CN113793661A - Intelligent monitoring and early warning system for traumatic hemorrhagic shock - Google Patents
Intelligent monitoring and early warning system for traumatic hemorrhagic shock Download PDFInfo
- Publication number
- CN113793661A CN113793661A CN202110850563.XA CN202110850563A CN113793661A CN 113793661 A CN113793661 A CN 113793661A CN 202110850563 A CN202110850563 A CN 202110850563A CN 113793661 A CN113793661 A CN 113793661A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- wounded
- management module
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 56
- 208000032456 Hemorrhagic Shock Diseases 0.000 title claims abstract description 38
- 206010049771 Shock haemorrhagic Diseases 0.000 title claims abstract description 38
- 230000000472 traumatic effect Effects 0.000 title claims abstract description 26
- 238000007726 management method Methods 0.000 claims abstract description 60
- 230000000007 visual effect Effects 0.000 claims abstract description 21
- 238000010801 machine learning Methods 0.000 claims abstract description 15
- 238000013524 data verification Methods 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims abstract description 6
- 239000003086 colorant Substances 0.000 claims abstract description 5
- 230000035939 shock Effects 0.000 claims description 25
- 208000014674 injury Diseases 0.000 claims description 14
- 230000008733 trauma Effects 0.000 claims description 13
- 230000004872 arterial blood pressure Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000012800 visualization Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 33
- 238000010586 diagram Methods 0.000 description 15
- 230000008901 benefit Effects 0.000 description 9
- 201000010099 disease Diseases 0.000 description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 8
- 238000000034 method Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000035487 diastolic blood pressure Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000035488 systolic blood pressure Effects 0.000 description 2
- 108010064719 Oxyhemoglobins Proteins 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 229910052697 platinum Inorganic materials 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000008736 traumatic injury Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- General Engineering & Computer Science (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides an intelligent monitoring and early warning system for traumatic hemorrhagic shock, which comprises: the user information management module manages the user information; the wounded information management module manages the wounded information; the prediction management module calls corresponding prediction models to perform prediction under a specific time window according to the selected different time windows; the prediction management module calls a machine learning module to predict data, and the prediction management module comprises the following steps: selecting a time window, acquiring data, checking the data and predicting the data; the data verification is to verify the wounded information, call a machine learning model integrated in a background to predict, and return a prediction result; the monitoring management module automatically calls wounded data from the background to predict, and then real-time monitoring on information of a plurality of wounded is realized; the visual display module displays the state of the wounded by using different colors according to different prediction results, and draws a corresponding chart to display the change condition of the indexes of the wounded.
Description
Technical Field
The invention relates to the technical field of software, in particular to an intelligent monitoring and early warning system for traumatic hemorrhagic shock.
Background
In the medical field, trauma is the main cause of death between 1 year and 45 years, traumatic injury is often accompanied by hemorrhagic shock, Traumatic Hemorrhagic Shock (THS) is one of the main causes of death of trauma patients and is the largest potential preventable factor, trauma patients often have the characteristics of complicated and variable diseases and rapid development, hemorrhagic shock is difficult to identify in the early stage, and the death rate of patients once suffering from the diseases is extremely high. In the first aid of wounded patients, the time factor is very critical, and the field of wound first aid is mainly said to be 'platinum ten minutes, gold one hour', so that after medical care personnel receive and treat patients, the medical care personnel are required to quickly know various index conditions of the wounded patients, make preliminary analysis and judgment and make medical treatment decision. Under the background of 'big health' of the whole people, methods such as data mining, machine learning and the like are widely applied in various medical branch fields.
Disclosure of Invention
The object of the present invention is to solve at least one of the technical drawbacks mentioned.
Therefore, the invention aims to provide an intelligent monitoring and early warning system for traumatic hemorrhagic shock.
In order to achieve the above object, an embodiment of the present invention provides an intelligent monitoring and early warning system for traumatic hemorrhagic shock, which includes a user information management module, a wounded information management module, a prediction management module, a monitoring management module, and a visual display module, wherein,
the user information management module is used for managing user information and comprises: user registration and user login;
the wounded information management module is used for managing the wounded information and comprises: adding wounded information and inquiring the wounded information;
the prediction management module is used for calling corresponding prediction models according to the selected different time windows to predict under a specific time window, and the prediction management module calls corresponding machine learning modules to predict data, and the prediction management module comprises: selecting a time window, acquiring data, checking the data and predicting the data, wherein the data acquired by the data acquisition wearable device is directly imported; the data verification is the verification of wounded information, the prediction management calls a machine learning model integrated in a background to predict according to each piece of recorded data, and a prediction result is returned;
the monitoring management module is used for automatically calling wounded personnel data from a background to predict, and further realizes real-time monitoring on information of a plurality of wounded personnel at the same time;
the visual display module is used for displaying the state of the wounded by using different colors according to different prediction results and drawing a corresponding chart to display the change condition of the indexes of the wounded.
Furthermore, the prediction management module receives message data from the MQTT server, analyzes the message data, obtains the numerical value of the required vital sign index, stores the numerical value in a database field corresponding format, and displays the output result to the user through the visual display module.
Further, the prediction management module performs data verification, including: carrying out data verification by taking the age, the shock index and the mean arterial pressure of the patient as judgment standards; the prediction management module calls patient information from a database, and calculates a shock index and an average arterial pressure according to a recorded data index; and displaying the patient information, prompting the condition that the data do not meet the conditions, and declaring the influence of the data which do not meet the standard on the prediction result.
Further, the prediction management module performs a time window selection, including: and according to the received time window selected by the front-end user, transmitting a time window selection result instruction to the background, and providing a prediction model interface under the specific time window by the background for subsequent data prediction under the specific time window.
Further, the prediction management module performs data prediction, including: taking a machine learning algorithm as an inner core, carrying out prediction analysis on existing data or real-time data flow to generate a prediction result, storing the prediction result in a database and feeding back the prediction result to a webpage end; and displaying the prediction result in a real-time prediction state.
Furthermore, the monitoring management module dynamically predicts all wounded persons in real time and returns the wounded persons to a front-end page, and displays whether the wounded persons are subjected to shock prediction through an algorithm and the probability of the shock prediction through a dynamic data table; and a visual display module; the monitoring management module receives index data from a plurality of intelligent acquisition devices corresponding to a plurality of sick and wounded, stores the index data into the database according to the received time sequence, reads data from the database, calls the model to predict, outputs a prediction result, outputs a dynamic data table of a monitoring page through the visual display module, presents a sick and wounded list and the prediction result, and updates the prediction result in real time according to the received data.
Further, the visualization display module displays the vital sign data, the shock index and the calculated data of the mean arterial pressure by using an echarts chart.
Further, the visual display module changes in real time in the form of matching of indicator lights and text description, and presents the state of the patient on a monitoring page.
The intelligent monitoring and early warning system for the hemorrhagic shock of the trauma, provided by the embodiment of the invention, has the following beneficial effects:
in the aspect of index collection and data acquisition, along with the development of technologies such as sensors and artificial intelligence in the fields such as medical equipment, wearable equipment can realize gathering simple and easy medical index, and these equipment rely on advantages such as small, convenient to carry, data transmission are timely and incessant, are accepted by more and more use scenes. In practice, wearable devices can produce large amounts of high quality real-time data compared to traditional medical index acquisition devices, and therefore have greater research value in big data analysis. In the aspect of indexes, the wearable equipment can be used for rapidly acquiring physiological data such as vital signs in time without the support of large-scale medical equipment and only needs to be worn, so that the wearable equipment has the characteristics of simplicity and rapidness. For the prediction of the traumatic hemorrhagic shock, the more easily the used index is collected, the more quickly the prediction can be realized, and the wearable equipment can dynamically monitor continuous data, thereby providing possibility for the dynamic prediction of the traumatic hemorrhagic shock.
In the aspect of disease prediction, the machine learning algorithm has great advantages in the aspect of disease prediction by virtue of the advantages of high efficiency, good precision and the like. However, only the algorithm model is the first step, and if the algorithm model can be integrated into the information system, the actual scene can be further approximated. The existing intelligent aid decision support system for predicting diseases is less, and the system resource capable of intelligently monitoring traumatic hemorrhagic shock is more scarce.
The non-functional requirements of the intelligent monitoring and early warning system for the hemorrhagic shock of the trauma provided by the embodiment of the invention are as follows: non-functional requirements are also important components, which can ensure that functional requirements work properly. The method mainly comprises the performance requirement, the safety requirement, the easy operability requirement, the flexibility requirement and the like of the system. The system has the practicability and stability on the basis of having the basic functions only by meeting the non-functional requirements.
(1) Performance of
The order of magnitude of the background of the system is considered, and the corresponding time requirement of user operation is met. The system performance indexes such as response time, resource utilization rate and the number of clicks need to be comprehensively considered according to actual conditions. In the present system, the prediction for each piece of data is typically no more than 3 seconds, and the time for data transmission is within the user's acceptable range.
(2) Safety feature
The security of data is important for systems and even more important for medical related systems. In the aspect of software, the system has enough confidentiality, avoids data leakage, controls the authority of a user and the like. In terms of hardware, a corresponding vendor should provide a solution in the event of a failure.
(3) Easy operability
The main users of the system are medical staff, and the use scenes are usually urgent, so the system needs to consider the simplicity of operation, such as concise page, simple and convenient operation, intuitive display and the like. And the use flow of the system needs to be simple and easy, and the system should not be excessively complicated.
(4) Flexibility
In view of the sophistication and complexity of the medical scenario, some functional modules of the system may be updated and the configuration of the system should be as flexible as possible so that the system has a scalable space. Meanwhile, when interfaces exist with other systems or the existing interfaces are changed, the target can be finished only by making proper adjustment.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a structural diagram of an intelligent monitoring and early warning system for hemorrhagic shock in trauma according to an embodiment of the invention;
FIG. 2 is a schematic diagram of user information management according to an embodiment of the present invention;
FIG. 3 is a schematic illustration of triage information management according to an embodiment of the invention;
FIG. 4 is a diagram illustrating prediction management according to an embodiment of the present invention;
FIG. 5 is a schematic illustration of monitoring management according to an embodiment of the invention;
FIG. 6 is a schematic diagram of a user registration page according to an embodiment of the invention;
FIG. 7 is a schematic diagram of a user login page according to an embodiment of the present invention;
FIG. 8 is a schematic view of adding a sick and wounded panel according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a list of patient information according to an embodiment of the invention;
FIG. 10 is a schematic diagram of a sick and wounded query according to an embodiment of the present invention;
FIG. 11 is a diagram illustrating the selection of a time window according to an embodiment of the present invention;
FIG. 12 is a schematic illustration of manually entering data according to an embodiment of the present invention;
FIG. 13 is a diagram illustrating a data verification popup according to an embodiment of the present invention;
FIG. 14 is a schematic diagram of a prediction details page according to an embodiment of the present invention;
FIG. 15 is a schematic diagram of a smart monitor page according to an embodiment of the invention;
FIGS. 16a and 16b are schematic diagrams of dynamic graphs according to embodiments of the present invention;
FIG. 17 is a diagram of a predictive information panel, according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The invention provides an intelligent monitoring and early warning system for hemorrhagic shock of trauma, which has the following characteristics:
firstly, wearable equipment is used as a scene, and modeling is carried out through a machine learning algorithm by utilizing five indexes of heart rate, systolic pressure, diastolic pressure, respiration and blood oxygen saturation. The early identification, early diagnosis and early treatment of the patients with the traumatic hemorrhagic shock can be realized by carrying out early prediction and early warning on the fate of the patients with the traumatic hemorrhagic shock.
Then, on the basis of excellent model effect, the model is integrated into the system, so that the model has a specific use carrier, an intelligent monitoring and early warning system for traumatic hemorrhagic shock is constructed, and users such as medical workers can more conveniently enjoy benefits brought by the prediction model.
The research object is a traumatic hemorrhagic shock intelligent monitoring and early warning system, and the user who uses the system to the greatest extent is medical personnel. Medical personnel can use this system input wounded's medical index (rhythm of the heart, systolic pressure, diastolic pressure, breathing, oxyhemoglobin saturation) data, carry out the prediction of the quick result of traumatic hemorrhagic shock wounded to supplementary medical personnel realize the quick classification to wounded, improve diagnostic efficiency and medical resource's utilization ratio.
As shown in fig. 1, the intelligent monitoring and early warning system for traumatic hemorrhagic shock in the embodiment of the present invention comprises: the system comprises a user information management module 1, a wounded information management module 2, a prediction management module 3, a monitoring management module 4 and a visual display module 5.
Specifically, as shown in fig. 2, the user information management module 1 is configured to manage user information, and includes: user registration and user login.
(1) User registration:
description of the function:
to use the system, a valid account must first be created.
The user normally fills in the registered user name, password and mailbox information in the form, selects gender and finishes the registration after confirming the correct submission, as shown in fig. 6.
The function is realized:
inputting: the user fills in a user name, a password and a mailbox through a form displayed on the front-end web page, and selects gender.
And (3) treatment: the front end firstly completes the integrity and normalization check of the form, and if the check is not passed (for example, the form data is not completely filled, the mailbox filling does not conform to the mailbox format, and the like), a popup window is returned to prompt the user to supplement information or refill the information. And if the user name is occupied, returning to prompt the user to refill the user name, otherwise, passing the registration.
And (3) outputting: and the front page pops up to prompt the user that the registration is successful, and jumps to a login interface, so that the user can enter the system after logging in.
Exception handling:
and if the filled user name exists, returning to a popup window to prompt the user to refill.
If the passwords filled in twice are inconsistent, returning to the popup window to prompt the user to refill.
And returning to a popup window to prompt the user to refill the user name and the mailbox which are filled in are not in accordance with the specification.
(2) User login:
description of the function: the system is used by internal users, without guest roles, and therefore must log into an account when entering the system, as shown in fig. 7.
The user can log in the system and enter the system to use the functions of the system after correctly filling in the user name and the password which are successfully registered on the form and submitting the user name and the password.
The function is realized:
inputting: the user fills in a username and password and selects "login" through a form presented on the front-end web page.
And (3) treatment: the front end firstly completes the integrity and normalization check of the form, and if the check fails (such as the user name or the password is not completely filled or the user name exceeds the maximum limit), a popup prompt error is returned, and the user needs to refill the form. If the front end passes the verification, the data is transmitted to a background, whether the user name and the password are consistent with the storage in the database or not is checked, if not, a popup window prompting error is returned, and the user needs to refill the popup window; if the data are consistent, the login is successful, and the system is entered.
And (3) outputting: and the front-end page pops up to prompt the user that the login is successful, and jumps to the internal page of the system.
Exception handling:
and if the user name and the password are not completely filled, returning to a popup window to prompt the user to fill in the user name and the password.
And if the filled user name and password are incorrect, returning to a popup window to prompt the user to refill.
As shown in fig. 3, the wounded information management module 2 is used for managing wounded information, and includes: wounded information addition and wounded information query. That is, the wounded information needs to be added before prediction is performed, and the wounded information may be searched as needed.
(1) Adding wounded parts
Description of the function: the system supports the function of "adding sick and wounded".
The user can fill in the number, name, age, telephone and sex of the wounded in the form of the page, and the adding of the wounded can be completed by clicking the adding. In the contents of the form, the wounded number, name and age must be filled in, and the rest may not be filled in, as shown in fig. 8.
The function is realized:
inputting: the user enters the sick and wounded information through the form of the page.
And (3) treatment: the background receives the information of the sick and wounded from the front end, processes the information into a corresponding format and stores the information into a corresponding database table of the background. The background can check the uniqueness of the wounded number, if not, the background prompts the user to re-input the wounded number, and if the number is unique, the data insertion is completed.
And (3) outputting: the prompt popup for "add success" is windowed and the added victim information is updated in the upper victim list, as shown in fig. 9.
Exception handling:
the filled-in form is incomplete, such as missing wounded number, and the user is prompted that the filling-in must be supplemented.
The field uniqueness conflicts, the wounded person number is required to have uniqueness, and if the number is not unique, the user is prompted to re-input.
(2) Searching wounded person
Description of the function:
the sick and wounded information is displayed in a form of a data table on a front-end web page, and the data table is returned to a background database. When there are many sick and wounded, it is very inconvenient to directly search for a certain sick and wounded from the data table, so a functional module of "sick and wounded retrieval" is added, and the user can input the number or name of the sick and wounded in the upper search box, i.e. the sick and wounded in the list can be searched, as shown in fig. 10.
The function is realized:
inputting: the user inputs a complete wounded number in the first search box and clicks 'search'; or enter the complete patient name in a second search box and click "search".
And (3) treatment: and transmitting the data input by the user to the background, retrieving the data (the number or name of the sick and wounded) according to conditions, returning the result and transmitting the result to the front-end page.
And (3) outputting: and returning the searched sick and wounded according to the search condition, and displaying the sick and wounded in a data table of the page.
Exception handling: if the wounded number or name input by the user does not exist, the empty table is returned.
The prediction management module 3 is configured to invoke corresponding prediction models to perform prediction in a specific time window according to the selected different time windows, and includes: time window selection, data acquisition, data check and data prediction, wherein, in the aspect of the data acquisition, can directly import through the data that wearable equipment that have protocols such as MQTT gathered, can also carry out manual entry through medical personnel. The data check is a check on basic information of the wounded, such as whether the basic information meets the inclusion and exclusion criteria. And the prediction is carried out by calling a machine learning model integrated in the background according to each piece of recorded data and returning a prediction result to an interface.
Specifically, as shown in fig. 4, the prediction management module 3 receives message data from the MQTT server, analyzes the message data, obtains a numerical value of a required vital sign index, stores the numerical value in a database field corresponding format, and displays an output result to a user by the visual display module 5.
(1) Time window selection
Description of the function:
and according to the received time window selected by the front-end user, transmitting a time window selection result instruction to the background, and providing a prediction model interface under the specific time window by the background for subsequent data prediction under the specific time window. And selecting a time window required for prediction from a drop-down frame of the pop-up window by a user according to actual prediction requirements, wherein in the prediction of the traumatic hemorrhagic shock, the time window is 'how much time the traumatic hemorrhagic shock can occur'. The system obtains the content selected by the user from the front end selected by the user, and transmits the content to the background so as to adapt to the subsequent prediction and provide a corresponding time window model. As shown in fig. 11.
The function is realized:
inputting: user selection (input) of data from the front end page.
And (3) treatment: acquiring front-end data and transmitting the front-end data to a background, and selecting and setting a corresponding model path by the background according to the received data content for calling in prediction.
And (3) outputting: the system adapts to the corresponding time window model and no output is presented to the user.
(2) Automatic data acquisition
Description of the function: the data collected by the data collecting device reach the MQTT server through publishing, the system server subscribes data to the MQTT server by an appointed theme, the data is sent and received in a message form, and is processed in a background under the state that the user operation is not influenced, so that the user can not see the data in the process. The processing procedure mainly includes decoding the message and putting the message into a database in an acceptable format and frequency.
The function is realized:
inputting: message data from the MQTT server.
And (3) treatment: and analyzing the message data, acquiring the numerical values of indexes such as the required vital signs and the like, and warehousing the numerical values in a format corresponding to the database fields.
And (3) outputting: no output may be presented to the user.
Exception handling:
when a certain index of the message is null after transcoding, the message is replaced by a null character string and then stored in a database.
When the communication with the MQTT server is interrupted, a reconnection request is initiated in a circulating mode.
(3) Manual data entry
Description of the function: aiming at the scenes that data cannot be automatically loaded (such as the situation that a data acquisition device cannot be accessed or network conditions cannot be supported), the system provides a data manual entry function. The user can enter data in the index manual entry interface and view the data entered in the prediction, as shown in fig. 12.
The function is realized:
inputting: the manually input index data of vital signs and the like is one at a time, and the acquisition time needs to be filled.
And (3) treatment: and storing a database of the index data, and inquiring the database of the input data of the prediction.
And (3) outputting: one or more pieces of index data are shown in tabular form.
Exception handling: the index data is in a numerical value format, and entry of illegal characters is refused.
(4) Data verification
The prediction management module 3 performs data verification, including: carrying out data verification by taking the age, the shock index and the mean arterial pressure of the patient as judgment standards; the prediction management module 3 calls patient information from a database, and calculates a shock index and an average arterial pressure according to the recorded data indexes; and displaying the patient information, prompting the condition that the data do not meet the conditions, and declaring the influence of the data which do not meet the standard on the prediction result.
Description of the function: in the data verification link, the core function provided by the system is data verification using patient age, Shock Index (SI), mean arterial pressure (MBP) as the criteria, as shown in fig. 13.
The function is realized:
inputting: no manual input of information by the user is required.
And (3) treatment: and calling patient information from the database, and calculating the SI and MBP according to the input data indexes.
And (3) outputting: and displaying the basic information of the patient, prompting the condition that the data does not meet the conditions (the green standard is met, and the red standard is not met), and declaring the possible influence of the data which does not meet the standards on the prediction result.
Exception handling: is free of
(5) Data prediction
The prediction management module 3 performs data prediction, and comprises: taking a machine learning algorithm as an inner core, carrying out prediction analysis on existing data or real-time data flow to generate a prediction result, storing the prediction result in a database and feeding back the prediction result to a webpage end; and displaying the prediction result in a real-time prediction state.
Description of the function: the prediction function is a system core function, a machine learning algorithm is used as an inner core, and prediction analysis is carried out on existing data or real-time data flow. In the web panel, the system presents the patient basic information, medical information, index data, and prediction information, as shown in fig. 14.
The function is realized:
inputting: no manual input of information by the user is required.
And (3) treatment: and calling the trained prediction model by the background, predicting the existing data or the real-time data stream, generating a prediction result, storing the prediction result in the database and feeding back the prediction result to the webpage end.
And (3) outputting:
in the real-time prediction state, the indicator lamp continuously flickers to represent that prediction is continuously carried out, the prediction result is displayed behind the indicator lamp, green and red are used for distinguishing safety from shock, and the prediction result is presented in a format of that the probability that the patient XX is expected to generate shock in the selected time window is as follows: XXXXX ".
Exception handling: in the real-time prediction process, information such as prediction operation errors and insufficient data volume is fed back, and subsequent prediction is not influenced.
As shown in fig. 5, the monitoring management module 4 is configured to automatically retrieve the wounded data from the background for prediction, so as to implement real-time monitoring on information of multiple wounded persons at the same time. The monitoring function is to predict a plurality of wounded person data simultaneously, does not need medical personnel to independently type in data, and the system can constantly automatic call data from the backstage and predict to play real-time supervision's effect.
(1) Intelligent monitoring
Specifically, the monitoring management module 4 dynamically predicts all wounded persons in real time and returns the predicted wounded persons to a front-end page, and displays whether the wounded persons are subjected to shock prediction and the probability of shock prediction through an algorithm through a dynamic data table; and is displayed by the visual display module 5; the monitoring management module 4 receives index data from a plurality of intelligent acquisition devices corresponding to a plurality of sick and wounded, stores the index data into the database according to the received time sequence, reads data from the database, calls the model to predict, outputs a prediction result, outputs a dynamic data table of a monitoring page through the visual display module 5, presents a sick and wounded list and the prediction result, and updates the prediction result in real time according to the received data.
Description of the function: in many cases, the user needs to quickly locate the patient at risk of shock, and therefore it is desirable to be able to monitor all the patients participating in the test on one page. The detection function can predict all wounded persons dynamically in real time and return to a front-end page, information such as whether the wounded persons can generate shock or not through algorithm prediction and probability of generating shock is displayed through dynamic data table display, and the information is prompted through red and green visualization module icons. There is also a "view details" button in the last column of each row that the user can click on to enter the predicted results page for the sick and wounded to view the index data details, as shown in FIG. 15.
The function is realized:
inputting: the user does not need to enter at this page.
And (3) treatment: the background continuously receives index data from a plurality of intelligent acquisition devices corresponding to a plurality of sick and wounded, stores the index data into the database according to the received time sequence, reads the data from the database, calls the model to predict, and outputs a prediction result (whether shock occurs and the probability of shock occurrence).
And (3) outputting: and the dynamic data table of the monitoring page presents a sick and wounded list, a prediction result (whether shock or not and shock probability) and a state icon of the sick and wounded list, and updates the prediction result in real time according to the received data.
Exception handling:
no data is returned. The page is stuck or the received data does not meet the model operation requirement (for example, the received index data is incomplete and cannot call the model for calculation)
And no data of the form is updated. The data transmission of the sick and wounded is interrupted or the data transmission caused by the falling of the intelligent acquisition equipment is stopped.
The alert icon is not loaded or changed. Typically due to page jams.
(2) Detail checking
Description of the function: the user can see the prediction information of all the sick and wounded on the intelligent detection page, and needs to view detailed index data of a certain sick and wounded, and then can enter the detail page of the sick and wounded to view through the 'view details' button.
The function is realized:
inputting: the user realizes the background input of the id of the selected sick and wounded and the clicked time stamp by clicking a 'view details' button corresponding to a certain sick and wounded.
And (3) treatment: and the background receives the sick and wounded serial number and the time stamp of the clicking time selected by the user, retrieves a prediction result page entering the corresponding sick and wounded, and intercepts a data calling model after the time stamp for prediction by taking the received time stamp as a boundary.
And (3) outputting: and entering a result page for selecting the sick and wounded.
Exception handling:
and the result page has no data after the jump. Generally, due to the fact that data transmission is interrupted, no new data is transmitted to the sick and wounded person after clicking 'view details', and then the prediction module cannot be executed continuously.
The visual display module 5 is used for displaying the state of the wounded by using different colors according to different prediction results, and drawing a corresponding chart to display the change condition of the indexes of the wounded.
The visualization mainly acts on a user interface of the system, and the user experience can be improved through visual display. In the system, the state of the wounded can be displayed by different colors according to different prediction results, and a corresponding chart can be drawn to show the change condition of the indexes of the wounded. On the monitoring page, tables of different wounded person index data can be displayed, and states can also be displayed according to the visual control, such as indicator light flickering and the like.
(1) Index real-time monitoring dynamic chart
A visualization module of the system displays original data such as vital signs and the like and calculated data such as MBP, SI and the like by using an echarts chart. The vital sign curve dynamically extends along with the loading of real-time data, and the threshold value is marked by a red line, so that the visual judgment of a user is facilitated. The MBP and SI curves are dynamically presented through real-time calculation, and the change trend is clear at a glance. Fig. 16a and 16b are schematic diagrams of dynamic charts according to an embodiment of the present invention.
(2) Display of predicted results
The prediction result is changed in real time in a form that the indicator light is matched with the text description, and the method is green, safe and early-warning in red.
(3) Monitoring patient status
The monitoring page describes the patient state in a list, mostly in a concise and intuitive way with a set of icons. When the background model predicts that the patient is not shocked, the status bar displays a green static identifier; when the patient is predicted not to be in shock, the status bar red warning icon flashes, and the patient information is set top in the list. FIG. 17 is a diagram of a predictive information panel, according to an embodiment of the invention.
The operation environment of the intelligent monitoring and early warning system for the hemorrhagic shock of the trauma provided by the embodiment of the invention is as follows:
hardware: a CPU: intel binuclear @2.50GHz or above; hard disk: 40G or more; memory: 1G or more;
a display: resolution 1024 x 768 or more; peripheral equipment: USB interface, keyboard and mouse; network bandwidth: requires 512K of bandwidth; more than 2M is recommended; remote terminal services are not supported; therefore, the system cannot be used for a server and only can use software through a local console; operating the system: windows7/Windows8/Windows10 are supported, including 32-bit and 64-bit versions.
The intelligent monitoring and early warning system for the hemorrhagic shock of the trauma, provided by the embodiment of the invention, has the following beneficial effects:
in the aspect of index collection and data acquisition, along with the development of technologies such as sensors and artificial intelligence in the fields such as medical equipment, wearable equipment can realize gathering simple and easy medical index, and these equipment rely on advantages such as small, convenient to carry, data transmission are timely and incessant, are accepted by more and more use scenes. In practice, wearable devices can produce large amounts of high quality real-time data compared to traditional medical index acquisition devices, and therefore have greater research value in big data analysis. In the aspect of indexes, the wearable equipment can be used for rapidly acquiring physiological data such as vital signs in time without the support of large-scale medical equipment and only needs to be worn, so that the wearable equipment has the characteristics of simplicity and rapidness. For the prediction of the traumatic hemorrhagic shock, the more easily the used index is collected, the more quickly the prediction can be realized, and the wearable equipment can dynamically monitor continuous data, thereby providing possibility for the dynamic prediction of the traumatic hemorrhagic shock.
In the aspect of disease prediction, the machine learning algorithm has great advantages in the aspect of disease prediction by virtue of the advantages of high efficiency, good precision and the like. However, only the algorithm model is the first step, and if the algorithm model can be integrated into the information system, the actual scene can be further approximated. The existing intelligent aid decision support system for predicting diseases is less, and the system resource capable of intelligently monitoring traumatic hemorrhagic shock is more scarce.
The non-functional requirements of the intelligent monitoring and early warning system for the hemorrhagic shock of the trauma provided by the embodiment of the invention are as follows: non-functional requirements are also important components, which can ensure that functional requirements work properly. The method mainly comprises the performance requirement, the safety requirement, the easy operability requirement, the flexibility requirement and the like of the system. The system has the practicability and stability on the basis of having the basic functions only by meeting the non-functional requirements.
(1) Performance of
The order of magnitude of the background of the system is considered, and the corresponding time requirement of user operation is met. The system performance indexes such as response time, resource utilization rate and the number of clicks need to be comprehensively considered according to actual conditions. In the present system, the prediction for each piece of data is typically no more than 3 seconds, and the time for data transmission is within the user's acceptable range.
(2) Safety feature
The security of data is important for systems and even more important for medical related systems. In the aspect of software, the system has enough confidentiality, avoids data leakage, controls the authority of a user and the like. In terms of hardware, a corresponding vendor should provide a solution in the event of a failure.
(3) Easy operability
The main users of the system are medical staff, and the use scenes are usually urgent, so the system needs to consider the simplicity of operation, such as concise page, simple and convenient operation, intuitive display and the like. And the use flow of the system needs to be simple and easy, and the system should not be excessively complicated.
(4) Flexibility
In view of the sophistication and complexity of the medical scenario, some functional modules of the system may be updated and the configuration of the system should be as flexible as possible so that the system has a scalable space. Meanwhile, when interfaces exist with other systems or the existing interfaces are changed, the target can be finished only by making proper adjustment.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The utility model provides a traumatic hemorrhagic shock intelligent monitoring early warning system which characterized in that includes: a user information management module, a wounded information management module, a prediction management module, a monitoring management module and a visual display module,
the user information management module is used for managing user information and comprises: user registration and user login;
the wounded information management module is used for managing the wounded information and comprises: adding wounded information and inquiring the wounded information;
the prediction management module is used for calling corresponding prediction models according to the selected different time windows to predict under a specific time window, and the prediction management module calls corresponding machine learning modules to predict data, and the prediction management module comprises: selecting a time window, acquiring data, checking the data and predicting the data, wherein the data acquired by the data acquisition wearable device is directly imported; the data verification is the verification of wounded information, the prediction management calls a machine learning model integrated in a background to predict according to each piece of recorded data, and a prediction result is returned;
the monitoring management module is used for automatically calling wounded personnel data from a background to predict, and further realizes real-time monitoring on information of a plurality of wounded personnel at the same time;
the visual display module is used for displaying the state of the wounded by using different colors according to different prediction results and drawing a corresponding chart to display the change condition of the indexes of the wounded.
2. The intelligent monitoring and early warning system for traumatic hemorrhagic shock as recited in claim 1, wherein the prediction management module receives message data from the MQTT server, analyzes the message data to obtain a numerical value of a required vital sign index, stores the numerical value in a database field corresponding format, and displays an output result to a user by the visual display module.
3. The intelligent monitoring and warning system for traumatic hemorrhagic shock of claim 1, wherein the prediction management module performs data verification comprising: carrying out data verification by taking the age, the shock index and the mean arterial pressure of the patient as judgment standards; the prediction management module calls patient information from a database, and calculates a shock index and an average arterial pressure according to a recorded data index; and displaying the patient information, prompting the condition that the data do not meet the conditions, and declaring the influence of the data which do not meet the standard on the prediction result.
4. The intelligent monitoring and warning system for traumatic hemorrhagic shock of claim 1, wherein the prediction management module performs time window selection comprising: and according to the received time window selected by the front-end user, transmitting a time window selection result instruction to the background, and providing a prediction model interface under the specific time window by the background for subsequent data prediction under the specific time window.
5. The intelligent monitoring and early warning system for hemorrhagic shock in trauma according to claim 1, wherein the prediction management module performs data prediction comprising: taking a machine learning algorithm as an inner core, carrying out prediction analysis on existing data or real-time data flow to generate a prediction result, storing the prediction result in a database and feeding back the prediction result to a webpage end; and displaying the prediction result in a real-time prediction state.
6. The intelligent monitoring and early warning system for traumatic hemorrhagic shock as claimed in claim 1, wherein the monitoring and management module dynamically predicts all wounded persons in real time and returns the predicted wounded persons to a front page, and displays whether the wounded persons are subjected to shock or not and the probability of shock through algorithm prediction through a dynamic data table; and a visual display module; the monitoring management module receives index data from a plurality of intelligent acquisition devices corresponding to a plurality of sick and wounded, stores the index data into the database according to the received time sequence, reads data from the database, calls the model to predict, outputs a prediction result, outputs a dynamic data table of a monitoring page through the visual display module, presents a sick and wounded list and the prediction result, and updates the prediction result in real time according to the received data.
7. The intelligent monitoring and early warning system for hemorrhagic shock in trauma according to claim 1, wherein the visualization display module uses an echarts chart to display the vital sign data, the shock index and the calculated data of mean arterial pressure.
8. The intelligent monitoring and early warning system for hemorrhagic shock in trauma as claimed in claim 1, wherein the visual display module changes in real time in the form of an indicator light matched with a text description and presents the state of the patient on a monitoring page.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110850563.XA CN113793661A (en) | 2021-07-27 | 2021-07-27 | Intelligent monitoring and early warning system for traumatic hemorrhagic shock |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110850563.XA CN113793661A (en) | 2021-07-27 | 2021-07-27 | Intelligent monitoring and early warning system for traumatic hemorrhagic shock |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113793661A true CN113793661A (en) | 2021-12-14 |
Family
ID=78876946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110850563.XA Pending CN113793661A (en) | 2021-07-27 | 2021-07-27 | Intelligent monitoring and early warning system for traumatic hemorrhagic shock |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113793661A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017218431A1 (en) * | 2016-06-13 | 2017-12-21 | Flashback Technologies, Inc. | Rapid detection of bleeding following injury |
| CN110051380A (en) * | 2019-06-05 | 2019-07-26 | 南京清科信息科技有限公司 | The system and method that continuous real-time monitoring is carried out to body state |
| CN110289061A (en) * | 2019-06-27 | 2019-09-27 | 黎檀实 | A kind of Time Series Forecasting Methods of the traumatic hemorrhagic shock condition of the injury |
| CN111657888A (en) * | 2020-05-28 | 2020-09-15 | 首都医科大学附属北京天坛医院 | Severe acute respiratory distress syndrome early warning method and system |
| CN113017568A (en) * | 2021-03-03 | 2021-06-25 | 中国人民解放军海军军医大学 | Method and system for predicting physiological changes and death risks of severely wounded patients |
-
2021
- 2021-07-27 CN CN202110850563.XA patent/CN113793661A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017218431A1 (en) * | 2016-06-13 | 2017-12-21 | Flashback Technologies, Inc. | Rapid detection of bleeding following injury |
| CN110051380A (en) * | 2019-06-05 | 2019-07-26 | 南京清科信息科技有限公司 | The system and method that continuous real-time monitoring is carried out to body state |
| CN110289061A (en) * | 2019-06-27 | 2019-09-27 | 黎檀实 | A kind of Time Series Forecasting Methods of the traumatic hemorrhagic shock condition of the injury |
| CN111657888A (en) * | 2020-05-28 | 2020-09-15 | 首都医科大学附属北京天坛医院 | Severe acute respiratory distress syndrome early warning method and system |
| CN113017568A (en) * | 2021-03-03 | 2021-06-25 | 中国人民解放军海军军医大学 | Method and system for predicting physiological changes and death risks of severely wounded patients |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6551243B2 (en) | System and user interface for use in providing medical information and health care delivery support | |
| CN102708128B (en) | For receiving, mapping and constructing the method and system of the data from disparate system | |
| CA2739829C (en) | Predetermined presentation of patient data at bedside | |
| EP3380963B1 (en) | Tracking usage of a pulse oximeter via a network system | |
| US8922377B2 (en) | System, method, and software for automating complex alerts | |
| CN106874699A (en) | It is a kind of based on the health management system arranged of iOS platforms | |
| CN109741826B (en) | Anesthesia evaluation decision tree construction method and equipment | |
| JP2005505817A (en) | A system to support clinical judgment by modeling the collected patient medical information | |
| CN106456002A (en) | Unobtrusive advisors for patient monitor | |
| CN112735610A (en) | Post-hospital follow-up system and follow-up method | |
| WO2021032055A1 (en) | Automatic entry method and device for clinical trial reports, electronic equipment, and storage medium | |
| US20230395253A1 (en) | Cloud-edge collaborative processing system and method for icu data based on third-party business | |
| CN1983258A (en) | System and user interface for processing patient medical data | |
| CN105574355B (en) | The recording method of clinical research data and system | |
| Calvo et al. | A methodology to analyze heart data using fuzzy automata | |
| CN113113136A (en) | Medical aid decision-making system based on mixed reality | |
| AU2022231758A1 (en) | Medical care assistance device, and operation method and operation program therefor | |
| CN113241180A (en) | Health management method and device | |
| Khovrichev et al. | Intelligent approach for heterogeneous data integration: Information processes analysis engine in clinical remote monitoring systems | |
| WO2021096467A1 (en) | Triage decision support method and the system using this method | |
| CN113793661A (en) | Intelligent monitoring and early warning system for traumatic hemorrhagic shock | |
| JP5209340B2 (en) | Report creation system and report creation device | |
| US11445906B2 (en) | Systems and methods for storing data on medical sensors | |
| CN111489801A (en) | Report query method and device | |
| CN112151178A (en) | Intelligent health cloud platform based on Java language development |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |