CN115312178A - Acute hypotension data processing method and device based on noninvasive parameters - Google Patents
Acute hypotension data processing method and device based on noninvasive parameters Download PDFInfo
- Publication number
- CN115312178A CN115312178A CN202211118011.0A CN202211118011A CN115312178A CN 115312178 A CN115312178 A CN 115312178A CN 202211118011 A CN202211118011 A CN 202211118011A CN 115312178 A CN115312178 A CN 115312178A
- Authority
- CN
- China
- Prior art keywords
- information
- physiological parameter
- characteristic
- characteristic value
- noninvasive
- 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
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
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a method and a device for processing acute hypotension data based on noninvasive parameters, wherein the method comprises the following steps: acquiring noninvasive physiological parameter information; the non-invasive physiological parameter information comprises N non-invasive physiological parameter sets; n is a positive integer not less than 5; the noninvasive physiological parameter set comprises 7 physiological parameter information; preprocessing and dimensionality reduction processing are carried out on the noninvasive physiological parameter information to obtain optimal characteristic value information; and calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information. Therefore, the method is beneficial to improving the accuracy of data processing based on non-invasive parameters, and further more simply, quickly and accurately analyzing the acute hypotension condition.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for processing acute hypotension data based on noninvasive parameters.
Background
Many scoring systems exist such as APACHE, SAPS and MPM that can analyze acute hypotension conditions based on baseline characteristics, but due to lack of adequate calibration, their prediction accuracy may be limited, and some systems may even issue false alarms. At present, invasive physiological parameters are generally adopted for processing physiological data of acute hypotension, and single parameter is adopted for risk analysis, so that the risk analysis is easily interfered and the accuracy rate is low. Therefore, the method and the device for processing the acute hypotension data based on the non-invasive parameters are provided to improve the accuracy of data processing based on the non-invasive parameters, so that the acute hypotension condition can be analyzed more simply, rapidly and accurately.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method and a device for processing acute hypotension data based on non-invasive parameters, which can obtain risk result information through preprocessing, dimensionality reduction processing, calculation processing and comparative analysis of non-invasive physiological parameter information, and are beneficial to improving the accuracy of data processing based on the non-invasive parameters, thereby analyzing the acute hypotension condition more simply, quickly and accurately.
In order to solve the above technical problem, a first aspect of the embodiments of the present invention discloses a method for processing acute hypotension data based on non-invasive parameters, where the method includes:
acquiring noninvasive physiological parameter information; the non-invasive physiological parameter information comprises N sets of non-invasive physiological parameters; n is a positive integer not less than 5; the set of non-invasive physiological parameters comprises 7 physiological parameter information;
preprocessing and dimensionality reduction processing are carried out on the noninvasive physiological parameter information to obtain optimal characteristic value information;
and calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information.
As an alternative implementation manner, in the first aspect of the embodiment of the present invention, the acquiring noninvasive physiological parameter information includes:
acquiring observation window time information and an acquisition time interval;
sequentially collecting noninvasive physiological parameters from the time point of the time information of the observation window by taking a collection time interval as an interval time length to obtain initial noninvasive physiological parameter information; the initial noninvasive physiological parameter information comprises the N initial noninvasive physiological parameter sets; the initial noninvasive physiological parameter set comprises 7 initial physiological parameter information;
for any initial noninvasive physiological parameter set, 12 statistical parameters are respectively extracted from all 7 pieces of initial physiological parameter information in the initial noninvasive physiological parameter set, and a noninvasive physiological parameter set corresponding to the initial noninvasive physiological parameter set is obtained.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the performing pre-processing and dimension reduction processing on the noninvasive physiological parameter information to obtain optimal eigenvalue information includes:
preprocessing the noninvasive physiological parameter information, and constructing a characteristic matrix to obtain a characteristic value matrix;
screening the eigenvalues of the eigenvalue matrix to obtain eigenvalue sorting information; the characteristic value sorting information comprises a plurality of characteristic score values; each of the characteristic score values corresponds to unique one of the characteristic parameter information;
and performing dimension reduction processing on the characteristic value sequencing information to obtain optimal characteristic value information.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the preprocessing the noninvasive physiological parameter information and constructing a feature matrix to obtain a feature value matrix includes:
data summarization and integration are carried out on the noninvasive physiological parameter information to obtain first characteristic value information; the first characteristic value information comprises 7 pieces of characteristic value information to be selected; each piece of feature information to be selected comprises 12 pieces of feature parameter information; each piece of feature parameter information comprises a feature parameter vector with the length of N;
screening abnormal values of the first characteristic value information by using a preset abnormal value screening strategy to obtain abnormal value information;
emptying the abnormal value information by using a missing value, and estimating and filling the emptied abnormal value information to obtain second characteristic value information;
and constructing a characteristic matrix for the second characteristic value information to obtain a characteristic value matrix.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the performing eigenvalue screening on the eigenvalue matrix to obtain eigenvalue ranking information includes:
carrying out normalization processing on the characteristic value matrix to obtain a normalization matrix;
calculating the normalization matrix by using a preset first screening strategy to obtain first score value information;
calculating the normalization matrix by using a preset second screening strategy to obtain second score value information;
calculating the normalized matrix by using a preset third screening strategy to obtain third score value information;
calculating the first score value information, the second score value information and the third score value information by using a preset screening model to obtain fourth score value information;
carrying out normalization processing on the fourth score value information to obtain feature score value information; the feature score value information includes a plurality of the feature score values;
and sorting the characteristic score value information from large to small according to the characteristic score value to obtain characteristic value sorting information.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the performing dimension reduction processing on the eigenvalue ranking information to obtain optimal eigenvalue information includes:
the characteristic parameter information corresponding to the characteristic score value in the characteristic value sorting information is selected step by step in the forward direction to obtain characteristic value information to be selected;
calculating an AUC value of the information of the characteristic value to be selected;
judging whether the AUC value is greater than or equal to an evaluation threshold value or not to obtain an evaluation judgment result;
when the evaluation judgment result is negative, triggering and executing the forward step-by-step selection of the characteristic parameter information corresponding to the characteristic score value in the characteristic value sorting information to obtain the characteristic value information to be selected;
and when the evaluation judgment result is yes, determining the information of the characteristic value to be selected as the information of the optimal characteristic value.
As an alternative implementation manner, in the first aspect of the embodiment of the present invention, the integrated prediction model includes a first prediction model, a second prediction model, and a third prediction model;
the calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information, including:
calculating the optimal characteristic value information by using the first prediction model to obtain a first prediction probability;
calculating the optimal characteristic value information by using the second prediction model to obtain a second prediction probability;
calculating the optimal characteristic value information by using the third prediction model to obtain a third prediction probability;
carrying out weighted summation processing on the first prediction probability, the second prediction probability and the third prediction probability to obtain prediction probability values;
judging whether the predicted probability value is greater than or equal to a probability threshold value or not to obtain a probability judgment result;
when the probability judgment result is yes, analyzing and processing the predicted probability value by using an expert knowledge model to obtain analysis result information;
and determining risk result information according to the analysis result information.
The second aspect of the embodiment of the invention discloses an acute hypotension data processing device based on noninvasive parameters, which comprises:
the acquisition module is used for acquiring noninvasive physiological parameter information; the non-invasive physiological parameter information comprises N sets of non-invasive physiological parameters; n is a positive integer not less than 5; the set of non-invasive physiological parameters comprises 7 physiological parameter information;
the first processing module is used for preprocessing and dimension reduction processing on the noninvasive physiological parameter information to obtain optimal characteristic value information;
and the second processing module is used for performing calculation processing and comparative analysis on the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the specific manner of acquiring the noninvasive physiological parameter information by the acquisition module is as follows:
acquiring observation window time information and an acquisition time interval;
sequentially collecting noninvasive physiological parameters from the time point of the time information of the observation window by taking a collection time interval as an interval time length to obtain initial noninvasive physiological parameter information; the initial noninvasive physiological parameter information comprises the N initial noninvasive physiological parameter sets; the initial noninvasive physiological parameter set comprises 7 initial physiological parameter information;
for any initial noninvasive physiological parameter set, 12 statistical parameters are respectively extracted from all 7 pieces of initial physiological parameter information in the initial noninvasive physiological parameter set, and a noninvasive physiological parameter set corresponding to the initial noninvasive physiological parameter set is obtained.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the specific manner of performing the preprocessing and the dimension reduction processing on the noninvasive physiological parameter information by the first processing module to obtain the optimal eigenvalue information is as follows:
preprocessing the noninvasive physiological parameter information, and constructing a characteristic matrix to obtain a characteristic value matrix;
carrying out eigenvalue screening on the eigenvalue matrix to obtain eigenvalue sorting information; the characteristic value sequencing information comprises a plurality of characteristic score values; each of the characteristic score values corresponds to unique one of the characteristic parameter information;
and performing dimension reduction processing on the characteristic value sequencing information to obtain optimal characteristic value information.
As an optional implementation manner, in a second aspect of the embodiment of the present invention, the first processing module performs preprocessing on the noninvasive physiological parameter information, and constructs a feature matrix, and a specific manner of obtaining the feature value matrix is as follows:
data summarization and integration are carried out on the noninvasive physiological parameter information to obtain first characteristic value information; the first characteristic value information comprises 7 pieces of characteristic value information to be selected; each piece of feature information to be selected comprises 12 pieces of feature parameter information; each piece of characteristic parameter information comprises a characteristic parameter vector with the length of N;
screening abnormal values of the first characteristic value information by using a preset abnormal value screening strategy to obtain abnormal value information;
emptying the abnormal value information by using a missing value, and estimating and filling the emptied abnormal value information to obtain second characteristic value information;
and constructing a characteristic matrix for the second characteristic value information to obtain a characteristic value matrix.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the specific manner of performing eigenvalue screening on the eigenvalue matrix by the first processing module to obtain the ranking information of the eigenvalues is as follows:
carrying out normalization processing on the characteristic value matrix to obtain a normalization matrix;
calculating the normalization matrix by using a preset first screening strategy to obtain first score value information;
calculating the normalization matrix by using a preset second screening strategy to obtain second score value information;
calculating the normalized matrix by using a preset third screening strategy to obtain third score value information;
calculating the first score value information, the second score value information and the third score value information by using a preset screening model to obtain fourth score value information;
normalizing the fourth score value information to obtain feature score value information; the feature score value information includes a plurality of the feature score values;
and sorting the characteristic score value information from large to small according to the characteristic score value to obtain characteristic value sorting information.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the first processing module performs dimension reduction processing on the eigenvalue ranking information, and a specific manner of obtaining optimal eigenvalue information is as follows:
forward gradually selecting the characteristic parameter information corresponding to the characteristic score value in the characteristic value sorting information to obtain characteristic value information to be selected;
calculating an AUC value of the information of the characteristic value to be selected;
judging whether the AUC value is greater than or equal to an evaluation threshold value to obtain an evaluation judgment result;
when the evaluation judgment result is negative, triggering and executing the forward step-by-step selection of the characteristic parameter information corresponding to the characteristic score value in the characteristic value sorting information to obtain the characteristic value information to be selected;
and when the evaluation judgment result is yes, determining the information of the characteristic values to be selected as the information of the optimal characteristic values.
As an alternative implementation, in the second aspect of the embodiment of the present invention, the integrated prediction model includes a first prediction model, a second prediction model, and a third prediction model;
the second processing module performs calculation processing and comparative analysis on the optimal characteristic value information by using a preset integrated prediction model, and the specific mode of obtaining risk result information is as follows:
calculating the optimal characteristic value information by using the first prediction model to obtain a first prediction probability;
calculating the optimal characteristic value information by using the second prediction model to obtain a second prediction probability;
calculating the optimal characteristic value information by using the third prediction model to obtain a third prediction probability;
carrying out weighted summation processing on the first prediction probability, the second prediction probability and the third prediction probability to obtain prediction probability values;
judging whether the predicted probability value is greater than or equal to a probability threshold value or not to obtain a probability judgment result;
when the probability judgment result is yes, analyzing and processing the predicted probability value by using an expert knowledge model to obtain analysis result information;
and determining risk result information according to the analysis result information.
The invention discloses a third aspect of another acute hypotension data processing device based on non-invasive parameters, which comprises:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute part or all of the steps of the non-invasive parameter-based acute hypotension data processing method disclosed in the first aspect of the embodiment of the invention.
In a fourth aspect of the present invention, a computer storage medium is disclosed, which stores computer instructions for performing some or all of the steps of the non-invasive parameter based acute hypotension data processing method disclosed in the first aspect of the embodiments of the present invention when being called.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, noninvasive physiological parameter information is obtained; the non-invasive physiological parameter information comprises N non-invasive physiological parameter sets; n is a positive integer not less than 5; the noninvasive physiological parameter set comprises 7 physiological parameter information; preprocessing and dimensionality reduction processing are carried out on the noninvasive physiological parameter information to obtain optimal characteristic value information; and calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information. Therefore, the method is beneficial to improving the accuracy of data processing based on non-invasive parameters, and further more simply, quickly and accurately analyzing the acute hypotension condition.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for processing acute hypotension data based on non-invasive parameters according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating another method for processing acute hypotension data based on non-invasive parameters, according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an acute hypotension data processing apparatus based on noninvasive parameters according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of another non-invasive parameter-based acute hypotension data processing apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a noninvasive physiological parameter information time window according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or apparatus that comprises a list of steps or elements is not limited to those listed but may alternatively include other steps or elements not listed or inherent to such process, method, product, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention discloses an acute hypotension data processing method and device based on noninvasive parameters, which can obtain risk result information through preprocessing, dimensionality reduction processing, calculation processing and comparative analysis of noninvasive physiological parameter information, are beneficial to improving the data processing accuracy based on the noninvasive parameters, and further analyze the acute hypotension condition more simply, quickly and accurately. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for processing data of acute hypotension based on non-invasive parameters according to an embodiment of the present invention. The method for processing acute hypotension data based on non-invasive parameters described in fig. 1 is applied to a data processing system, such as a local server or a cloud server for processing and managing the acute hypotension data based on non-invasive parameters, and the embodiments of the present invention are not limited thereto. As shown in fig. 1, the method for processing acute hypotension data based on non-invasive parameters may include the following operations:
101. and acquiring noninvasive physiological parameter information.
In an embodiment of the present invention, the non-invasive physiological parameter information includes N non-invasive physiological parameter sets.
In an embodiment of the present invention, N is a positive integer not less than 5.
In an embodiment of the present invention, the noninvasive physiological parameter set includes 7 pieces of physiological parameter information.
102. And preprocessing and dimensionality reduction processing are carried out on the noninvasive physiological parameter information to obtain optimal characteristic value information.
103. And calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information.
Optionally, the physiological parameter information includes heart rate information, respiratory rate information, pulse rate information, oxygen saturation information, systolic pressure information, diastolic pressure information, and pressure-average information.
Therefore, the acute hypotension data processing method based on the noninvasive parameters, which is described by the embodiment of the invention, can obtain risk result information through preprocessing, dimension reduction processing, calculation processing and comparative analysis of the noninvasive physiological parameter information, and is beneficial to improving the data processing accuracy based on the noninvasive parameters, so that the acute hypotension condition can be analyzed more simply, quickly and accurately.
In an alternative embodiment, as shown in fig. 5, the acquiring non-invasive physiological parameter information in step 101 includes:
acquiring time information of an observation window and an acquisition time interval;
sequentially collecting noninvasive physiological parameters from the time point of arrival of the time information of the observation window by taking the collection time interval as the interval time length to obtain initial noninvasive physiological parameter information; the initial noninvasive physiological parameter information comprises N initial noninvasive physiological parameter sets; the initial noninvasive physiological parameter set comprises 7 pieces of initial physiological parameter information;
for any initial noninvasive physiological parameter set, 12 statistical parameters are respectively extracted from all 7 initial physiological parameter information in the initial noninvasive physiological parameter set, and a noninvasive physiological parameter set corresponding to the initial noninvasive physiological parameter set is obtained.
Optionally, the statistical parameters include a maximum value, a minimum value, a mean value, a median, a standard deviation, a skewness, a kurtosis, an upper quartile, IQR, a range, a mean absolute deviation, and a variance.
Optionally, the IQR is a quartile range.
Optionally, T 0 Starting access point for obtaining samples for non-invasive physiological parameters, from point of time of stay T 1 At first, satisfy T 1 ≥T 0 At the observation windowLength of time x 1 In the method, the time length is [ T ] by taking the acquisition time interval as an interval 1 ,T 1 +x 1 ]Non-invasive physiological parameters are collected over time. X after non-invasive physiological parameter acquisition 2 For the length of the prediction interval, the prediction window is set to a time period of [ T 1 +x 1 +x 2, T 1 +x 1 +x 2 +x 3 ]Wherein x is 3 And analyzing and processing the non-invasive physiological parameter information in the time period of the prediction window for the time length of the prediction window.
For example, in an observation window time length of 5 hours in total, with 1 hour as an acquisition time interval, 12 statistical parameters (maximum value, minimum value, mean value, median, standard deviation, skewness, kurtosis, upper quartile, IQR, range, mean absolute deviation, variance) are extracted from 7 physiological parameter information (heart rate information, respiratory rate information, pulse rate information, oxygen saturation information, systolic pressure information, diastolic pressure information, and mean pressure information) of each sample every 1 hour, and 5 noninvasive physiological parameter sets can be generated.
Therefore, the acute hypotension data processing method based on the noninvasive parameters, which is described by the embodiment of the invention, can be used for obtaining the information of the noninvasive physiological parameters, so that the accuracy of data processing based on the noninvasive parameters can be improved, and the condition of the acute hypotension can be analyzed more simply, quickly and accurately.
Example two
Referring to fig. 2, fig. 2 is a flowchart illustrating another method for processing acute hypotension data based on non-invasive parameters according to an embodiment of the present invention. The method for processing acute hypotension data based on non-invasive parameters described in fig. 2 is applied to a data processing system, such as a local server or a cloud server for processing and managing the acute hypotension data based on non-invasive parameters, and the embodiments of the present invention are not limited thereto. As shown in fig. 2, the method for processing acute hypotension data based on non-invasive parameters may include the following operations:
201. and acquiring noninvasive physiological parameter information.
202. Preprocessing the noninvasive physiological parameter information, and constructing a characteristic matrix to obtain a characteristic value matrix.
203. And screening the eigenvalue of the eigenvalue matrix to obtain eigenvalue sorting information.
In an embodiment of the present invention, the eigenvalue ranking information includes a plurality of eigenvalue scores.
In an embodiment of the present invention, each of the feature score values corresponds to only one piece of feature parameter information.
204. And performing dimension reduction processing on the characteristic value sequencing information to obtain optimal characteristic value information.
205. And calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information.
In the embodiment of the present invention, for specific technical details and technical noun explanations of step 201 and step 205, reference may be made to the detailed description of step 101 and step 103 in the first embodiment, and details are not repeated in the embodiment of the present invention.
Therefore, the acute hypotension data processing method based on the noninvasive parameters, which is described by the embodiment of the invention, can obtain risk result information through preprocessing, dimension reduction processing, calculation processing and comparative analysis of the noninvasive physiological parameter information, and is beneficial to improving the data processing accuracy based on the noninvasive parameters, so that the acute hypotension condition can be analyzed more simply, quickly and accurately.
In an optional embodiment, the preprocessing the noninvasive physiological parameter information and constructing the feature matrix to obtain the feature value matrix includes:
data summarization and integration are carried out on the noninvasive physiological parameter information to obtain first characteristic value information; the first characteristic value information comprises 7 pieces of information of characteristic values to be selected; each piece of feature information to be selected comprises 12 pieces of feature parameter information; each piece of characteristic parameter information comprises a characteristic parameter vector with the length of N;
screening abnormal values of the first characteristic value information by using a preset abnormal value screening strategy to obtain abnormal value information;
emptying the abnormal value information by using the missing value, and estimating and filling the emptied abnormal value information to obtain second characteristic value information;
and constructing a characteristic matrix for the second characteristic value information to obtain a characteristic value matrix.
Optionally, the abnormal value information includes a plurality of abnormal characteristic parameters.
In this optional embodiment, as an optional implementation manner, the above-mentioned screening the abnormal value of the first feature value information by using a preset abnormal value screening policy is performed, and a specific manner of obtaining the abnormal value information is as follows:
for any characteristic parameter vector in the information of the characteristic values to be selected, carrying out median potential difference calculation on the characteristic parameter vector by using a median potential difference model to obtain a median potential difference corresponding to the characteristic parameter vector;
calculating any characteristic parameter in the characteristic parameter vector by using an abnormal calculation model to obtain an abnormal characteristic value corresponding to the characteristic parameter;
judging whether the abnormal characteristic value is larger than an abnormal threshold value or not to obtain an abnormal judgment result;
and when the abnormity judgment result is yes, determining the characteristic parameter as an abnormal characteristic parameter.
Optionally, the specific form of the middle level difference model is as follows:
wherein Z is the median potential difference, x j Is the jth characteristic parameter in the characteristic parameter vector;
is the median of the feature parameter vector.
Optionally, the specific form of the anomaly calculation model is as follows:
wherein YC is equal to or greater than 3.5 as a criterion for determining an abnormal value.
In this optional implementation, as another optional implementation, the above estimating and filling the empty abnormal value information to obtain the second characteristic value information specifically includes:
for any empty abnormal characteristic parameter, carrying out numerical estimation on the empty abnormal characteristic parameter by using an estimation model to obtain an estimation value;
and filling all the estimated values into empty abnormal value information to obtain second characteristic value information.
Optionally, the specific manner of the estimation model is as follows:
wherein y is an estimated value, X is a serial number of the abnormal characteristic parameter in the characteristic parameter vector, X11 is a maximum serial number in the characteristic parameter vector corresponding to the abnormal characteristic parameter, X10 is a minimum serial number in the characteristic parameter vector corresponding to the abnormal characteristic parameter, y11 is a characteristic parameter corresponding to the maximum serial number, and y10 is a characteristic parameter corresponding to the minimum serial number.
Therefore, the acute hypotension data processing method based on the non-invasive parameters, which is described by the embodiment of the invention, can be used for preprocessing the information of the non-invasive physiological parameters, constructing the characteristic matrix and obtaining the characteristic value matrix, and is more beneficial to improving the data processing accuracy based on the non-invasive parameters, so that the acute hypotension condition can be analyzed more simply, quickly and accurately.
In another optional embodiment, the performing eigenvalue screening on the eigenvalue matrix to obtain eigenvalue ranking information includes:
normalizing the characteristic value matrix to obtain a normalized matrix;
calculating the normalized matrix by using a preset first screening strategy to obtain first score value information;
calculating the normalized matrix by using a preset second screening strategy to obtain second score value information;
calculating the normalized matrix by using a preset third screening strategy to obtain third score value information;
calculating the first score information, the second score information and the third score information by using a preset screening model to obtain fourth score information;
normalizing the fourth score information to obtain feature score information; the feature score value information includes a plurality of feature score values;
and sorting the characteristic score value information from big to small according to the characteristic score value to obtain characteristic value sorting information.
In this optional embodiment, as an optional implementation manner, the specific manner of performing calculation processing on the normalized matrix by using a preset first screening policy to obtain the first score information is as follows:
carrying out sample classification on the normalized matrix to obtain a first sample information set; the first sample information set comprises a plurality of first sample information; the first sample information comprises a plurality of first samples; each first sample comprises 12 first sample values;
for any first sample information, initializing a plurality of weight vectors with the length of 12 to obtain first weight vector information corresponding to the first sample information; the first weight vector information comprises a plurality of first weight vectors; each first weight vector corresponds to a first sample corresponding to the first sample information;
randomly selecting a first sample from the first sample information as a first target sample;
selecting a first weight vector matched with the first target sample from the first weight vector information as a first target weight vector;
selecting one sample closest to the first target sample from the first sample information as a first spare sample;
selecting one sample from other first sample information except the first sample information as a second spare sample;
calculating the first target weight vector, the first standby sample and the second standby sample by using a diff algorithm to obtain a standby weight vector and iteration times;
judging whether the iteration times are equal to an iteration threshold value or not to obtain an iteration judgment result; updating the first weight vector information by using the standby weight vector;
when the iteration judgment result is negative, triggering and executing to randomly select a first sample from the first sample information as a first target sample;
when the iteration judgment result is yes, performing product summation processing on the first sample information by using first weight vector information to obtain standby first score value information;
and summing all the standby first score value information to obtain first score value information.
In this optional embodiment, as another optional implementation, the specific manner of performing calculation processing on the normalized matrix by using a preset second screening policy to obtain the second score information is as follows:
calculating the normalized matrix by using a Fisher algorithm to obtain a standby score matrix;
and carrying out mean value calculation processing on the standby score matrix to obtain second score value information.
Optionally, the Fisher algorithm described above is a non-iterative solution to a linear separable problem.
In this optional embodiment, as another optional implementation manner, the specific manner of obtaining the third score information by performing calculation processing on the normalized matrix by using a preset third screening policy is as follows:
classifying the normalized matrix to obtain a class characteristic information set; the category characteristic information set comprises M category characteristic information; each category feature information includes L category features; m is a positive integer; l is a positive integer;
for any category feature information, calculating the category feature information by using a first category probability model to obtain a category feature probability value;
summing all the category characteristic probability values to obtain a standby category probability value and category calculation times;
judging whether the category calculation times are equal to a category threshold value or not to obtain a category judgment result;
when the classification judgment result is negative, updating historical standby classification probability value information by using the standby classification probability value, and triggering execution to perform classification on the normalized matrix to obtain a classification characteristic information set; the historical standby category probability value information comprises a plurality of historical standby category probability values;
when the type judgment result is yes, sorting the standby type probability value and all historical standby type probability values in the historical standby type probability value information from small to large, and selecting a first sorted value as a target type probability value;
and generating third score value information according to the target category probability value.
Optionally, the first class probability model has a specific form:
lb is a category feature probability value, and pi is a probability that the ith category feature in the category feature information is divided into the category feature information.
Optionally, the category threshold may be preset, and the embodiment of the present invention is not limited.
Optionally, the specific form of the screening model is as follows:
fourth score information = first score information + second score information — third score information.
Therefore, the acute hypotension data processing method based on the non-invasive parameters, which is described by the embodiment of the invention, can be used for screening the characteristic values of the characteristic value matrix to obtain the characteristic value sequencing information, so that the accuracy of data processing based on the non-invasive parameters can be improved, and the acute hypotension condition can be analyzed more simply, quickly and accurately.
In another optional embodiment, performing dimension reduction processing on the eigenvalue ranking information to obtain optimal eigenvalue information includes:
forward gradually selecting characteristic parameter information corresponding to the characteristic score values in the characteristic value sorting information to obtain characteristic value information to be selected;
calculating an AUC value of the information of the characteristic value to be selected;
judging whether the AUC value is greater than or equal to the evaluation threshold value to obtain an evaluation judgment result;
when the evaluation judgment result is negative, triggering to execute forward step-by-step selection of characteristic parameter information corresponding to the characteristic score value in the characteristic value sorting information to obtain characteristic value information to be selected;
and when the evaluation judgment result is yes, determining the information of the characteristic value to be selected as the information of the optimal characteristic value.
Optionally, the AUC value is an area under a characteristic curve.
Optionally, the number of the optimal feature values in the optimal feature value information is between 1/2 and 2/3 of the number of the feature parameter information.
Optionally, the characteristic curve is fitted according to all characteristic parameter information.
Therefore, by the aid of the acute hypotension data processing method based on the non-invasive parameters, dimension reduction processing can be performed on the characteristic value sequencing information to obtain optimal characteristic value information, data processing accuracy based on the non-invasive parameters can be improved, and the acute hypotension condition can be analyzed more simply, quickly and accurately.
In yet another alternative embodiment, the integrated predictive model includes a first predictive model, a second predictive model, and a third predictive model;
calculating, processing and contrastively analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information, wherein the risk result information comprises:
calculating the optimal characteristic value information by using a first prediction model to obtain a first prediction probability;
calculating the optimal characteristic value information by using a second prediction model to obtain a second prediction probability;
calculating the optimal characteristic value information by using a third prediction model to obtain a third prediction probability;
carrying out weighted summation processing on the first prediction probability, the second prediction probability and the third prediction probability to obtain prediction probability values;
judging whether the predicted probability value is greater than or equal to a probability threshold value or not to obtain a probability judgment result;
when the probability judgment result is yes, analyzing and processing the predicted probability value by using an expert knowledge model to obtain analysis result information;
and determining risk result information according to the analysis result information.
Optionally, the first prediction model is a decision tree-based model.
Optionally, the second prediction model is a tree model-based model.
Optionally, the third prediction model is a model based on an adaptive lifting tree algorithm.
Optionally, the probability threshold is 0.5.
Therefore, the acute hypotension data processing method based on the non-invasive parameters, which is described by the embodiment of the invention, can utilize the preset integrated prediction model to perform calculation processing and comparative analysis on the optimal characteristic value information to obtain risk result information, is more beneficial to improving the data processing accuracy based on the non-invasive parameters, and further more simply, quickly and accurately analyzes the acute hypotension condition.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic structural diagram of an apparatus for processing acute hypotension data based on noninvasive parameters according to an embodiment of the present invention. The apparatus depicted in fig. 3 can be applied to a data processing system, such as a local server or a cloud server for management of acute hypotension data processing based on non-invasive parameters, and the embodiments of the present invention are not limited thereto. As shown in fig. 3, the apparatus may include:
an obtaining module 301, configured to obtain noninvasive physiological parameter information; the non-invasive physiological parameter information comprises N non-invasive physiological parameter sets; n is a positive integer not less than 5; the noninvasive physiological parameter set comprises 7 physiological parameter information;
the first processing module 302 is configured to perform preprocessing and dimension reduction on the noninvasive physiological parameter information to obtain optimal eigenvalue information;
and the second processing module 303 is configured to perform calculation processing and comparative analysis on the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information.
It can be seen that, by implementing the apparatus for processing acute hypotension data based on noninvasive parameters described in fig. 3, risk result information can be obtained through preprocessing, dimensionality reduction processing, calculation processing and comparative analysis on noninvasive physiological parameter information, which is beneficial to improving the accuracy of data processing based on noninvasive parameters, and then more concise, rapid and accurate analysis of the acute hypotension condition.
In another alternative embodiment, as shown in fig. 3, the specific way for the obtaining module 301 to obtain the noninvasive physiological parameter information is as follows:
acquiring observation window time information and an acquisition time interval;
sequentially collecting noninvasive physiological parameters from the time point of the time information of the observation window by taking the collection time interval as the interval time length to obtain initial noninvasive physiological parameter information; the initial noninvasive physiological parameter information comprises N initial noninvasive physiological parameter sets; the initial noninvasive physiological parameter set comprises 7 pieces of initial physiological parameter information;
for any initial noninvasive physiological parameter set, 12 statistical parameters are respectively extracted from all 7 pieces of initial physiological parameter information in the initial noninvasive physiological parameter set to obtain a noninvasive physiological parameter set corresponding to the initial noninvasive physiological parameter set.
It can be seen that, by implementing the acute hypotension data processing apparatus based on noninvasive parameters described in fig. 3, it is possible to obtain noninvasive physiological parameter information, which is beneficial to improve the accuracy of data processing based on noninvasive parameters, and further to analyze the acute hypotension situation more simply, quickly, and accurately.
In a further alternative embodiment, as shown in fig. 3, the first processing module 302 performs preprocessing and dimension reduction on the noninvasive physiological parameter information to obtain the optimal eigenvalue information in a specific manner:
preprocessing the noninvasive physiological parameter information, and constructing a characteristic matrix to obtain a characteristic value matrix;
carrying out eigenvalue screening on the eigenvalue matrix to obtain eigenvalue sorting information; the characteristic value sequencing information comprises a plurality of characteristic score values; each characteristic score value corresponds to unique characteristic parameter information;
and performing dimension reduction processing on the characteristic value sequencing information to obtain optimal characteristic value information.
It can be seen that, by implementing the apparatus for processing acute hypotension data based on noninvasive parameters described in fig. 3, risk result information can be obtained through preprocessing, dimensionality reduction processing, calculation processing and comparative analysis on noninvasive physiological parameter information, which is beneficial to improving the accuracy of data processing based on noninvasive parameters, and then more concise, rapid and accurate analysis of the acute hypotension condition.
In yet another alternative embodiment, as shown in fig. 3, the first processing module 302 performs preprocessing on the noninvasive physiological parameter information and constructs a feature matrix, and the specific manner of obtaining the feature value matrix is as follows:
data summarization and integration are carried out on the noninvasive physiological parameter information to obtain first characteristic value information; the first characteristic value information comprises 7 pieces of information of characteristic values to be selected; each piece of feature information to be selected comprises 12 pieces of feature parameter information; each piece of characteristic parameter information comprises a characteristic parameter vector with the length of N;
screening abnormal values of the first characteristic value information by using a preset abnormal value screening strategy to obtain abnormal value information;
emptying the abnormal value information by using the missing value, and estimating and filling the emptied abnormal value information to obtain second characteristic value information;
and constructing a characteristic matrix for the second characteristic value information to obtain a characteristic value matrix.
Therefore, by implementing the acute hypotension data processing device based on the noninvasive parameters described in fig. 3, the noninvasive physiological parameter information can be preprocessed, the characteristic matrix can be constructed, and the characteristic value matrix can be obtained, which is more beneficial to improving the data processing accuracy based on the noninvasive parameters, and further more concise, faster and more accurate analysis of the acute hypotension condition.
In yet another alternative embodiment, as shown in fig. 3, the specific way for the first processing module 302 to perform eigenvalue screening on the eigenvalue matrix to obtain the ranking information of the eigenvalues is as follows:
normalizing the characteristic value matrix to obtain a normalized matrix;
calculating the normalized matrix by using a preset first screening strategy to obtain first score value information;
calculating the normalized matrix by using a preset second screening strategy to obtain second score value information;
calculating the normalized matrix by using a preset third screening strategy to obtain third score value information;
calculating the first score information, the second score information and the third score information by using a preset screening model to obtain fourth score information;
normalizing the fourth score value information to obtain feature score value information; the feature score value information includes a plurality of feature score values;
and sorting the characteristic score value information from big to small according to the characteristic score value to obtain characteristic value sorting information.
Therefore, by implementing the acute hypotension data processing device based on the noninvasive parameters described in fig. 3, the eigenvalue matrix can be screened to obtain the eigenvalue sorting information, which is beneficial to improving the data processing accuracy based on the noninvasive parameters, and further more simply, rapidly and accurately analyzing the acute hypotension condition.
In yet another alternative embodiment, as shown in fig. 3, the first processing module 302 performs dimension reduction processing on the eigenvalue ranking information to obtain the optimal eigenvalue information in a specific manner:
forward gradually selecting characteristic parameter information corresponding to the characteristic score values in the characteristic value sorting information to obtain characteristic value information to be selected;
calculating an AUC value of the information of the characteristic value to be selected;
judging whether the AUC value is greater than or equal to the evaluation threshold value to obtain an evaluation judgment result;
when the evaluation judgment result is negative, triggering execution to gradually select characteristic parameter information corresponding to the characteristic score values in the characteristic value sorting information in a forward direction to obtain characteristic value information to be selected;
and when the evaluation judgment result is yes, determining the information of the characteristic value to be selected as the information of the optimal characteristic value.
Therefore, by implementing the acute hypotension data processing device based on the noninvasive parameters described in fig. 3, the dimension reduction processing can be performed on the characteristic value sequencing information to obtain the optimal characteristic value information, which is more beneficial to improving the data processing accuracy based on the noninvasive parameters, and further more concise, rapid and accurate analysis of the acute hypotension condition.
In yet another alternative embodiment, as shown in FIG. 3, the integrated predictive model includes a first predictive model, a second predictive model, and a third predictive model;
the second processing module 303 performs calculation processing and comparative analysis on the optimal characteristic value information by using a preset integrated prediction model, and the specific way of obtaining risk result information is as follows:
calculating the optimal characteristic value information by using a first prediction model to obtain a first prediction probability;
calculating the optimal characteristic value information by using a second prediction model to obtain a second prediction probability;
calculating the optimal characteristic value information by using a third prediction model to obtain a third prediction probability;
carrying out weighted summation processing on the first prediction probability, the second prediction probability and the third prediction probability to obtain prediction probability values;
judging whether the predicted probability value is greater than or equal to a probability threshold value or not to obtain a probability judgment result;
when the probability judgment result is yes, analyzing and processing the predicted probability value by using an expert knowledge model to obtain analysis result information;
and determining risk result information according to the analysis result information.
Therefore, by implementing the acute hypotension data processing device based on the noninvasive parameters described in fig. 3, the optimal characteristic value information can be calculated, processed and contrasted and analyzed by using the preset integrated prediction model, so that risk result information is obtained, the data processing accuracy based on the noninvasive parameters can be improved, and the acute hypotension condition can be analyzed more simply, quickly and accurately.
Example four
Referring to fig. 4, fig. 4 is a schematic structural diagram of another non-invasive parameter-based acute hypotension data processing apparatus according to an embodiment of the present invention. The apparatus depicted in fig. 4 can be applied to a data processing system, such as a local server or a cloud server for management of acute hypotension data processing based on non-invasive parameters, and the embodiments of the present invention are not limited thereto. As shown in fig. 4, the apparatus may include:
a memory 401 storing executable program code;
a processor 402 coupled to a memory 401;
the processor 402 invokes executable program code stored in the memory 401 for performing the steps of the non-invasive parameter based acute hypotension data processing method described in embodiment one or embodiment two.
EXAMPLE five
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for processing the acute hypotension data based on the noninvasive parameters described in the first embodiment or the second embodiment.
Example six
The embodiment of the invention discloses a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to make a computer execute the steps of the method for processing acute hypotension data based on noninvasive parameters described in the first embodiment or the second embodiment.
The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above detailed description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above technical solutions may essentially or in part contribute to the prior art, be embodied in the form of a software product, which may be stored in a computer-readable storage medium, including a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable Programmable Read-Only Memory (EEPROM), an optical Disc-Read (CD-ROM) or other storage medium capable of storing data, a magnetic tape, or any other computer-readable medium capable of storing data.
Finally, it should be noted that: the method and apparatus for processing acute hypotension data based on non-invasive parameters disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used for illustrating the technical solutions of the present invention, rather than for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for non-invasive parameter based acute hypotension data processing, the method comprising:
acquiring noninvasive physiological parameter information; the non-invasive physiological parameter information comprises N sets of non-invasive physiological parameters; n is a positive integer not less than 5; the set of non-invasive physiological parameters comprises 7 physiological parameter information;
preprocessing and dimensionality reduction processing are carried out on the noninvasive physiological parameter information to obtain optimal characteristic value information;
and calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information.
2. The method of claim 1, wherein the obtaining non-invasive physiological parameter information comprises:
acquiring time information of an observation window and an acquisition time interval;
sequentially collecting noninvasive physiological parameters from the time point of the time information of the observation window by taking the collection time interval as the interval time length to obtain initial noninvasive physiological parameter information; the initial noninvasive physiological parameter information comprises the N initial noninvasive physiological parameter sets; the initial noninvasive physiological parameter set comprises 7 initial physiological parameter information;
for any initial noninvasive physiological parameter set, 12 statistical parameters are respectively extracted from all 7 pieces of initial physiological parameter information in the initial noninvasive physiological parameter set, and a noninvasive physiological parameter set corresponding to the initial noninvasive physiological parameter set is obtained.
3. The method for processing acute hypotension data based on noninvasive parameters of claim 1, wherein the preprocessing and dimensionality reduction of the noninvasive physiological parameter information to obtain optimal eigenvalue information comprises:
preprocessing the noninvasive physiological parameter information, and constructing a characteristic matrix to obtain a characteristic value matrix;
screening the eigenvalues of the eigenvalue matrix to obtain eigenvalue sorting information; the characteristic value sorting information comprises a plurality of characteristic score values; each of the characteristic score values corresponds to unique one of the characteristic parameter information;
and performing dimension reduction processing on the characteristic value sequencing information to obtain optimal characteristic value information.
4. The method for processing acute hypotension data based on noninvasive parameters of claim 3, wherein the preprocessing the noninvasive physiological parameter information and constructing an eigenvalue matrix to obtain an eigenvalue matrix comprises:
data summarization and integration are carried out on the noninvasive physiological parameter information to obtain first characteristic value information; the first characteristic value information comprises 7 pieces of characteristic value information to be selected; each piece of feature information to be selected comprises 12 pieces of feature parameter information; each piece of feature parameter information comprises a feature parameter vector with the length of N;
screening abnormal values of the first characteristic value information by using a preset abnormal value screening strategy to obtain abnormal value information;
emptying the abnormal value information by using a missing value, and estimating and filling the emptied abnormal value information to obtain second characteristic value information;
and constructing a characteristic matrix for the second characteristic value information to obtain a characteristic value matrix.
5. The method for processing acute hypotension data based on noninvasive parameters of claim 3, wherein the eigenvalue screening of the eigenvalue matrix to obtain eigenvalue ranking information comprises:
carrying out normalization processing on the characteristic value matrix to obtain a normalization matrix;
calculating the normalization matrix by using a preset first screening strategy to obtain first score value information;
calculating the normalized matrix by using a preset second screening strategy to obtain second score value information;
calculating the normalized matrix by using a preset third screening strategy to obtain third score value information;
calculating the first score value information, the second score value information and the third score value information by using a preset screening model to obtain fourth score value information;
carrying out normalization processing on the fourth score value information to obtain feature score value information; the feature score value information includes a plurality of the feature score values;
and sorting the characteristic score value information from large to small according to the characteristic score value to obtain characteristic value sorting information.
6. The method for processing acute hypotension data based on noninvasive parameters of claim 3, wherein the performing dimension reduction on the eigenvalue ranking information to obtain optimal eigenvalue information comprises:
forward gradually selecting the characteristic parameter information corresponding to the characteristic score value in the characteristic value sorting information to obtain characteristic value information to be selected;
calculating an AUC value of the to-be-selected characteristic value information;
judging whether the AUC value is greater than or equal to an evaluation threshold value to obtain an evaluation judgment result;
when the evaluation judgment result is negative, triggering and executing the forward step-by-step selection of the characteristic parameter information corresponding to the characteristic score value in the characteristic value sorting information to obtain the characteristic value information to be selected;
and when the evaluation judgment result is yes, determining the information of the characteristic value to be selected as the information of the optimal characteristic value.
7. The non-invasive parameter based acute hypotension data processing method of claim 1, wherein the integrated predictive model comprises a first predictive model, a second predictive model and a third predictive model;
the calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information, including:
calculating the optimal characteristic value information by using the first prediction model to obtain a first prediction probability;
calculating the optimal characteristic value information by using the second prediction model to obtain a second prediction probability;
calculating the optimal characteristic value information by using the third prediction model to obtain a third prediction probability;
carrying out weighted summation processing on the first prediction probability, the second prediction probability and the third prediction probability to obtain prediction probability values;
judging whether the predicted probability value is greater than or equal to a probability threshold value or not to obtain a probability judgment result;
when the probability judgment result is yes, analyzing and processing the prediction probability value by using an expert knowledge model to obtain analysis result information;
and determining risk result information according to the analysis result information.
8. An apparatus for acute hypotension data processing based on non-invasive parameters, the apparatus comprising:
the acquisition module is used for acquiring noninvasive physiological parameter information; the non-invasive physiological parameter information comprises N sets of non-invasive physiological parameters; n is a positive integer not less than 5; the set of non-invasive physiological parameters comprises 7 physiological parameter information;
the first processing module is used for preprocessing and dimensionality reduction processing on the noninvasive physiological parameter information to obtain optimal characteristic value information;
and the second processing module is used for calculating, processing, comparing and analyzing the optimal characteristic value information by using a preset integrated prediction model to obtain risk result information.
9. An apparatus for acute hypotension data processing based on non-invasive parameters, the apparatus comprising:
a memory storing executable program code;
a processor coupled with the memory;
the processor invokes the executable program code stored in the memory to perform the non-invasive parameter based acute hypotension data processing method of any one of claims 1-7.
10. A computer storage medium storing computer instructions which, when invoked, perform a method of non-invasive parameter based acute hypotension data processing according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211118011.0A CN115312178A (en) | 2022-09-14 | 2022-09-14 | Acute hypotension data processing method and device based on noninvasive parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211118011.0A CN115312178A (en) | 2022-09-14 | 2022-09-14 | Acute hypotension data processing method and device based on noninvasive parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115312178A true CN115312178A (en) | 2022-11-08 |
Family
ID=83866828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211118011.0A Pending CN115312178A (en) | 2022-09-14 | 2022-09-14 | Acute hypotension data processing method and device based on noninvasive parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115312178A (en) |
-
2022
- 2022-09-14 CN CN202211118011.0A patent/CN115312178A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109350032B (en) | Classification method, classification system, electronic equipment and storage medium | |
| CN107516075B (en) | Electrocardiosignal detection method and device and electronic equipment | |
| CN111772619B (en) | Heart beat identification method based on deep learning, terminal equipment and storage medium | |
| CN112155602B (en) | Method and device for determining optimal standard section of fetus | |
| CN114463609B (en) | Method and device for determining fluorescent mixed points in cell microscopic image | |
| CN111462102B (en) | Intelligent analysis system and method based on novel coronavirus pneumonia X-ray chest radiography | |
| CN112184656A (en) | Method and device for determining fetus section based on ultrasonic dynamic image | |
| WO2018180197A1 (en) | Data analysis device, data analysis method and data analysis program | |
| CN115440196A (en) | Voice recognition method, device, medium and equipment based on user facial expression | |
| CN114708301A (en) | Motion artifact identification method and device, storage medium and electronic equipment | |
| CN113989519B (en) | Long-tail target detection method and system | |
| CN113918433A (en) | Adaptive intelligent network equipment performance index abnormity detection device and method | |
| US6941288B2 (en) | Online learning method in a decision system | |
| CN113763331A (en) | Coronary artery dominant type determination method, device, storage medium, and electronic apparatus | |
| CN113487223A (en) | Risk assessment method and risk assessment system based on information fusion | |
| CN115312178A (en) | Acute hypotension data processing method and device based on noninvasive parameters | |
| CN111968087A (en) | Plant disease area detection method | |
| CN110675382A (en) | Aluminum electrolysis superheat degree identification method based on CNN-LapseLM | |
| CN115662595A (en) | User information management method and system based on online diagnosis and treatment system | |
| CN115115038A (en) | Model construction method based on single lead electrocardiosignal and gender identification method | |
| CN114708634A (en) | Relative weight analysis method and device based on face image and electronic equipment | |
| CN114202110A (en) | Service fault prediction method and device based on RF-XGBOOST | |
| CN113111918A (en) | Cerebral apoplexy risk screening method based on abnormal sample detection and multi-dimensional information output | |
| CN112085584A (en) | Enterprise credit default probability calculation method and system | |
| CN115620802B (en) | Gene data processing method and system |
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 |