temperature prediction engine may include a natural language processing (NLP) engine configured to receive the contextual patient data as unstructured data and convert the unstructured data to structured data including data elements associated with predicting patient temperature. The contextual patient data may include information from a remotely located telemedicine provider. The NLP engine may be configured to create a curated transcript for a remotely located telemedicine provider based on the structured data. The physiologic data may include a textual input from the at least one medical device. The NLP engine may be configured to predict one or more items of future structured data based on previously determined structured data. The NLP engine may include at least one machine learning model associated with the prediction of temperature projection. The NLP engine may be PATENT Docket No.: Z20821WO-01 configured to train and update the at least one machine learning model based on the contextual patient data. The at least one machine learning model may be a locally stored machine learning model in an unconnected state of the communicative coupling to the cloud server and may be a model stored at the cloud server in a connected state of the communicative coupling to the cloud server. [00303] With reference now to FIG.9, there is provided a system that provides both smart patient monitoring and treatment capability. The smart patient monitoring system 2000 includes a sensor reading hardware 2100, a processor 2200, a user interface 2300, a communication hardware 2400, and a temperature out hardware 2500 that are similar to those described hereinabove with respect to the smart patient monitoring system 1000 (FIG.1). The system may include a temperature prediction engine TPE including hardware logic and/or software logic configured for execution on processing circuitry. The processor 2200 and/or a memory 2250 (e.g., a non-transitory processor readable storage medium) may provide the hardware logic and/or the software logic of the temperature prediction engine. FIG. 9 illustrates the smart patient monitoring system 2000, further including temperature management hardware 3000. The smart patient monitoring system 2000 is integrated in the temperature management hardware 3000 that provides therapeutic intervention to the patient such as, e.g., intravascular temperature management therapy (IVTM) (FIG. 3), surface temperature management therapy (FIG. 4), or evaporative cooling therapy (FIGS. 5 and 5A). Under such a configuration, the temperature management hardware 3000 may include the temperature prediction engine described hereinabove. In an embodiment, the cloud server 1800 may include the temperature prediction engine, and temperature management hardware 3000 may be connected to the cloud server 1800 to provide the patient data to the cloud server 1800. The cloud server 1800 may provide temperature prediction of the patient to the smart patient monitoring system 2000, as shown in FIG. 10. In an embodiment, the smart patient monitoring system 2000 may be integrated with a user interface 506 of a temperature management system 500 configured for intravascular or surface temperature management therapy as shown in FIG. 11. In an embodiment, the user interface 506 including the smart patient monitoring system 2000 may be detachable from an extracorporeal control console 504 of the temperature management system 500. Under such a configuration, the user interface 506 may serve PATENT Docket No.: Z20821WO-01 as a standalone smart patient monitoring system 2000. In an embodiment, the smart patient monitoring system 2000 may be integrated with an evaporative cooling device 450, as shown in FIG 12. In another embodiment, the smart patient monitoring system 2000 may be integrated with a defibrillator hardware 350, as shown in FIG.13. In yet another embodiment, the smart patient monitoring system 2000 may be integrated with a wearable cooling vest 3150 worn by the patient, as shown in FIG.14. [00304] Although shown as a component of the smart monitoring or treatment devices in several of the embodiments described herein, in certain embodiments the temperature prediction engine (TPE) may be disposed on another medical device or at a remote computing device (e.g., a cloud server) which is in communication with the smart monitoring or treatment device. In certain embodiments, the temperature prediction engine may be a distributed resource across multiple physical devices that work together programmatically. [00305] With reference to FIG. 15, there is provided an example illustration of the user interface 1300, 2300. The user interface 1300, 2300 may include a display 1302, 2302 configured to show visual representations of the predicted temperature trajectory of the patient, e.g., based on a regression curve fit of historical patient temperature. The patient temperature curve 5000, representing detected patient temperature data of a patient, extends for a period of time, and based on such data, a temperature prediction 5100 is shown in phantom extending from the patient temperature curve 5000. The user interface 1300, 2300 further illustrates current patient temperature and an alert threshold 5500 that is set by the clinician. The temperature prediction engine of the smart patient monitoring device 1000 is able to predict at time t0 the predicted temperature 5100 crossing the alert threshold 5500 at time t₁. For example, at time t₀, the patient temperature is 37.4° C, i.e., below the alert threshold of 38° C. However, based on the predicted temperature trajectory of the patient, the patient temperature is predicted to cross the alert level of 38° C in about 20 to 40 minutes (t1-t0). [00306] In another embodiment, the temperature prediction engine may include a processor 1200, 2200 and one or more algorithms implemented by the processor 1200, 2200 that predict whether a future temperature condition may occur. The algorithm may be based on multiple parameters. As described hereinabove, the parameters may include prior patient data sets including measured historical temperature profiles of patients PATENT Docket No.: Z20821WO-01 assuming the patient undergoes various modalities of therapeutic interventions; measured historical temperature profiles of patients without any therapeutic intervention; and other measured historical patient profiles of physiologic parameters such as oxygen saturation, partial pressure of oxygen, heart rate, respiratory rate, or blood pressure. Such data may be collected and used to develop and train a machine learning based model using, e.g., TensorFlow software platform. Such a model may be utilized to predict future temperature of the patient based on the patient’s current parameters including temperature and other physiologic parameters such as oxygen saturation, partial pressure of oxygen, heart rate, respiratory rate, or blood pressure. [00307] Based on the model, the smart patient monitoring system 1000 provides predicted temperature trajectory of the patient assuming the patient undergoes various therapeutic interventions such as, e.g., intravascular temperature management, surface cooling, evaporative cooling, and others described herein. In an embodiment, the model may be a binary classifier that classifies whether or not the patient is likely to experience a future temperature event, such as becoming febrile. In this case, the corresponding device alert may include an estimated timeframe based on training data. It is further contemplated that the model may include a plurality of algorithms and a regression curve fit model to further refine the predictions of patient temperatures. Based on the model, the temperature prediction engine TPE may communicate with the controller of the temperature management hardware 3000 or a remote treatment device to adjust or initiate intervention. [00308] With reference to FIG.16, there is provided another example illustration of the user interface 1300, 2300. The user interface 1300, 2300 may include a display 1302, 2302 configured to show visual representations of the temperature prediction engine’s temperature prediction of the patient under the assumption of various therapeutic interventions. For example, one or more machine learning algorithms may be trained to predict how patients historically respond to temperature-related interventions, as described hereinabove. The patient temperature curve 6000 extends for a period of time (until t₀), and predictions of patient temperature assuming the patient undergoes various therapeutic interventions (e.g., meds, surface cooling, IVTM,) are shown in phantom line 6020, 6030, 6040 extending from the patient temperature curve 6000 at time t0. Prediction of patient temperature under the PATENT Docket No.: Z20821WO-01 assumption of the patient not receiving any therapeutic intervention is shown in phantom line 6010 as a baseline. [00309] The user interface 1300, 2300 may further illustrate an alert threshold 6500 that may be set by the clinician. The prediction of patient temperature or trajectory 6010 without undergoing any therapeutic intervention crosses the alert threshold 6500 at time t1 and the prediction of patient temperature assuming the patient undergoes a first therapeutic intervention such as, e.g., medication, crosses the alert threshold 6500 at time t2. These predictions are obtained at time t0. The prediction of patient temperature trajectories 6030, 6040 assumes that the patient undergoes other therapeutic interventions such as, e.g., surface cooling and intravascular temperature management, respectively. The trajectories 6030, 6040 remain under the alert threshold 6500. Based on the predicted temperature trajectories of the patient based on the model, the clinician may apply the surface cooling and/or the intravascular temperature management therapy to the patient and quickly eliminate the option of non-therapy (predicted temperature trajectory 6010) or medication intervention (predicted temperature trajectory 6020). In other embodiments, the predictions of the patient temperature under the assumption of different therapeutic interventions may be shown simultaneously, sequentially, or at the clinician’s command. [00310] With reference to FIG.17, there is provided another example illustration of the user interface 1300, 2300. In particular, the display 1302, 2302 may show a visual representation of the temperature management-related events such as, e.g., interventions or shivering. Such events may be entered into the smart patient monitoring system 1000, 2000 by the clinician. This provides the clinician with a visual record of events. The actual temperature history of the patient with different therapeutic interventions, e.g., surface cooling and medication at time t-1 and t-2, respectively, may be taken into account by the algorithm or used to train a machine learning model to obtain the prediction of the patient temperatures 7030, 7020, shown in phantom. The predictions provide the clinician with a visual indication of the predicted patient temperature. The visual representation may also include a particular temperature threshold and show the predicted temperature trajectory crossing an alert threshold 7500 at time t₁. This prediction is obtained at time t₀. The clinician at this time may PATENT Docket No.: Z20821WO-01 proactively apply other therapeutic interventions to prevent the patient temperature from crossing the alert threshold 7500. [00311] With reference now to FIG. 18, a smart monitoring system, e.g., implementing the machine learning algorithm, may be applied to an open-loop system in which, e.g., a surface cooling device (FIG. 4A), is utilized. The display 1302, 2302 may show visual representation of the actual temperature curve 8000 of the patient undergoing a therapeutic intervention 8030, e.g., surface cooling, applied to the patient at time t-1. The processor 1200 of the smart patient monitoring system 1000 may receive patient data from, e.g., the patient temperature sensor 1150. The temperature prediction engine TPE may predict a first temperature of the patient from time t with temperature management therapy applied to the patient. In addition, the temperature prediction engine TPE may further predict a second temperature of the patient from time t without the temperature management therapy applied to the patient from time t. The temperature prediction engine may utilize the parameters described hereinabove. [00312] The algorithm provides a prediction of the patient temperature under the assumption of continuous application of the first therapeutic intervention 8030. However, the prediction of the temperature of the patient under continuous application of the first therapeutic intervention, e.g., surface cooling, results in the predicted temperature trajectory 8020 crossing a lower alert threshold 8500b at time t1. The algorithm may further provide a prediction of the patient temperature under the assumption of the patient discontinuing the first therapeutic intervention (the surface cooling) at time t₀ as shown by phantom line 8010. This prediction is available at time t0. Such prediction of the patient temperature enables the clinician to discontinue application of the first therapeutic intervention at time t₀, or at a time before t₁, which in turn, allows the clinician to prevent the temperature of the patient crossing the low alert threshold 8500b. The prediction of the temperature of the patient under the assumption of discontinued application of the first therapeutic intervention remains between the upper and lower alert thresholds 8500a, 8500b. Such a prediction may be useful for patients that need to be transported during which time the patient may be without any therapeutic intervention. Based on the prediction, the clinician utilize portable temperature management devices. PATENT Docket No.: Z20821WO-01 [00313] With reference to FIG. 19, a smart monitoring system may be configured to receive user input of additional patient information to further refine the temperature _{prediction algorithm. The additional input may include} ^{age, gender, height, weight of} the patient, or the type of catheter being used. Having this data entered at the bedside of the patient may also reduce user workload in the post-case debrief process and may also increase the probability of the data being input to the system, which improves the ^{quality of the overall database. The additional input may be displayed as shown on} _the user interface 1300, 2300. [00314] In an embodiment, an algorithm may further provide a feedback loop by calculating the discrepancies between the predicted events and the actual events that take place after the predicted events. Such discrepancies together with the corresponding patient data sets may be utilized to improve the accuracy of the algorithm model. [00315] The extracorporeal control console 102 may include an alert engine that generates one or more alerts to indicate if the predicted temperature trajectory of the patient crosses the alert threshold provided by the clinician. The alert may be generated for presentation on, e.g., the user interface 106 of the intravascular temperature management system 100. The smart patient monitoring system 1000 may also send the alert to one or more other computing devices, such as computing devices associated with the hospital network 1700. The user interface 106 may be coupled to the extracorporeal control console 102 via a wire or wirelessly (e.g., the user interface 106 may be a portable tablet or remote computing device). In an embodiment, the smart patient monitoring system 1000 may also serve as the user interface 106 of the extracorporeal control console 102. It is contemplated that the user interface 106 may be detachable from the extracorporeal control console 104 and wirelessly connected to the extracorporeal control console 104. [00316] In an embodiment, the smart patient monitoring system generates the alert to cause the treatment hardware such as the intravascular temperature management system 100 (FIG.3) to perform an action. For example, feedback may be presented to a clinician, such as an audio cue, visual presentation, and so forth. The alert can cause the smart patient monitoring system 1000, 2000 or the intravascular temperature management system 100 to contact a clinician (e.g., place a phone call or page to a PATENT Docket No.: Z20821WO-01 physician, or nurse). The alert can cause the smart patient monitoring system 1000, 2000 or the intravascular temperature management system 100 to display future projection or prediction of the temperature of the patient assuming the patient undergoes the intervention or display future projection or prediction of the temperature of the patient without the intervention. In addition, the alert can cause the smart patient monitoring system 1000, 2000 to update a health record associated with the patient or cause the smart patient monitoring system 1000, 2000 to retrieve a health record associated with the patient for further analysis. In certain implementations, the smart patient monitoring system 1000, 2000 may be configured to determine if the alert is a real time alert or recorded for retrospective review. If it is a real time, the smart patient monitoring system may determine whether to display the alert on the user interface 1300, transmit the alert in an information chain, or send the alert data to a third-party monitor. In an embodiment, the alert system may include voice activated warnings or visual indications including flashing of colored lights. In an embodiment, different colors may designate different types of warnings. [00317] The alert may open a cell phone-based application or open an Internet- based application. From either application the clinician could see the alert plus other relevant data that may have been transmitted. The alert may include a non-patient specific identifier such as a bed number. Additionally, the clinician would have the opportunity to take actions in response to receiving the alert. This might include triggering a phone call to the ICU desk, adjusting the temperature change range or duration of the change on the alert (in the application or remote to the temperature management system) or marking that the clinician has seen the alert. [00318] With reference to FIG. 20 and as described hereinabove, a method of predicting patient temperature may include receiving, by processing circuitry, patient data from at least one sensor, the patient data representing physiologic parameters of the patient 11000; taking into account, by the processing circuitry, at least one therapeutic intervention to predict a first temperature, wherein the at least one therapeutic intervention comprises a therapy that affects the patient’s temperature. In some examples, taking into account at least one therapeutic intervention may include manipulating the patient data to account for at least one therapeutic intervention or applying at least one therapeutic intervention to the patient data 12000; preparing, by PATENT Docket No.: Z20821WO-01 the processing circuitry, for presentation at a user interface, the prediction of the first temperature 13000; and providing, by the processing circuitry, the prediction of the first temperature of the patient to the user interface 14000. [00319] With reference to FIG. 21 and as described hereinabove, a method of predicting patient temperature may include receiving, by processing circuitry, patient data from at least one sensor, the patient data representing physiologic parameters of the patient 21000; manipulating, by processing circuitry, the patient data prior to a first time to extrapolate temperature of the patient over a period of time after the first time as a first temperature prediction of the patient 22000; preparing, by processing circuitry, for presentation at a user interface, the first temperature prediction 23000; and providing, by processing circuitry, the first temperature prediction of the patient to the user interface 24000. [00320] Some implementations of subject matter and operations described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. For example, in some implementations, the processor of the temperature management system can be implemented using digital electronic circuitry, or in computer software, firmware, or hardware, or in combinations of one or more of them. [00321] Some implementations described in this specification (e.g., the processor of the temperature management system) can be implemented as one or more groups or modules of digital electronic circuitry, computer software, firmware, or hardware, or in combinations of one or more of them. Although different modules can be used, each module need not be distinct, and multiple modules can be implemented on the same digital electronic circuitry, computer software, firmware, or hardware, or combination thereof. [00322] Some implementations described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on computer storage medium for execution by, or to control the operation of, data processing apparatus. A computer storage medium can be, or can be included in, a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination of one or more of PATENT Docket No.: Z20821WO-01 them. Moreover, while a computer storage medium is not a propagated signal, a computer storage medium can be a source or destination of computer program instructions encoded in an artificially generated propagated signal. The computer storage medium can also be, or be included in, one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices). [00323] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed for execution on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network. [00324] Some of the processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform actions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit). [00325] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random access memory or both. A computer includes a processor for performing actions in accordance with instructions and one or more memory devices for storing instructions and data. A computer may also include or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. However, a computer need not have such devices. Devices suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices (e.g., PATENT Docket No.: Z20821WO-01 EPROM, EEPROM, flash memory devices, and others), magnetic disks (e.g., internal hard disks, removable disks, and others), magneto optical disks, and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry. [00326] To provide for interaction with a user, operations can be implemented on a computer having a display device (e.g., a monitor, or another type of display device) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse, a trackball, a tablet, a touch sensitive screen, or another type of pointing device) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, speech, or tactile input. In addition, a computer can interact with a user by sending documents to and receiving documents from a device that is used by the user; for example, by sending web pages to a web browser on a user’s client device in response to requests received from the web browser. [00327] A computer system may include a single computing device, or multiple computers that operate in proximity or generally remote from each other and typically interact through a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), an inter- network (e.g., the Internet), a network comprising a satellite link, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks). A relationship of client and server may arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. [00328] While this specification contains many details, these should not be construed as limitations on the scope of what may be claimed, but rather as descriptions of features specific to particular examples. Certain features that are described in this specification in the context of separate implementations can also be combined. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple embodiments separately or in any suitable sub- combination. PATENT Docket No.: Z20821WO-01 [00329] A number of embodiments have been described. For example, the detailed description and the accompanying drawings to which it refers are intended to describe some, but not necessarily all, examples or embodiments of the system. The described embodiments are to be considered in all respects only as illustrative and not restrictive. Nevertheless, various modifications may be made without departing from the scope of the data processing system described herein. Accordingly, other embodiments are within the scope of the following claims.

Claims

PATENT Docket No. Z20821US-01 WHAT IS CLAIMED IS: 1. A patient monitoring device for predicting patient temperature, the patient monitoring device comprising: a user interface; and a temperature prediction engine comprising hardware logic and/or software logic configured for execution on processing circuitry, the temperature prediction engine configured to: receive patient data; take into account at least one therapeutic intervention, wherein the at least one therapeutic intervention comprises a therapy that affects the patient’s temperature; predict a first temperature of the patient for a first scenario in which the patient undergoes the at least one therapeutic intervention; prepare for presentation at the user interface the prediction of the first temperature; and provide the prediction of the first temperature to the user interface. 2. The patient monitoring device according to claim 1, wherein the temperature prediction engine uses regression curve fitting to predict the first temperature of the patient. 3. The patient monitoring device according to claim 1, wherein the prediction of the first temperature includes prediction of a first temperature trajectory over a period of time. 4. The patient monitoring device according to claim 1, wherein the temperature prediction engine receives historical data of a patient under the at least one therapeutic intervention. PATENT Docket No. Z20821US-01 5. The patient monitoring device according to claim 4, wherein the historical data of the patient under the at least one therapeutic intervention includes historical temperature data, historical SaO2 data, historical SPO2 data, historical blood pressure data, historical heart rate data, or historical respiratory rate data. 6. The patient monitoring device according to claim 4, wherein the temperature prediction engine receives historical temperature data of patients without the at least one therapeutic intervention. 7. The patient monitoring device according to claim 4, wherein the temperature prediction engine receives historical oxygen saturation data of patients. 8. The patient monitoring device according to claim 1, wherein the at least one therapeutic intervention includes intravascular cooling. 9. The patient monitoring device according to claim 1, wherein the at least one therapeutic intervention includes surface cooling. 10. The patient monitoring device according to claim 1, wherein the patient data includes at least one physiologic or anthropometric parameters of the patient. 11. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. 12. The patient monitoring device according to claim 11, wherein the temperature prediction engine is configured to predict a second temperature by manipulating the patient data to account for a second therapeutic intervention. 13. The patient monitoring device according to claim 12, wherein the temperature prediction engine is configured to prepare for presentation at the user PATENT Docket No. Z20821US-01 interface a second graph of the patient temperature versus time, based on the prediction of the second temperature. 14. The patient monitoring device according to claim 13, wherein the second and third graphs are contiguous at time t. 15. The patient monitoring device according to claim 14, wherein the temperature prediction engine is configured to provide the first and second graphs in a superposed relation. 16. The patient monitoring device according to claim 11, wherein the temperature prediction engine is further configured to predict a third temperature from time t when the at least one therapeutic intervention is discontinued at time t. 17. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to predict the first temperature based on historical patient temperature data. 18. The patient monitoring device according to claim 1, wherein the patient data includes patient temperature. 19. The patient monitoring device according to claim 18, wherein the patient data includes patient temperature data over a period of about 120 minutes. 20. The patient monitoring device according to claim 1, wherein the patient data includes SaO2, SpO2, heart rate, or blood pressure of the patient. 21. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to receive a user input for a threshold temperature. 22. The patient monitoring device according to claim 21, wherein the threshold temperature is about 38 degrees Celsius. PATENT Docket No. Z20821US-01 23. The patient monitoring device according to claim 21, further comprising an alert engine that is configured to receive the threshold temperature value and create an alert for the user when the prediction of the first temperature of the patient crosses the threshold temperature. 24. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to receive the patient data from at least one sensor. 25. The patient monitoring device according to claim 24, wherein the at least one sensor is a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. 26. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to receive the patient data from a patient monitor, wherein the patient monitor is coupled to one or more patient data sensors. 27. The patient monitoring device according to claim 1, wherein the user interface includes a display or audio device. 28. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to create data including the prediction of the first temperature of the patient. 29. The patient monitoring device according to claim 28, wherein the data is stored in a cloud storage database. 30. The patient monitoring device according to claim 28, wherein the temperature prediction engine is configured to communicate with a patient temperature management device. PATENT Docket No. Z20821US-01 31. The patient monitoring device according to claim 30, wherein the temperature prediction engine is configured to transmit the data to the patient temperature management device. 32. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to provide temperature related events to the user interface. 33. The patient monitoring device according to claim 32, wherein the temperature related events include an occurrence of shivering of the patient. 34. The patient monitoring device according to claim 32, wherein the temperature prediction engine is configured to predict the first temperature of the patient based on the temperature related events. 35. The patient monitoring device according to claim 1, wherein the user interface is configured to be detachable from the patient monitoring device. 36. The patient monitoring device according to claim 1, wherein the user interface is configured to be wirelessly coupled to a patient temperature management device. 37. The patient monitoring device according to claim 36, wherein the patient temperature management device includes an evaporative cooling device. 38. The patient monitoring device according to claim 36, wherein the patient temperature management device includes a wearable device. 39. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to communicate with a portable device. PATENT Docket No. Z20821US-01 40. The patient monitoring device according to claim 39, wherein the temperature prediction engine is configured to communicate with a defibrillation hardware. 41. A patient monitoring device for predicting patient temperature, the patient monitoring device comprising: a user interface; and a temperature prediction engine comprising hardware logic and/or software logic configured for execution on processing circuitry configured to: receive patient data over a period of time; manipulate the patient data prior to a first time; extrapolate temperature of the patient over a period of time after the first time based on the manipulated patient data to provide a predicted patient temperature trajectory; prepare for presentation at the user interface predicted patient temperature trajectory; and provide the predicted patient temperature trajectory to the user interface. 42. The patient monitoring device according to claim 41, wherein the temperature prediction engine uses regression curve fitting processes to predict a first temperature of the patient. 43. The patient monitoring device according to claim 42, wherein the temperature prediction engine receives historical temperature data of patients under at least one therapeutic intervention. 44. The patient monitoring device according to claim 42, wherein the temperature prediction engine receives historical oxygen saturation data of patients. 45. The patient monitoring device according to claim 41, wherein the patient data includes at least one physiologic or anthropometric parameters of the patient. PATENT Docket No. Z20821US-01 46. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to be communicatively coupled to an external temperature management device. 47. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to manipulate the patient data to account for at least one therapeutic intervention to predict a second temperature. 48. The patient monitoring device according to claim 47, wherein the at least one therapeutic intervention includes intravascular cooling. 49. The patient monitoring device according to claim 47, wherein the at least one therapeutic intervention includes surface cooling. 50. The patient monitoring device according to claim 47, wherein the temperature prediction engine is configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. 51. The patient monitoring device according to claim 50, wherein the temperature prediction engine is configured to prepare for presentation at the user interface a second graph of the patient temperature versus time, based on the prediction of the second temperature. 52. The patient monitoring device according to claim 51, wherein the first and second graphs are contiguous at the first time. 53. The patient monitoring device according to claim 51, wherein the temperature prediction engine is configured to provide the first and second graphs in a superposed relation. PATENT Docket No. Z20821US-01 54. The patient monitoring device according to claim 47, wherein the temperature prediction engine is configured to predict a third temperature by manipulating the patient data to account for a second therapeutic intervention. 55. The patient monitoring device according to claim 54, wherein the temperature prediction engine is further configured to predict a fourth temperature from the first time when the at least one therapeutic intervention is discontinued at the first time. 56. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to predict the first temperature based on historical patient data. 57. The patient monitoring device according to claim 56, wherein the historical patient data includes historical temperature data, historical SaO2 data, historical SPO2 data, historical blood pressure data, historical heart rate data, or historical respiratory rate data. 58. The patient monitoring device according to claim 57, wherein the patient data includes patient temperature data over a period of about 120 minutes. 59. The patient monitoring device according to claim 42, wherein the patient data includes patient temperature. 60. The patient monitoring device according to claim 42, wherein the patient data includes SaO2, SpO2, heart rate, or blood pressure of the patient. 61. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to receive a user input for a threshold temperature. 62. The patient monitoring device according to claim 60, wherein the threshold temperature is about 38 degrees Celsius. PATENT Docket No. Z20821US-01 63. The patient monitoring device according to claim 42, further comprising an alert engine that is configured to receive the threshold temperature value and create an alert for the user when the prediction of the first temperature of the patient crosses the threshold temperature value. 64. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to receive the patient data from at least one sensor. 65. The patient monitoring device according to claim 63, wherein the at least one sensor is a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. 66. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to receive the patient data from a patient monitor, wherein the patient monitor is coupled to one or more patient data sensors. 67. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to provide temperature related events to the user interface. 68. The patient monitoring device according to claim 67, wherein the temperature related events include an occurrence of shivering of the patient. 69. The patient monitoring device according to claim 67, wherein the temperature prediction engine is configured to predict the first temperature of the patient based on the temperature related events. 70. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to create data including the prediction of the first temperature of the patient. PATENT Docket No. Z20821US-01 71. The patient monitoring device according to claim 70, wherein the data is stored in a cloud storage database. 72. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to communicate with a patient temperature management device. 73. The patient monitoring device according to claim 70, wherein the temperature prediction engine is configured to transmit the data to the patient temperature management device. 74. The patient monitoring device according to claim 42, wherein the user interface includes a display. 75. The patient monitoring device according to claim 42, wherein the user interface is configured to be detachable from the patient monitoring device. 76. The patient monitoring device according to claim 42, wherein the user interface is configured to be wirelessly coupled to a patient temperature management device. 77. The patient monitoring device according to claim 76, wherein the patient temperature management device includes an evaporative cooling device. 78. The patient monitoring device according to claim 76, wherein the patient temperature management device includes a wearable device. 79. The patient monitoring device according to claim 42, wherein the temperature prediction engine is configured to communicate with a portable device. 80. The patient monitoring device according to claim 79, wherein the temperature prediction engine is configured to communicate with a defibrillation hardware. PATENT Docket No. Z20821US-01 81. A temperature management system for delivery of a temperature management therapy to a patient comprising: a temperature management device configured to control temperature of the patient; at least one patient sensor configured to generate data indicative of a physiologic parameter history of the patient; a user interface; and a controller communicatively coupled to the user interface, the controller comprising a processor configured to: receive patient data from the at least one patient sensor; predict a first temperature of the patient based on the patient data; based on the prediction of the first temperature of the patient, prepare, for presentation at the user interface the prediction of the first temperature of the patient; provide the prediction of the first temperature of the patient to the user interface; and based on the prediction of the first temperature of the patient, control the temperature management device to adjust or maintain the temperature of the patient. 82. The temperature management system according to claim 81, wherein the processor implements regression curve fitting to predict the first temperature of the patient. 83. The patient monitoring device according to claim 82, wherein the prediction of the first temperature includes prediction of a first temperature trajectory over a period of time. 84. The patient monitoring device according to claim 83, wherein the temperature prediction engine receives historical temperature data of patients under at least one therapeutic intervention. PATENT Docket No. Z20821US-01 85. The patient monitoring device according to claim 83, wherein the temperature prediction engine receives historical oxygen saturation data of patients. 86. The temperature management system according to claim 83, wherein the at least one therapeutic intervention to the patient includes intravascular cooling of the patient. 87. The temperature management system according to claim 83, wherein the at least one therapeutic intervention to the patient includes surface cooling of the patient. 88. The patient monitoring device according to claim 81, wherein the processor is configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. 89. The temperature management system according to claim 87, wherein the processor is configured to predict a second temperature of the patient by manipulating the patient data to account for a second therapeutic intervention. 90. The temperature management system according to claim 88, wherein the processor is configured to prepare for presentation at the user interface a second graph of the patient temperature versus time, based on the prediction of the second temperature of the patient. 91. The temperature management system according to claim 89, wherein the first and second graphs are contiguous at a first time. 92. The temperature management system according to claim 90, wherein the processor is configured to provide the first and second graphs in a superposed relation. 93. The temperature management system according to claim 91, wherein the processor is further configured to predict a third temperature of the patient from the PATENT Docket No. Z20821US-01 first time if the at least one therapeutic intervention were discontinued at the first time. 94. The temperature management system according to claim 82, wherein the processor is configured to predict the first temperature of the patient based on historical patient temperature data. 95. The temperature management system according to claim 82, wherein the patient data includes patient temperature. 96. The temperature management system according to claim 95, wherein the patient data includes patient temperature data over a period of about 120 minutes. 97. The temperature management system according to claim 82, wherein the patient data includes SaO2, SpO2, heart rate, or blood pressure. 98. The temperature management system according to claim 89, wherein the processor is configured to receive a user input for a threshold temperature. 99. The temperature management system according to claim 98, wherein the threshold temperature is about 38 degrees Celsius. 100. The temperature management system according to claim 98, wherein the processor is configured to create an alert for the user when the prediction of the first or second temperatures of the patient crosses the threshold temperature. 101. The temperature management system according to claim 82, wherein the at least one patient sensor is a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. 102. The temperature management system according to claim 82, wherein the processor is configured to provide temperature related events to the user interface. PATENT Docket No. Z20821US-01 103. The temperature management system according to claim 102, wherein the temperature related events include an occurrence of shivering of the patient. 104. The temperature management system according to claim 102, wherein the processor is configured to predict the first temperature of the patient based on the temperature related events. 105. The temperature management system according to claim 93, wherein the processor is configured to create data including the prediction of the first, second, or third temperatures. 106. The temperature management system according to claim 105, wherein the data is stored in a cloud storage database. 107. The temperature management system according to claim 82, wherein the user interface is configured to be detachable from the temperature management device. 108. The temperature management system according to claim 82, wherein the user interface is configured to be wirelessly coupled to the temperature management device. 109. The patient monitoring device according to claim 82, wherein the user interface includes a display. 110. A patient monitoring device for predicting patient temperature, the patient monitoring device comprising: at least one sensor; and a controller communicatively coupled to the at least one sensor, the controller comprising a processor configured to: receive patient data from the at least one sensor; PATENT Docket No. Z20821US-01 predict a first temperature of the patient from a first time with temperature management therapy applied to the patient prior to the first time, based on the received patient data; predict a second temperature of the patient from the first time without the temperature management therapy applied to the patient from the first time; and transmit the prediction of the first or second temperatures to a temperature management device. 111. The patient monitoring device according to claim 110, wherein the temperature prediction engine uses regression curve fitting intelligence processes to predict the first temperature of the patient. 112. The patient monitoring device according to claim 110, wherein the prediction of the first temperature includes a prediction of a first temperature trajectory over a period of time. 113. The patient monitoring device according to claim 110, wherein the processor receives historical temperature data of patients under the temperature management therapy. 114. The patient monitoring device according to claim 111, wherein the processor receives historical oxygen saturation data of patients. 115. The patient monitoring device according to claim 110, wherein the temperature management therapy to the patient includes intravascular cooling of the patient. 116. The patient monitoring device according to claim 111, wherein the temperature management therapy to the patient includes surface cooling of the patient. PATENT Docket No. Z20821US-01 117. The patient monitoring device according to claim 111, wherein the processor is configured to prepare for presentation at the user interface a first graph of the patient temperature versus time, based on the prediction of the first temperature. 118. The patient monitoring device according to claim 117, wherein the processor is configured to prepare for presentation at the user interface a second graph of the patient temperature versus time, based on the prediction of the second temperature of the patient. 119. The patient monitoring device according to claim 118, wherein the first and second graphs are contiguous at time t. 120. The patient monitoring device according to claim 118, wherein the processor is configured to provide the first and second graphs in a superposed relation. 121. The patient monitoring device according to claim 111, wherein the processor is configured to predict a third temperature by manipulating the patient data to account for second temperature management therapy. 122. The patient monitoring device according to claim 111, wherein the patient data includes patient temperature. 123. The patient monitoring device according to claim 111, wherein the patient data includes SaO2, SpO2, heart rate, or blood pressure. 124. The patient monitoring device according to claim 111, wherein the processor is configured to receive a user input for the threshold temperature. 125. The patient monitoring device according to claim 111, wherein the threshold temperature is about 38 degrees Celsius. PATENT Docket No. Z20821US-01 126. The patient monitoring device according to claim 111, wherein the processor is configured to receive the patient data from at least one sensor. 127. The patient monitoring device according to claim 111, wherein the patient data includes patient temperature data over a period of about 120 minutes. 128. The patient monitoring device according to claim 126, wherein the at least one sensor is a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. 129. The patient monitoring device according to claim 111, wherein the processor is configured to receive the patient data from a patient monitor, wherein the patient monitor is coupled to one or more patient data sensors. 130. The patient monitoring device according to claim 111, wherein the processor is configured to create data including the prediction of the first temperature of the patient. 131. The patient monitoring device according to claim 130, wherein the data is stored in a cloud storage database. 132. The patient monitoring device according to claim 111, wherein the user interface is configured to be detachable from the patient monitoring device. 133. The patient monitoring device according to claim 111, wherein the user interface is configured to be wirelessly coupled to the temperature management device. 134. The patient monitoring device according to claim 111, wherein the processor is configured to communicate with a portable device. 135. The patient monitoring device according to claim 111, wherein the patient temperature management device includes a wearable device. PATENT Docket No. Z20821US-01 136. The patient monitoring device according to claim 111, wherein the processor is configured to provide temperature related events. 137. The patient monitoring device according to claim 136, wherein the temperature related events include an occurrence of shivering of the patient. 138. The patient monitoring device according to claim 136, wherein the processor is configured to predict the first temperature of the patient based on the temperature related events. 139. The patient monitoring device according to claim 111, wherein the processor is configured to create an alert for a user when the prediction of the first or second temperatures crosses a threshold temperature to enable operation of the temperature management device to be adjusted. 140. The patient monitoring device according to claim 110, further comprising a user interface configured to be communicatively coupled to a temperature management device. 141. A method of predicting patient temperature comprising: receiving, by processing circuitry, patient data from at least one sensor, the patient data representing physiologic parameters of the patient; taking into account, by the processing circuitry, at least one therapeutic intervention to predict a first temperature, wherein the at least one therapeutic intervention comprises a therapy that affects the patient’s temperature; preparing, by the processing circuitry, for presentation at a user interface, the prediction of the first temperature; and providing, by the processing circuitry, the prediction of the first temperature of the patient to the user interface. 142. The method according to claim 141, wherein taking into account the at least one therapeutic intervention comprises manipulating the patient data to account PATENT Docket No. Z20821US-01 for the at least one therapeutic intervention to predict a first temperature trajectory over a period of time. 143. The method according to claim 141, further comprising inputting a threshold temperature to create an alert when the prediction of the first temperature crosses the threshold temperature. 144. The method according to claim 141, wherein receiving patient data includes generating patient data from a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. 145. The method according to claim 141, further comprising, based on the prediction of the first temperature, preparing for presentation at the user interface, a first graph of the patient temperature versus time. 146. The method according to claim 145, further comprising manipulating the patient data to account for a second therapeutic intervention to predict a second temperature of the patient. 147. The method according to claim 146, further comprising, based on the prediction of the second temperature, preparing for presentation at the user interface, a second graph of the patient temperature versus time. 148. The method according to claim 146, further comprising providing the first and second graphs to the user interface in a superposed relation. 149. A method of predicting patient temperature comprising: receiving, by processing circuitry, patient data from at least one sensor, the patient data representing physiologic parameters of the patient; manipulating, by processing circuitry, the patient data prior to a first time to extrapolate temperature of the patient over a period of time after the first time as a first temperature prediction of the patient; PATENT Docket No. Z20821US-01 preparing, by processing circuitry, for presentation at a user interface, the first temperature prediction; and providing, by processing circuitry, the first temperature prediction of the patient to the user interface. 150. The method according to claim 149, further comprising transmitting the first temperature prediction of the patient to an external temperature management device. 151. The method according to claim 149, wherein receiving patient data includes generating patient data from a temperature sensor, a SaO2 sensor, a SpO2 sensor, a blood pressure sensor, or a heart rate sensor. 152. The method according to claim 149, further comprising inputting a threshold temperature value by a user to create an alert when the first temperature prediction crosses the threshold temperature value. 153. The method according to claim 149, further comprising, based on the first temperature prediction, preparing for presentation at the user interface, a first graph of the patient temperature versus time. 154. The method according to claim 149, further comprising manipulating the patient data to account for a therapeutic intervention to derive a second temperature prediction. 155. The method according to claim 154, further comprising, based on the second temperature prediction, preparing for presentation at the user interface, a second graph of the patient temperature versus time. 156. The method according to claim 155, further comprising providing the first and second graphs to the user interface, in a superposed relation. PATENT Docket No. Z20821US-01 157. A temperature management system for delivery of a temperature management therapy to a patient comprising: a patient monitoring device including: at least one sensor; and a controller communicatively coupled to the at least one sensor, the controller comprising a processor configured to: receive patient data from the at least one sensor; predict a first temperature of the patient from a first time with temperature management therapy applied to the patient, based on the received patient data; and transmit the prediction of the first temperature to the temperature management device. 158. The temperature management system according to claim 157, further comprising a temperature management device operatively coupled to the patient monitoring device. 159. The temperature management system according to claim 158, wherein the temperature management device is configured to adjust or maintain the temperature of the patient based on the prediction of the first temperature of the patient monitoring device. 160. The temperature management system according to claim 157, wherein the processor is configured to predict a second temperature of the patient from the first time without the temperature management therapy applied to the patient from the first time. 161. The temperature management system according to claim 157, wherein the patient monitoring device further includes a user interface. 162. The patient monitoring device according to claim 41, wherein the predicted patient temperature trajectory includes a prediction for the onset of fever. PATENT Docket No. Z20821US-01 163. The patient monitoring device according to claim 81, wherein the prediction of the first temperature includes a prediction for the onset of fever. 164. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to predict the first temperature of the patient based on the received patient data and taking into account the at least one therapeutic intervention. 165. The patient monitoring device according to claim 164, wherein the temperature prediction engine is configured to take into account a temperature difference associated with the therapeutic intervention. 166. The patient monitoring device according to claim 1, wherein the temperature prediction engine applies the patient data to a model that takes into account the at least one therapeutic intervention. 167. The patient monitoring device according to claim 166, wherein the model of the temperature prediction engine is a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. 168. The patient monitoring device according to claim 167, wherein the prior patient data sets of physiological parameters include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. 169. The patient monitoring device according to claim 167, wherein the machine learning model is trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 170. The patient monitoring device according to claim 167, wherein the machine learning model is trained on prior patient data sets of physiological PATENT Docket No. Z20821US-01 parameters without the at least one therapeutic intervention to identify temperature prediction of the patient without the at least one therapeutic intervention. 171. The patient monitoring device according to claim 170, wherein the machine learning model is trained to adjust the temperature prediction of the patient without the at least one therapeutic intervention, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 172. The patient monitoring device according to claim 1, wherein the temperature prediction engine uses machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. 173. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to manipulate the patient data to account for the at least one therapeutic intervention. 174. The patient monitoring device according to claim 1, wherein the temperature prediction engine is configured to predict a temperature trajectory of the patient based on the regression curve fit. 175. The patient monitoring device according to claim 174, wherein the temperature prediction engine is configured to manipulate the predicted temperature trajectory of the patient to account for the at least one therapeutic intervention. 176. The patient monitoring device according to claim 41, wherein the temperature prediction engine is configured to predict a first temperature of the patient based on the received patient data and taking into account at least one therapeutic intervention. PATENT Docket No. Z20821US-01 177. The patient monitoring device according to claim 176, wherein the temperature prediction engine is configured to take into account a temperature difference associated with the therapeutic intervention. 178. The patient monitoring device according to claim 41, wherein the temperature prediction engine applies the patient data to a model that takes into account at least one therapeutic intervention. 179. The patient monitoring device according to claim 178, wherein the model of the temperature prediction engine is a machine learning model trained on prior patient data sets of physiological parameters to identify a first temperature of the patient. 180. The patient monitoring device according to claim 179, wherein the prior patient data sets of physiological parameters include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. 181. The patient monitoring device according to claim 180, wherein the machine learning model is trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 182. The patient monitoring device according to claim 179, wherein the machine learning model is trained on prior patient data sets of physiological parameters without the at least one therapeutic intervention to identify temperature prediction of the patient without the at least one therapeutic intervention. 183. The patient monitoring device according to claim 182, wherein the machine learning model is trained to adjust the temperature prediction of the patient without the at least one therapeutic intervention, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. PATENT Docket No. Z20821US-01 184. The patient monitoring device according to claim 41, wherein the temperature prediction engine uses machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. 185. The patient monitoring device according to claim 41, wherein the temperature prediction engine is configured to manipulate the patient data to account for at least one therapeutic intervention. 186. The patient monitoring device according to claim 41, wherein the temperature prediction engine is configured to predict a temperature trajectory of the patient based on regression curve fit. 187. The patient monitoring device according to claim 186, wherein the temperature prediction engine is configured to manipulate the predicted temperature trajectory of the patient to account for at least one therapeutic intervention. 188. The patient monitoring device according to claim 81, wherein the temperature prediction engine is configured to predict the first temperature of the patient based on the received patient data and taking into account at least one therapeutic intervention. 189. The patient monitoring device according to claim 188, wherein the temperature prediction engine is configured to take into account a temperature difference associated with the at least one therapeutic intervention. 190. The patient monitoring device according to claim 81, wherein the temperature prediction engine applies the patient data to a model that takes into account at least one therapeutic intervention. 191. The patient monitoring device according to claim 190, wherein the model of the temperature prediction engine is a machine learning model trained on PATENT Docket No. Z20821US-01 prior patient data sets of physiological parameters to identify the first temperature of the patient. 192. The patient monitoring device according to claim 191, wherein the prior patient data sets of physiological parameters include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. 193. The patient monitoring device according to claim 192, wherein the machine learning model is trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 194. The patient monitoring device according to claim 191, wherein the machine learning model is trained on prior patient data sets of physiological parameters without the at least one therapeutic intervention to identify temperature prediction of the patient without the at least one therapeutic intervention. 195. The patient monitoring device according to claim 194, wherein the machine learning model is trained to adjust the temperature prediction of the patient without the at least one therapeutic intervention, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 196. The patient monitoring device according to claim 81, wherein the temperature prediction engine uses machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. 197. The patient monitoring device according to claim 81, wherein the temperature prediction engine is configured to manipulate the patient data to account for at least one therapeutic intervention. PATENT Docket No. Z20821US-01 198. The patient monitoring device according to claim 81, wherein the temperature prediction engine is configured to predict a temperature trajectory of the patient based on regression curve fit. 199. The patient monitoring device according to claim 198, wherein the temperature prediction engine is configured to manipulate the predicted temperature trajectory of the patient to account for at least one therapeutic intervention. 200. The patient monitoring device according to claim 110, wherein the temperature prediction engine applies the patient data to a model that takes into account the temperature management therapy. 201. The patient monitoring device according to claim 200, wherein the model of the temperature prediction engine is a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. 202. The patient monitoring device according to claim 201, wherein the prior patient data sets of physiological parameters include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. 203. The patient monitoring device according to claim 201, wherein the machine learning model is trained on prior patient data sets of physiological parameters associated with the temperature management therapy. 204. The patient monitoring device according to claim 201, wherein the machine learning model is trained on prior patient data sets of physiological parameters without the temperature management therapy to identify temperature prediction of the patient without the temperature management therapy. 205. The patient monitoring device according to claim 204, wherein the machine learning model is trained to adjust the temperature prediction of the patient PATENT Docket No. Z20821US-01 without the temperature management therapy, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the temperature management therapy. 206. The patient monitoring device according to claim 110, wherein the temperature prediction engine uses machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. 207. The patient monitoring device according to claim 110, wherein the temperature prediction engine is configured to manipulate the patient data to account for the temperature management therapy. 208. The patient monitoring device according to claim 110, wherein the temperature prediction engine is configured to predict a temperature trajectory of the patient based on the regression curve fit. 209. The patient monitoring device according to claim 208, wherein the temperature prediction engine is configured to manipulate the predicted temperature trajectory of the patient to account for the temperature management therapy. 210. The method according to claim 141, wherein taking into account the at least one therapeutic intervention includes applying the patient data to a model that takes into account the at least one therapeutic intervention. 211. The method according to claim 210, wherein the model is a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. 212. The method according to claim 211, wherein the prior patient data sets of physiological parameters include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. PATENT Docket No. Z20821US-01 213. The method according to claim 212, wherein the machine learning model is trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 214. The method according to claim 212, wherein the machine learning model is trained on prior patient data sets of physiological parameters without the temperature management therapy to identify temperature prediction of the patient without the at least one therapeutic intervention. 215. The method according to claim 212, wherein the machine learning model is trained to adjust the temperature prediction of the patient without the temperature management therapy, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 216. The method according to claim 214, wherein the machine learning model uses machine learning analysis including a convolutional neural network (CNN), deep neural network (DNN), clustering tree, or synaptic learning network. 217. The method according to claim 149, wherein manipulating the patient data includes applying the patient data to a model that takes into account the at least one therapeutic intervention. 218. The method according to claim 210, wherein the model is a machine learning model trained on prior patient data sets of physiological parameters to identify the first temperature of the patient. 219. The method according to claim 211, wherein the prior patient data sets of physiological parameters include at least one of measured historical temperature, historical SaO2, historical SpO2, historical blood pressure, historical heart rate, and historical respiratory rate of patients. PATENT Docket No. Z20821US-01 220. The method according to claim 212, wherein the machine learning model is trained on prior patient data sets of physiological parameters associated with the at least one therapeutic intervention. 221. The method according to claim 212, wherein the machine learning model is trained on prior patient data sets of physiological parameters without the temperature management therapy to identify temperature prediction of the patient without the at least one therapeutic intervention. 222. The method according to claim 212, wherein the machine learning model is trained to adjust the temperature prediction of the patient without the temperature management therapy, to identify the first temperature of the patient by taking into account prior patient data sets of physiological parameters associated with the at least one therapeutic intervention.