Perioperative period hypothermia prediction system based on artificial intelligence

Abstract

The invention provides a perioperative period hypothermia prediction system based on artificial intelligence, and relates to the technical field of body temperature prediction. Body temperature sample data of a target object in a perioperative period are collected in real time; determining a body temperature disturbance coefficient of each sample data point in the body temperature sample data, converting the body temperature sample data into a body temperature characterization sequence of the target object in the perioperative period according to all the body temperature disturbance coefficients, and determining a body temperature trend factor of the target object in the perioperative period through the body temperature characterization sequence; obtaining multi-dimensional factor data related to the target object in the perioperative period, and performing feature extraction on the multi-dimensional factor data to obtain perioperative period related feature vectors of the target object; according to the body temperature trend factor and the perioperative period related feature vector, perioperative period hypothermia prediction is carried out, and a perioperative period hypothermia prediction result of the target object is obtained. The related data quality of the target object can be improved, and the related features in the target object are extracted for body temperature prediction, so that the prediction precision of the prediction system is improved.

Description

Technical Field

[0001] The present application relates to the technical field of body temperature prediction, and more specifically, to an artificial intelligence-based perioperative hypothermia prediction system. Background Art

[0002] Perioperative hypothermia (PH) refers to the phenomenon that the patient's core body temperature drops below 36°C during surgery or within a short period of time after surgery. Hypothermia not only increases the risk of postoperative infection, coagulation dysfunction, cardiovascular complications, and hospitalization time, but also affects the patient's postoperative recovery. Therefore, accurate prediction and prevention of perioperative hypothermia are crucial for anesthesia management and perioperative care. In recent years, the development of artificial intelligence (AI) technology has provided new possibilities for the prediction of perioperative hypothermia, especially methods based on machine learning and deep learning, which can utilize large-scale surgical data to improve the accuracy and real-time nature of prediction.

[0003] In the existing technology, the performance of artificial intelligence models is highly dependent on the quality and quantity of data. However, perioperative data often have great heterogeneity. For example, the body temperature measurement methods (such as esophageal temperature, bladder temperature, axillary temperature, etc.) in different hospitals may be different, and there are also large differences in data formats and recording methods, which makes data integration and standardization a major problem. In addition, the perioperative data of some patients may be missing and noisy, which reduces the accuracy of model predictions. Therefore, how to improve the quality of relevant data of the target object and extract relevant features therein to predict body temperature in order to improve the prediction accuracy of the prediction system is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an artificial intelligence-based perioperative hypothermia prediction system, which can improve the quality of relevant data of the target object and extract relevant features therein to perform temperature prediction, so as to improve the prediction accuracy of the prediction system.

[0005] The present application provides a perioperative hypothermia prediction system based on artificial intelligence, the prediction system comprising: A data collection module is used to collect temperature sample data of the target object in the perioperative period in real time; A body temperature feature extraction module, used to determine the body temperature perturbation coefficient of each sample data point in the body temperature sample data, convert the body temperature sample data into a body temperature representation sequence of the target object in the perioperative period according to all the body temperature perturbation coefficients, and determine the body temperature trend factor of the target object in the perioperative period through the body temperature representation sequence; A related feature extraction module is used to obtain multidimensional factor data related to the target object during the perioperative period, perform feature extraction on the multidimensional factor data, and then obtain a perioperative related feature vector of the target object; The body temperature prediction module is used to predict perioperative hypothermia according to the body temperature trend factor and the perioperative-related characteristic vector, and then obtain the perioperative hypothermia prediction result of the target object.

[0006] In this embodiment, the body temperature sample data of the target object during the perioperative period is collected in real time by means of an intelligent temperature sensor.

[0007] In this embodiment, determining the body temperature disturbance coefficient of each sample data point in the body temperature sample data specifically includes: For each sample data point in the body temperature sample data, obtaining a neighboring sample domain of the sample data point; Determine the neighbor similarity sequence of the sample data point through the neighbor sample domain, and then obtain the neighbor similarity sequence of each sample data point; Determine the global data density of the body temperature sample data through the nearest similarity sequence of each sample data point; The body temperature disturbance coefficient of each sample data point in the body temperature sample data is determined respectively according to the corresponding nearest neighbor similarity sequence and the global data density.

[0008] In this embodiment, converting the body temperature sample data into a body temperature representation sequence of the target object during the perioperative period according to all body temperature disturbance coefficients specifically includes: Obtaining a preset disturbance threshold; Filtering out all body temperature characterization data points in the body temperature sample data according to each body temperature disturbance coefficient and the disturbance threshold; The body temperature characterization sequence of the target object during the perioperative period is constructed through all the body temperature characterization data points.

[0009] In this embodiment, determining the temperature trend factor of the target object during the perioperative period through the temperature characterization sequence specifically includes: Dividing the body temperature representation sequence to obtain body temperature representation segments of the target subject at different stages during the perioperative period; Determine the temperature trend fluctuation value of the target object at different stages during the perioperative period according to the corresponding temperature representation segment; The temperature trend factor of the target subject during the perioperative period is determined through all the temperature trend fluctuation values.

[0010] In this embodiment, the body temperature trend factor indicates the severity of the fluctuation of the body temperature data trend of the target object during the perioperative period.

[0011] In this embodiment, the multi-dimensional factor data includes the target subject's electronic medical record, anesthesia information, imaging examination data, and real-time physiological monitoring data.

[0012] In this embodiment, feature extraction is performed on the multidimensional factor data to obtain the perioperative-related feature vector of the target object, specifically including: Preprocessing the multidimensional factor data to obtain preprocessed multidimensional factor data; A deep learning-based feature extraction model is used to extract features from the preprocessed multidimensional factor data to obtain the perioperative-related feature vectors of the target object.

[0013] In this embodiment, the prediction of perioperative hypothermia based on the body temperature trend factor and the perioperative period-related feature vector is to input the body temperature trend factor and the perioperative period-related feature vector into a machine learning model to predict perioperative hypothermia.

[0014] In this embodiment, the perioperative hypothermia prediction result includes whether the target object has hypothermia and the predicted body temperature of the target object.

[0015] In this embodiment, the anomaly detection model is a long short-term memory network model.

[0016] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: The data acquisition module is used to collect the target object's body temperature sample data in the perioperative period in real time; the body temperature feature extraction module is used to determine the body temperature perturbation coefficient of each sample data point in the body temperature sample data, and the body temperature sample data is converted into a body temperature representation sequence of the target object in the perioperative period according to all the body temperature perturbation coefficients, and the body temperature trend factor of the target object in the perioperative period is determined through the body temperature representation sequence; the multidimensional factor data related to the target object in the perioperative period is obtained through the relevant feature extraction module, and the feature extraction is performed on the multidimensional factor data to obtain the perioperative relevant feature vector of the target object; the body temperature prediction module predicts perioperative hypothermia according to the body temperature trend factor and the perioperative relevant feature vector to obtain the perioperative hypothermia prediction result of the target object.

[0017] It can be seen that in the present application, firstly, by calculating the body temperature perturbation coefficient, abnormal fluctuations in perioperative body temperature changes can be effectively identified, and the body temperature sample data can be converted into a body temperature representation sequence. This process helps to remove noise data, highlight key temperature change points, and make the data more refined and efficient. By further calculating the body temperature trend factor, the body temperature change trend of individuals in different surgical stages can be quantified, thereby providing more representative input features for the artificial intelligence prediction model; then, by obtaining multidimensional factor data related to the target object in the perioperative period and performing deep learning-driven feature extraction on it, a high-dimensional, high-quality perioperative-related feature vector can be constructed, which can provide a more comprehensive description of the patient's physiological state and help the prediction model have stronger generalization ability and higher prediction accuracy; finally, by inputting the body temperature trend factor and the perioperative-related feature vector into the prediction model for perioperative hypothermia prediction, a variety of factors affecting body temperature can be comprehensively considered, thereby improving the accuracy and robustness of the prediction.

[0018] In summary, the technical solution adopted in this application can improve the quality of relevant data of the target object, and extract relevant features therein to predict body temperature, so as to improve the prediction accuracy of the prediction system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 It is a module structure diagram of the perioperative hypothermia prediction system based on artificial intelligence provided by the present application; Figure 2 is an exemplary flow chart for determining a temperature trend factor of a target subject during the perioperative period provided by the present application; Figure 3 is an exemplary flowchart for determining perioperative-related feature vectors of a target object provided by the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0022] The embodiment of the present application provides a perioperative hypothermia prediction system based on artificial intelligence, the core of which is to collect the temperature sample data of the target object in the perioperative period in real time through the data acquisition module; determine the temperature perturbation coefficient of each sample data point in the temperature sample data through the temperature feature extraction module, convert the temperature sample data into the temperature representation sequence of the target object in the perioperative period according to all the temperature perturbation coefficients, and determine the temperature trend factor of the target object in the perioperative period through the temperature representation sequence; obtain the multidimensional factor data related to the target object in the perioperative period through the relevant feature extraction module, extract the features of the multidimensional factor data, and then obtain the perioperative relevant feature vector of the target object; the temperature prediction module predicts perioperative hypothermia according to the temperature trend factor and the perioperative relevant feature vector, and then obtains the perioperative hypothermia prediction result of the target object. The above scheme can improve the quality of the relevant data of the target object, and extract the relevant features therein to perform temperature prediction, so as to improve the prediction accuracy of the prediction system.

[0023] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown, this figure is a module structure diagram of a perioperative hypothermia prediction system based on artificial intelligence according to this embodiment of the present application. The prediction system includes: a data acquisition module 100, a body temperature feature extraction module 200, a related feature extraction module 300 and a body temperature prediction module 400, which are respectively described as follows: The data collection module 100 collects the temperature sample data of the target object during the perioperative period in real time.

[0024] In specific implementation, the target object's body temperature sample data during the perioperative period can be collected in real time through an intelligent temperature sensor; it should be noted that in order to accurately predict perioperative hypothermia, the use of intelligent temperature sensors for real-time body temperature monitoring can effectively improve the timeliness and accuracy of the data. In this application, continuous body temperature monitoring of the target object is achieved through a non-contact infrared temperature sensor or an implantable / attached temperature sensor, thereby obtaining the target object's body temperature sample data during the perioperative period.

[0025] The body temperature feature extraction module 200 is used to determine the body temperature perturbation coefficient of each sample data point in the body temperature sample data, convert the body temperature sample data into a body temperature characterization sequence of the target object in the perioperative period based on all the body temperature perturbation coefficients, and determine the body temperature trend factor of the target object in the perioperative period through the body temperature characterization sequence.

[0026] In this embodiment, the body temperature disturbance coefficient of each sample data point in the body temperature sample data may be determined in the following manner, namely: For each sample data point in the body temperature sample data, obtaining a neighboring sample domain of the sample data point; Determine the neighbor similarity sequence of the sample data point through the neighbor sample domain, and then obtain the neighbor similarity sequence of each sample data point; Determine the global data density of the body temperature sample data through the nearest similarity sequence of each sample data point; The body temperature disturbance coefficient of each sample data point in the body temperature sample data is determined respectively according to the corresponding nearest neighbor similarity sequence and the global data density.

[0027] In specific implementation, first, for each sample data point in the body temperature sample data, a neighbor sample domain of the sample data point can be obtained, that is, the neighbor similarity between the sample data point and other sample data points in the body temperature sample data is calculated by means of Euclidean distance, and the neighbor similarity represents the degree of similarity between the sample data points, thereby selecting the M sample data points closest to the sample data point, wherein the value of M can be preset according to historical experience, and the data set consisting of all the selected sample data points is used as the neighbor sample domain of the sample data point; then, the neighbor similarity sequence of the sample data point can be determined through the neighbor sample domain, that is, the neighbor similarities between each sample data point in the neighbor sample domain and the sample data point are arranged in order of size, thereby using the obtained sequence as the neighbor similarity sequence of the sample data point, and the neighbor similarity sequence of each sample data point can be obtained in the above manner.

[0028] In addition, in the specific implementation, the global data density of the body temperature sample data can be determined by the neighbor similarity sequence of each sample data point, wherein the global data density represents the overall data density of the body temperature sample data, and the mean of the neighbor similarity sequence of each sample data point can be calculated, thereby taking the mean of all calculation results as the global data density of the body temperature sample data; then, the body temperature perturbation coefficient of each sample data point in the body temperature sample data can be determined respectively according to the corresponding neighbor similarity sequence and the global data density, wherein the body temperature perturbation coefficient is an indicator representing the degree of perturbation of the sample data point to the overall data, and for each sample data point, the ratio of each neighbor similarity in the neighbor similarity sequence of the sample data point to the global data density can be calculated, thereby taking the mean of all calculation results as the body temperature perturbation coefficient of the sample data point, and the body temperature perturbation coefficient of each sample data point in the body temperature sample data can be obtained in the above manner.

[0029] In this embodiment, the body temperature sample data is converted into a body temperature representation sequence of the target object during the perioperative period according to all body temperature disturbance coefficients in the following manner, namely: Obtaining a preset disturbance threshold; Filtering out all body temperature characterization data points in the body temperature sample data according to each body temperature disturbance coefficient and the disturbance threshold; The body temperature characterization sequence of the target object during the perioperative period is constructed through all the body temperature characterization data points.

[0030] In the specific implementation, first, a pre-set disturbance threshold can be obtained, and the disturbance threshold can be set based on historical data and expert experience, which will not be repeated here; then, all body temperature characterization data points in the body temperature sample data can be screened out according to each body temperature disturbance coefficient and the disturbance threshold, that is, the sample data points in the body temperature sample data whose body temperature disturbance coefficient is less than the disturbance threshold are screened out, and the screened sample data points are used as body temperature characterization data points. All body temperature characterization data points in the body temperature sample data can be obtained in the above manner. It should be noted that when the body temperature disturbance coefficient is not less than the disturbance threshold, it indicates that the corresponding sample data point is a disturbance data point, that is, noise and interference; finally, the body temperature characterization sequence of the target object in the perioperative period can be constructed through all the body temperature characterization data points, that is, all the body temperature characterization data points are combined in the order of collection time, so that the composed sequence is used as the body temperature characterization sequence of the target object in the perioperative period.

[0031] Preferably, in this embodiment, reference Figure 2 As shown, this figure is an exemplary flow chart of determining the temperature trend factor of the target object during the perioperative period in an embodiment of the present application. In this embodiment, determining the temperature trend factor of the target object during the perioperative period through the temperature characterization sequence can be specifically implemented by the following steps: In step S21, the body temperature characterization sequence is divided to obtain body temperature characterization segments of the target object at different stages during the perioperative period; In step S22, the temperature trend fluctuation values ​​of the target subject at different stages during the perioperative period are determined according to the corresponding temperature representation segments; In step S23, the body temperature trend factor of the target subject during the perioperative period is determined through all the body temperature trend fluctuation values.

[0032] In the specific implementation, first, the body temperature representation sequence can be divided, that is, the body temperature representation sequence can be divided according to the corresponding stages of the target object in the perioperative period, so that the body temperature representation segments of the target object in different stages of the perioperative period can be obtained, and the perioperative period includes the preoperative stage, the intraoperative stage and the postoperative stage; then, the body temperature trend fluctuation value of the target object in different stages of the perioperative period can be determined according to the corresponding body temperature representation segment, wherein the body temperature trend fluctuation value represents the severity of the fluctuation of the body temperature data trend of the target object in the perioperative period, and the body temperature representation data points in the body temperature representation segment can be fitted by binomial, so as to obtain To the corresponding body temperature characterization curve, the average curvature of the body temperature characterization curve can be calculated, and the calculation result can be used as the body temperature trend fluctuation value of this stage. The body temperature trend fluctuation values ​​of the target object at different stages in the perioperative period can be obtained in the above manner; finally, the body temperature trend factor of the target object in the perioperative period can be determined through all the body temperature trend fluctuation values, wherein the body temperature trend factor indicates the severity of the fluctuation of the temperature data trend of the target object in the perioperative period, that is, each body temperature trend fluctuation value can be used as the value of the body temperature trend factor in the corresponding stage. The body temperature trend factor of the target object in the perioperative period can be obtained in the above manner.

[0033] It should be noted that by calculating the temperature perturbation coefficient, abnormal fluctuations in perioperative temperature changes can be effectively identified, and the temperature sample data can be converted into a temperature representation sequence. This process helps to remove noise data, highlight key temperature change points, and make the data more refined and efficient. By further calculating the temperature trend factor, the temperature change trend of individuals at different surgical stages can be quantified, thereby providing more representative input features for the artificial intelligence prediction model. The above method can significantly improve data quality, make the model pay more attention to the key factors that actually affect the occurrence of hypothermia, and reduce the interference of redundant information on prediction accuracy.

[0034] The relevant feature extraction module 300 is used to obtain multidimensional factor data related to the target object during the perioperative period, perform feature extraction on the multidimensional factor data, and then obtain a perioperative relevant feature vector of the target object.

[0035] It should be noted that in the present application, the multidimensional factor data includes the target object's electronic medical records, anesthesia information, imaging examination data and real-time physiological monitoring data; in specific implementation, the target object's electronic medical records can be obtained through the hospital information system, the target object's anesthesia information can be obtained through the anesthesia information management system, the target object's imaging examination data can be obtained through the medical image archiving and communication system, and the target object's real-time physiological monitoring data can be obtained through the patient monitoring system.

[0036] Preferably, in this embodiment, reference Figure 3As shown in FIG. 1 , this figure is an exemplary flow chart of determining the perioperative-related feature vector of the target object in an embodiment of the present application. In this embodiment, feature extraction of the multidimensional factor data is performed to obtain the perioperative-related feature vector of the target object, which can be specifically implemented by the following steps: In step S31, the multidimensional factor data is preprocessed to obtain preprocessed multidimensional factor data; In step S32, a deep learning-based feature extraction model is used to extract features from the preprocessed multidimensional factor data, thereby obtaining a perioperative-related feature vector of the target object.

[0037] In the specific implementation, first, the multidimensional factor data is preprocessed, that is, the numerical data in the multidimensional factor data is cleaned and missing values ​​are processed, and the time series data in the multidimensional factor data is aligned to ensure that the timestamps of intraoperative physiological monitoring data, anesthesia information, and preoperative examination data are consistent. Linear interpolation is used to fill the missing time points for physiological data at different times, and in order to reduce the impact of different data distributions on the model, the numerical features are normalized; then, different deep learning models are used for feature extraction for different types of data to automatically learn high-dimensional feature representations, that is, the feature extraction model based on deep learning can be used to extract features from the preprocessed multidimensional factor data. For example, the electronic medical records of the target object are extracted using a natural language processing (NLP) + Transformer / BERT model, the anesthesia information of the target object is extracted using a time series model based on LSTM (Long Short-Term Memory Network), the image examination data feature is extracted using a CNN deep learning network based on ResNet / EfficientNet, and the image examination data feature is extracted using a CNN based on LSTM / GRU + Transformer The time series model is used to extract features from real-time physiological monitoring data, so that the vector composed of all extracted features can be used as the perioperative related feature vector of the target object.

[0038] It should be noted that by obtaining multidimensional factor data related to the target object during the perioperative period (such as electronic medical records, anesthesia information, imaging examination data, and real-time physiological monitoring data) and performing deep learning-driven feature extraction on it, a high-dimensional, high-quality perioperative-related feature vector (PFV) can be constructed. The main advantages of doing so are: First, multi-source data fusion can provide a more comprehensive description of the patient's physiological state, improve the integrity and consistency of the data, and avoid information loss or deviation that may be caused by a single data source. Secondly, the deep learning model can automatically extract complex potential patterns, especially long-term dependent temporal features, such as intraoperative temperature change trends, the effects of anesthetic drugs on body temperature, etc., to ensure that the model can learn key features. In addition, imaging data combined with text medical record information can help identify potential hypothermia risk factors (such as thyroid dysfunction or hemodynamic instability) in patients, thereby enhancing the robustness of the prediction. Finally, through multimodal data fusion and feature vector construction, the temperature prediction model has stronger generalization ability and higher prediction accuracy, which can identify perioperative hypothermia risks earlier and more accurately, optimize surgical management, and improve patient safety.

[0039] The body temperature prediction module 400 is used to predict perioperative hypothermia according to the body temperature trend factor and the perioperative-related characteristic vector, and then obtain a perioperative hypothermia prediction result of the target object.

[0040] In this embodiment, the prediction of perioperative hypothermia based on the body temperature trend factor and the perioperative period-related feature vector is to input the body temperature trend factor and the perioperative period-related feature vector into a machine learning model to predict perioperative hypothermia.

[0041] It should be noted that the perioperative hypothermia prediction result includes whether the target object has hypothermia and the predicted body temperature of the target object; in specific implementation, the body temperature trend factor and the perioperative-related feature vector can be input into a suitable machine learning model, and the body temperature trend factor and the perioperative-related feature vector will be subjected to feature fusion (such as feature splicing or weighted fusion) to form a unified input vector, which is passed to the machine learning model. The machine learning model used in this application is a support vector machine (SVM). Other machine learning models can also be selected in actual implementation, which is not limited here. The machine learning model will make predictions based on the real-time input body temperature trend factor and perioperative-related feature vector, and the machine learning model will output the perioperative hypothermia prediction result, which includes whether the target object has hypothermia and the predicted body temperature of the target object.

[0042] In addition, it should be noted that by inputting the temperature trend factor and the perioperative-related feature vector into the prediction model, perioperative hypothermia prediction can comprehensively consider various factors affecting body temperature, such as the patient's basic information, anesthesia data, real-time physiological monitoring, imaging examination, etc., to improve the comprehensiveness and accuracy of the prediction. Through the fusion and feature extraction of multi-dimensional data, not only the quality of the target object-related data is improved, but also the prediction system can automatically identify key factors from a large amount of complex data, reduce errors caused by human intervention, and thus improve the accuracy and robustness of the prediction.

[0043] It can be seen that in the present application, firstly, by calculating the body temperature perturbation coefficient, abnormal fluctuations in perioperative body temperature changes can be effectively identified, and the body temperature sample data can be converted into a body temperature representation sequence. This process helps to remove noise data, highlight key temperature change points, and make the data more refined and efficient. By further calculating the body temperature trend factor, the body temperature change trend of individuals in different surgical stages can be quantified, thereby providing more representative input features for the artificial intelligence prediction model; then, by obtaining multidimensional factor data related to the target object in the perioperative period and performing deep learning-driven feature extraction on it, a high-dimensional, high-quality perioperative-related feature vector can be constructed, which can provide a more comprehensive description of the patient's physiological state and help the prediction model have stronger generalization ability and higher prediction accuracy; finally, by inputting the body temperature trend factor and the perioperative-related feature vector into the prediction model for perioperative hypothermia prediction, a variety of factors affecting body temperature can be comprehensively considered, thereby improving the accuracy and robustness of the prediction.

[0044] In summary, the technical solution adopted in this application can improve the quality of relevant data of the target object, and extract relevant features therein to predict body temperature, so as to improve the prediction accuracy of the prediction system.

[0045] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0046] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the 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), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0047] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. An artificial intelligence-based perioperative hypothermia prediction system, characterized in that: The prediction system comprises: A data collection module is used to collect temperature sample data of the target object in the perioperative period in real time; A body temperature feature extraction module, used to determine the body temperature perturbation coefficient of each sample data point in the body temperature sample data, convert the body temperature sample data into a body temperature representation sequence of the target object in the perioperative period according to all the body temperature perturbation coefficients, and determine the body temperature trend factor of the target object in the perioperative period through the body temperature representation sequence; A related feature extraction module is used to obtain multidimensional factor data related to the target object during the perioperative period, perform feature extraction on the multidimensional factor data, and then obtain a perioperative related feature vector of the target object; The body temperature prediction module is used to predict perioperative hypothermia according to the body temperature trend factor and the perioperative-related characteristic vector, and then obtain the perioperative hypothermia prediction result of the target object.

2. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: The intelligent temperature sensor is used to collect the target object’s body temperature sample data in real time during the perioperative period.

3. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: Determining the body temperature disturbance coefficient of each sample data point in the body temperature sample data specifically includes: For each sample data point in the body temperature sample data, obtaining a neighboring sample domain of the sample data point; Determine the neighbor similarity sequence of the sample data point through the neighbor sample domain, and then obtain the neighbor similarity sequence of each sample data point; Determine the global data density of the body temperature sample data through the nearest similarity sequence of each sample data point; The body temperature disturbance coefficient of each sample data point in the body temperature sample data is determined respectively according to the corresponding nearest neighbor similarity sequence and the global data density.

4. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: Converting the body temperature sample data into a body temperature representation sequence of the target object during the perioperative period according to all body temperature disturbance coefficients specifically includes: Obtaining a preset disturbance threshold; Filtering out all body temperature characterization data points in the body temperature sample data according to each body temperature disturbance coefficient and the disturbance threshold; The body temperature characterization sequence of the target object during the perioperative period is constructed through all the body temperature characterization data points.

5. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: Determining the temperature trend factor of the target object during the perioperative period through the temperature characterization sequence specifically includes: Dividing the body temperature representation sequence to obtain body temperature representation segments of the target subject at different stages during the perioperative period; Determine the temperature trend fluctuation value of the target object at different stages during the perioperative period according to the corresponding temperature representation segment; The temperature trend factor of the target subject during the perioperative period is determined through all the temperature trend fluctuation values.

6. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: The body temperature trend factor indicates the severity of the fluctuation of the body temperature data trend of the target subject during the perioperative period.

7. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: The multidimensional factor data includes the target subject's electronic medical record, anesthesia information, imaging examination data and real-time physiological monitoring data.

8. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: Extracting features from the multidimensional factor data to obtain perioperative-related feature vectors of the target object specifically includes: Preprocessing the multidimensional factor data to obtain preprocessed multidimensional factor data; A deep learning-based feature extraction model is used to extract features from the preprocessed multidimensional factor data to obtain the perioperative-related feature vectors of the target object.

9. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: Predicting perioperative hypothermia according to the body temperature trend factor and the perioperative period-related feature vector is to input the body temperature trend factor and the perioperative period-related feature vector into a machine learning model to predict perioperative hypothermia.

10. The artificial intelligence-based perioperative hypothermia prediction system according to claim 1, characterized in that: The perioperative hypothermia prediction result includes whether the target subject has hypothermia and the predicted body temperature of the target subject.

Images