Endocrine patient health management method and system integrated with electronic medical record

Abstract

The invention relates to the technical field of intelligent medical treatment, in particular to an endocrine patient health management method and system integrated with an electronic medical record. The method comprises the following steps: performing multi-dimensional data acquisition of an endocrine patient through a hospital information system, and performing multi-dimensional portrait construction of the patient to obtain a multi-dimensional health portrait of the patient; performing time sequence data feature extraction on the multi-dimensional health portrait of the patient to obtain time sequence feature data; acquiring historical physiological data of the patient; establishing an individualized physiological rhythm model according to the historical physiological data of the patient to obtain the individualized physiological rhythm model; and performing non-uniform interpolation on the time sequence characteristic data according to the individualized physiological rhythm model to obtain interpolated data. According to the method, the individualized physiological rhythm model and the dynamic baseline model are constructed, the dynamic early warning threshold value and subtype layering are combined, and accurate risk assessment and individualized health information management are performed on each patient, so that the health management effect is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and in particular to an endocrine patient health management method and system integrated with electronic medical records. Background Art

[0002] Traditional endocrine disease management mainly relies on regular follow-up by doctors and self-monitoring by patients. This approach has many limitations, such as: patients' physiological data are scattered in different medical institutions and systems, making them difficult to integrate and analyze; doctors need to spend a lot of time collecting and organizing data, which is inefficient; patients need to go to the hospital for regular follow-up visits, which is time-consuming and labor-intensive, and easily leads to a decrease in compliance. Later, electronic medical records and information technology were used to improve the health management of endocrine patients. Early methods mainly focused on using electronic medical record data for disease risk prediction and early warning, but most of these methods were based on group statistical data and ignored individual differences among patients, resulting in low accuracy in prediction and early warning.

[0003] The occurrence and development of endocrine diseases are affected by many factors, including genetics, environment, lifestyle, etc. Therefore, the disease phenotype and progression rate of different patients vary significantly. Health management methods that ignore individual differences have the following main disadvantages:

[0004] Inappropriate warning thresholds: Using a unified warning threshold will result in oversensitivity to some patients, resulting in frequent false alarms, while being insensitive to other patients, making it easy to miss real risks. For example, the range of blood sugar fluctuations varies greatly between the elderly and young people. Using the same blood sugar warning threshold will result in the elderly receiving frequent hypoglycemia warnings, while young people will not be able to receive high blood sugar warnings in time.

[0005] Poor health management results: Due to ignoring the individual differences of patients, health management plans are difficult to truly meet the needs of patients, resulting in poor management results. Summary of the invention

[0006] Based on this, it is necessary to provide an endocrine patient health management method and system integrating electronic medical records to solve at least one of the above technical problems.

[0007] To achieve the above purpose, a method for endocrine patient health management integrating electronic medical records comprises the following steps:

[0008] Step S1: Collect multi-dimensional data of endocrine patients through the integrated electronic medical records in the hospital information system, and construct a multi-dimensional portrait of the patient to obtain a multi-dimensional health portrait of the patient;

[0009] Step S2: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; obtaining the patient's historical physiological data; constructing an individualized physiological rhythm model based on the patient's historical physiological data to obtain an individualized physiological rhythm model; performing physiological rhythm-based non-uniform interpolation on the time series feature data according to the individualized physiological rhythm model to obtain interpolated data; generating an individualized dynamic baseline model based on the interpolated data to obtain an individualized dynamic baseline model;

[0010] Step S3: acquiring real-time physiological indicator data; calculating physiological indicator deviations according to the individualized dynamic baseline model and the real-time physiological indicator data to obtain physiological indicator deviation values; setting dynamic warning thresholds according to the patient's historical physiological data and the individualized dynamic baseline model to obtain warning dynamic thresholds; performing deviation warning identification on physiological indicator deviation values ​​according to the warning dynamic thresholds to obtain a real-time risk assessment report;

[0011] Step S4: Perform standardized feature extraction on the real-time risk assessment report and the patient's multi-dimensional health portrait to obtain standardized feature data; perform DBSCAN clustering analysis on the standardized feature data to obtain clustering results; perform clustering subtype stratification based on the clustering results to obtain subtype feature data; generate an individualized data report based on the subtype feature data and the real-time risk assessment report to obtain an individualized data report to implement endocrine patient health management operations.

[0012] The present invention integrates multi-dimensional data from hospital information systems, wearable devices and lifestyle questionnaires to construct a comprehensive patient health portrait, laying a solid data foundation for subsequent personalized analysis and precise management, thereby improving the overall effectiveness of health management. By constructing an individualized physiological rhythm model and a dynamic baseline model, personalized prediction and fluctuation range estimation of patient physiological indicators are achieved, providing an important reference basis for subsequent precise warning and risk assessment, thereby improving the personalization and accuracy of health management. By acquiring physiological indicator data in real time, and combining individualized dynamic baseline models and dynamic warning thresholds, real-time monitoring and deviation warning of patient physiological indicators are achieved, potential health risks can be discovered in time, and real-time data support is provided for subsequent risk assessment, thereby improving the timeliness and effectiveness of health management. By performing subtype stratification and cluster analysis on patients, and combining real-time risk data, a personalized data report is generated, providing patients and medical staff with more intuitive and easier-to-understand health information and personalized management suggestions, thereby improving the pertinence and practicality of health management. Therefore, the present invention provides an endocrine patient health management method with integrated electronic medical records, which effectively solves the shortcomings of existing methods that ignore individual differences in patients. By constructing an individualized physiological rhythm model and a dynamic baseline model, and combining it with dynamic warning thresholds and subtype stratification, this method achieves accurate risk assessment and personalized health information management for each patient, thereby significantly improving the effectiveness of health management.

[0013] Preferably, step S1 comprises the following steps:

[0014] Step S11: extracting the electronic medical record data of endocrine patients through the integrated electronic medical record in the hospital information system to obtain the electronic medical record data;

[0015] Step S12: synchronizing the device data of the wearable medical device of the endocrine patient through the wireless communication protocol to obtain real-time physiological data;

[0016] Step S13: Acquire lifestyle data; perform data cleaning and preprocessing on the electronic medical record data, real-time physiological data, and lifestyle data to obtain preprocessed patient data;

[0017] Step S14: construct a multi-dimensional portrait of the patient based on the pre-processed patient data to obtain a multi-dimensional health portrait of the patient.

[0018] By extracting electronic medical record data from the hospital information system, the present invention can comprehensively collect the patient's medical history, diagnosis, treatment, examination and other information, provide basic data for building a multi-dimensional health portrait of the patient, avoid information omission, and improve the accuracy of health management. The structured data format is also convenient for subsequent data processing and analysis. By synchronizing data with wearable medical devices, the patient's physiological index data, such as blood sugar, heart rate, blood pressure, etc., can be obtained in real time, timely reflect the patient's physiological state changes, realize continuous monitoring of the patient, and improve the timeliness of health management. Obtaining lifestyle data, such as diet, exercise, smoking, drinking, etc., can more comprehensively understand the patient's health status, identify potential risk factors, provide more accurate information for personalized health management, and improve the effectiveness of health management. By cleaning and preprocessing multi-source data, the quality and consistency of the data can be improved, and the influence of data noise and outliers can be eliminated. Constructing a multi-dimensional health portrait of the patient can integrate the patient's static information and dynamic data, form a comprehensive understanding of the patient's health status, provide a basis for subsequent risk assessment and personalized intervention, and ultimately improve the overall effect of health management.

[0019] Preferably, step S2 comprises the following steps:

[0020] Step S21: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; performing time granularity uniform processing on the time series feature data to obtain time granularity uniform data;

[0021] Step S22: Acquire historical physiological data of the patient; construct an individualized physiological rhythm model according to the historical physiological data of the patient to obtain an individualized physiological rhythm model;

[0022] Step S23: performing physiological rhythm-based non-uniform interpolation on the time granularity unified data according to the individualized physiological rhythm model to obtain interpolated data;

[0023] Step S24: Generate time series data according to the interpolated data and the unified time granularity data to obtain time series data; perform time series data segmentation on the time series data to obtain time series segmentation data;

[0024] Step S25: training a recurrent neural network model on the time series segmentation data to obtain a recurrent neural network model;

[0025] Step S26: inputting the time series data into the recurrent neural network model to predict the fluctuation range of the target physiological index, and obtaining the fluctuation range data of the physiological index;

[0026] Step S27: Generate an individualized dynamic baseline model based on the physiological indicator fluctuation range data and the recurrent neural network model to obtain an individualized dynamic baseline model.

[0027] The present invention can provide standardized and consistent data input for subsequent physiological rhythm model construction and dynamic baseline model generation by extracting time series data features and unifying time granularity, thereby improving the accuracy and reliability of the model. By constructing an individualized physiological rhythm model, the physiological fluctuation law unique to individual patients, such as postprandial blood glucose fluctuation pattern, circadian rhythm, etc., can be captured, providing a personalized reference basis for subsequent precise interpolation and dynamic baseline model construction. Based on the non-uniform interpolation method of the physiological rhythm model, the missing physiological index data can be estimated more accurately, the errors caused by methods such as linear interpolation can be avoided, and the integrity and accuracy of the data can be improved, especially in time periods with large fluctuations in physiological indicators, such as after meals. Generate complete time series data and perform segmentation, which can provide standardized input data for the training of the recurrent neural network model, ensuring that the model can learn the temporal dependence and fluctuation law of the patient's physiological indicators. By training the recurrent neural network model, the complex temporal patterns of the patient's physiological indicators can be learned, providing a powerful prediction model for the subsequent prediction of the fluctuation range of physiological indicators, and improving the accuracy of the prediction. Predicting the fluctuation range of the target physiological index can provide personalized fluctuation range information for the construction of the dynamic baseline model, so that the dynamic baseline model can better adapt to the physiological fluctuation characteristics of individual patients. By building an individualized dynamic baseline model, the baseline level can be dynamically adjusted according to the individual patient's physiological rhythm and fluctuation range, achieving more accurate deviation warning and risk assessment, avoiding misjudgment due to individual differences, and improving the personalization and effectiveness of health management.

[0028] Preferably, step S22 comprises the following steps:

[0029] Step S221: extracting postprandial blood glucose data from the patient's historical physiological data to obtain a postprandial blood glucose data set;

[0030] Step S222: performing peak time recognition on the postprandial blood glucose data set to obtain peak time data; performing peak height recognition on the postprandial blood glucose data set to obtain peak height data;

[0031] Step S223: performing peak characteristic analysis according to the peak time data and the peak height data to obtain peak characteristic data;

[0032] Step S224: Calculating the blood sugar drop rate for the post-meal blood sugar data set to obtain drop rate data;

[0033] Step S225: Gaussian process regression is used to construct an individualized physiological rhythm model for the peak characteristic data and the fall-back speed data to obtain an individualized physiological rhythm model.

[0034] By extracting postprandial blood glucose data, the present invention can focus on analyzing the fluctuation of postprandial blood glucose of patients, which is a critical period for blood glucose management and helps to capture the individualized postprandial blood glucose response pattern of patients more accurately. Identifying the peak time and peak height of postprandial blood glucose can quantify the key features of postprandial blood glucose fluctuations of patients and provide basic data for subsequent peak feature analysis. By analyzing the peak time and peak height, the postprandial blood glucose fluctuation pattern of patients can be deeply understood, such as the peak occurrence time and peak amplitude, to provide more refined feature input for the construction of individualized physiological rhythm models. Calculating the blood glucose drop speed can quantify the speed at which the patient's postprandial blood glucose returns to the baseline level, supplement the postprandial blood glucose fluctuation information outside the peak feature, and enable the physiological rhythm model to more comprehensively describe the patient's postprandial blood glucose response. Using Gaussian process regression to construct an individualized physiological rhythm model can effectively learn and fit the individualized postprandial blood glucose fluctuation pattern of patients, and can probabilistically predict future postprandial blood glucose fluctuations, improve the accuracy and reliability of the prediction, and thus better support personalized health management.

[0035] Preferably, step S23 includes the following steps:

[0036] Step S231: marking missing values ​​on the unified time granularity data to obtain missing value marked data; locating blood glucose missing values ​​on the missing value marked data to obtain blood glucose missing value location data;

[0037] Step S232: determining the most recent meal time for the blood sugar missing value location data to obtain the most recent meal time data;

[0038] Step S233: Calculate the missing time interval according to the blood glucose missing value position data and the most recent meal time data to obtain time interval data; input the most recent meal time data and the time interval data into the individualized physiological rhythm model to predict the blood glucose value to obtain a blood glucose prediction value; use the blood glucose prediction value as a preliminary interpolation of the blood glucose missing value, and generate preliminary interpolation blood glucose data to obtain preliminary interpolation blood glucose data;

[0039] Step S234: extracting exercise and medication information from the patient's multi-dimensional health portrait to obtain exercise and medication information data;

[0040] Step S235: correcting the interpolation result of the preliminary interpolated blood sugar data according to the sports medication information data to obtain corrected blood sugar data;

[0041] Step S236: performing physiological index interpolation processing of the time granularity unified data according to the individualized physiological rhythm model, the missing value marked data and the corrected blood glucose data to obtain the interpolated data.

[0042] By marking and locating missing values, the present invention can clarify which time points of blood glucose data need to be interpolated, provide target guidance for the subsequent interpolation process, and ensure the pertinence and effectiveness of the interpolation process. Determining the time of the most recent meal can provide important contextual information for interpolation based on the physiological rhythm model, because postprandial blood glucose fluctuations are greatly affected by meal time. Using individualized physiological rhythm models and meal time information for blood glucose prediction and preliminary interpolation, the missing blood glucose value can be estimated according to the physiological laws of individual patients, which is more accurate than simple linear interpolation, especially in the case of large postprandial blood glucose fluctuations. Extracting exercise and medication information can obtain important factors affecting blood glucose levels and provide necessary adjustment basis for subsequent correction of interpolation results. Correcting the preliminary interpolation results according to exercise and medication information can further improve the accuracy of blood glucose interpolation, because exercise and medication will have a significant impact on blood glucose levels. Combining individualized physiological rhythm models, missing value markings and corrected blood glucose data for final interpolation can generate more complete and accurate unified data of time granularity, providing a high-quality data basis for subsequent dynamic baseline model construction and risk assessment.

[0043] Preferably, step S3 comprises the following steps:

[0044] Step S31: acquiring real-time physiological index data of the patient through the wearable medical device, and acquiring context information related to the index, to obtain real-time physiological index data and index context information;

[0045] Step S32: using the individualized dynamic baseline model, performing dynamic baseline model prediction according to the indicator context information to obtain dynamic baseline model prediction data;

[0046] Step S33: performing deviation calculation on the real-time physiological index data and the dynamic baseline model prediction data to obtain a physiological index deviation value;

[0047] Step S34: setting a dynamic warning threshold according to the patient's historical physiological data and the individualized dynamic baseline model to obtain a warning dynamic threshold; triggering a warning according to the warning dynamic threshold to obtain warning information;

[0048] Step S35: Perform real-time risk assessment according to the early warning information to obtain real-time risk assessment results;

[0049] Step S36: Generate a real-time risk assessment report based on the real-time risk assessment results, warning information, and indicator context information to obtain a real-time risk assessment report.

[0050] The present invention can continuously monitor the physiological state of the patient by acquiring the patient's physiological index data and context information in real time, and understand the relevant factors affecting the changes in physiological indicators, so as to provide real-time and comprehensive data input for subsequent dynamic baseline model prediction and risk assessment. By using the individualized dynamic baseline model and context information for prediction, the baseline level can be dynamically adjusted according to the individual physiological characteristics and real-time status of the patient, thereby improving the accuracy and personalization of the baseline prediction. By calculating the deviation between the real-time physiological index data and the dynamic baseline prediction value, the degree to which the physiological index deviates from the normal range can be quantified, providing an important reference indicator for subsequent early warning triggering and risk assessment. By setting the dynamic early warning threshold according to the patient's historical data and the individualized dynamic baseline model, the false positives and false negatives caused by the fixed threshold can be avoided, the accuracy and sensitivity of the early warning can be improved, and personalized early warning settings can be performed according to the individual situation of the patient. By performing real-time risk assessment according to the early warning information, the patient's potential health risks can be identified in time. By generating a real-time risk assessment report, the patient's real-time physiological data, risk assessment results, and personalized health information can be integrated together, which is convenient for medical staff and patients to understand the patient's health status and improve the efficiency and effectiveness of health information management.

[0051] Preferably, step S34 includes the following steps:

[0052] Step S341: extracting an individualized baseline range according to the individualized dynamic baseline model to obtain individualized baseline range data;

[0053] Step S342: Calculating the volatility index of the patient's historical physiological data to obtain volatility index data;

[0054] Step S343: setting an initial threshold value according to the individualized baseline range data to obtain an initial warning threshold value.

[0055] Step S344: dynamically adjusting the initial warning threshold according to the volatility index data to obtain a dynamic warning threshold;

[0056] Step S345: using the early warning dynamic threshold to compare the deviation of the physiological index, and trigger an early warning to obtain early warning information.

[0057] The present invention can obtain the normal fluctuation range of the patient's physiological indicators by extracting individualized baseline range data, and provide a personalized reference basis for the subsequent setting of early warning thresholds. By calculating the volatility index of the patient's historical physiological data, the degree of fluctuation of the patient's physiological indicators can be quantified, providing important reference information for dynamically adjusting the early warning threshold. By setting the initial threshold according to the individualized baseline range data, the trigger range of the early warning can be preliminarily determined, and combined with the subsequent dynamic adjustment, a more accurate early warning can be achieved. By dynamically adjusting the early warning threshold according to the volatility index data, the early warning threshold can be better adapted to the individual physiological fluctuation characteristics of the patient, avoiding false alarms and missed alarms due to individual differences, and improving the accuracy of the early warning. By using the dynamic early warning threshold for deviation comparison and early warning triggering, it is possible to accurately determine whether the early warning needs to be triggered according to the patient's real-time physiological state and individualized fluctuation conditions, thereby improving the timeliness and effectiveness of the early warning.

[0058] Preferably, step S4 comprises the following steps:

[0059] Step S41: performing feature selection and extraction on the real-time risk assessment report and the multi-dimensional health portrait of the patient to obtain feature data to be clustered;

[0060] Step S42: performing feature dimensionality reduction on the clustered feature data to obtain reduced-dimensional feature data; performing feature standardization on the reduced-dimensional feature data to obtain standardized feature data;

[0061] Step S43: performing DBSCAN cluster analysis on the standardized feature data to obtain clustering results;

[0062] Step S44: performing subtype stratification according to the clustering results to obtain subtype stratification data; performing sub-feature analysis on the subtype stratification data to obtain subtype feature data;

[0063] Step S45: grouping the patients into subtypes according to the subtype stratification data and the subtype characteristic data to obtain patient subtype grouping data; extracting subtype group characteristics from a preset subtype group characteristic database according to the patient subtype grouping data to obtain subtype group characteristic data;

[0064] Step S46: extracting real-time risk data from the real-time risk assessment report to obtain real-time risk data;

[0065] Step S47: Generate an individualized data report for the subtype group characteristic data and the real-time risk data to obtain an individualized data report; perform data visualization processing on the individualized data report to implement health management operations for endocrine patients.

[0066] The present invention can provide effective data input for subsequent cluster analysis by selecting and extracting key features from real-time risk assessment reports and multi-dimensional health portraits of patients, and remove redundant information to improve clustering efficiency and accuracy. Dimensionality reduction and standardization of feature data can reduce data dimensions, eliminate the impact of dimensions between different features, and improve the efficiency and stability of clustering algorithms. Cluster analysis using the DBSCAN algorithm can effectively identify data clusters of different densities and separate noise points, thereby more accurately stratifying patients into subtypes. Subtype stratification is performed according to clustering results, and feature analysis is performed on each subtype, which can deeply understand the characteristics of patients of different subtypes and provide more refined information for personalized health management. Patients are grouped according to subtype stratification data and subtype feature data, and corresponding information is extracted from a preset subtype group feature database, which can provide more targeted management solutions for each subtype group and improve the personalization of health management. Extracting real-time risk data can understand the current risk status of patients and provide important real-time information for generating individualized data reports. Combining subtype group characteristic data and real-time risk data to generate individualized data reports and perform data visualization can provide patients and medical staff with more intuitive and easier-to-understand health information, facilitate patient self-management, and assist medical staff in understanding more detailed patient health information, ultimately improving the overall effectiveness of health management.

[0067] Preferably, step S43 includes the following steps:

[0068] Step S431: performing k-nearest neighbor distance calculation on each data point in the standardized feature data to obtain a k-nearest neighbor distance list;

[0069] Step S432: Draw a k distance graph according to the k nearest neighbor distance list to obtain a k distance graph;

[0070] Step S433: Adaptively determine the neighborhood radius according to the k-distance graph to obtain a neighborhood radius list;

[0071] Step S434: Calculate the time decay factor for each data point in the standardized feature data to obtain the time decay factor;

[0072] Step S435: performing time-weighted distance calculation on the standardized feature data according to the time attenuation factor to obtain time-weighted distance data;

[0073] Step S436: Perform DBSCAN clustering analysis on the standardized feature data according to the time-weighted distance data and the neighborhood radius list to obtain clustering results.

[0074] The present invention can quantify the local density of data points in feature space by calculating the k nearest neighbor distance of each data point, and provide basic data for subsequent drawing of k distance graph and determination of neighborhood radius. Drawing k distance graph can intuitively show the distribution of k nearest neighbor distance of data point, help users observe data density changes more clearly, and thus more accurately determine the neighborhood radius parameter of DBSCAN algorithm. Determine adaptive neighborhood radius according to k distance graph, automatically adjust neighborhood radius parameter according to actual distribution of data, avoid subjectivity and uncertainty caused by manual parameter setting, and improve clustering effect of DBSCAN algorithm. Calculate time decay factor, can reduce the weight of earlier data points in cluster analysis, make clustering results more focused on reflecting the patient's recent situation, and improve the timeliness of clustering results. Calculate time weighted distance according to time decay factor, can incorporate time factor into distance metric, make distance calculation more in line with actual situation, and improve clustering accuracy of DBSCAN algorithm. Combine time weighted distance and adaptive neighborhood radius to carry out DBSCAN cluster analysis, can comprehensively consider data density and time factors, more accurately identify different subtypes of patient populations, and improve the accuracy and effectiveness of subtype stratification.

[0075] Preferably, the present invention further provides an endocrine patient health management system integrated with electronic medical records, which is used to execute the endocrine patient health management method integrated with electronic medical records as described above, and the endocrine patient health management system integrated with electronic medical records comprises:

[0076] The multi-dimensional data collection module is used to collect multi-dimensional data of endocrine patients through the integrated electronic medical records in the hospital information system, and to construct a multi-dimensional portrait of the patient to obtain a multi-dimensional health portrait of the patient;

[0077] The time series data modeling module is used to extract time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; obtain the patient's historical physiological data; construct an individualized physiological rhythm model based on the patient's historical physiological data to obtain an individualized physiological rhythm model; perform non-uniform interpolation based on physiological rhythm on the time series feature data according to the individualized physiological rhythm model to obtain interpolated data; generate an individualized dynamic baseline model based on the interpolated data to obtain an individualized dynamic baseline model;

[0078] Deviation warning identification module, used to obtain real-time physiological index data; calculate physiological index deviation according to individualized dynamic baseline model and real-time physiological index data to obtain physiological index deviation value; set dynamic warning threshold according to patient's historical physiological data and individualized dynamic baseline model to obtain warning dynamic threshold; perform deviation warning identification on physiological index deviation value according to warning dynamic threshold to obtain real-time risk assessment report;

[0079] The subtype hierarchical clustering module is used to extract standardized features from real-time risk assessment reports and multi-dimensional health portraits of patients to obtain standardized feature data; perform DBSCAN clustering analysis on the standardized feature data to obtain clustering results; perform clustering subtype stratification based on the clustering results to obtain subtype feature data; generate individualized data reports based on subtype feature data and real-time risk assessment reports to obtain individualized data reports, so as to realize endocrine patient health management operations.

[0080] The present invention integrates multi-dimensional data from hospital information systems, wearable devices and lifestyle questionnaires to construct a comprehensive patient health portrait, laying a solid data foundation for subsequent personalized analysis and precise management, thereby improving the overall effectiveness of health management. By constructing an individualized physiological rhythm model and a dynamic baseline model, personalized prediction and fluctuation range estimation of patient physiological indicators are achieved, providing an important reference basis for subsequent precise warning and risk assessment, thereby improving the personalization and accuracy of health management. By acquiring physiological indicator data in real time, and combining individualized dynamic baseline models and dynamic warning thresholds, real-time monitoring and deviation warning of patient physiological indicators are achieved, potential health risks can be discovered in time, and real-time data support is provided for subsequent risk assessment, thereby improving the timeliness and effectiveness of health management. By performing subtype stratification and cluster analysis on patients, and combining real-time risk data, a personalized data report is generated, providing patients and medical staff with more intuitive and easier-to-understand health information and personalized management suggestions, thereby improving the pertinence and practicality of health management. Therefore, the present invention provides an endocrine patient health management method with integrated electronic medical records, which effectively solves the shortcomings of existing methods that ignore individual differences in patients. By constructing an individualized physiological rhythm model and a dynamic baseline model, and combining it with dynamic warning thresholds and subtype stratification, this method achieves accurate risk assessment and personalized health information management for each patient, thereby significantly improving the effectiveness of health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 A schematic flow chart of the steps of an endocrine patient health management method integrated with electronic medical records;

[0082] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0083] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0084] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0085] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0086] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0087] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0088] To achieve this, please refer to Figures 1 to 3 , a method for endocrine patient health management integrated with electronic medical records, comprising the following steps:

[0089] Step S1: Collect multi-dimensional data of endocrine patients through the integrated electronic medical records in the hospital information system, and construct a multi-dimensional portrait of the patient to obtain a multi-dimensional health portrait of the patient;

[0090] Step S2: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; obtaining the patient's historical physiological data; constructing an individualized physiological rhythm model based on the patient's historical physiological data to obtain an individualized physiological rhythm model; performing physiological rhythm-based non-uniform interpolation on the time series feature data according to the individualized physiological rhythm model to obtain interpolated data; generating an individualized dynamic baseline model based on the interpolated data to obtain an individualized dynamic baseline model;

[0091] Step S3: acquiring real-time physiological indicator data; calculating physiological indicator deviations according to the individualized dynamic baseline model and the real-time physiological indicator data to obtain physiological indicator deviation values; setting dynamic warning thresholds according to the patient's historical physiological data and the individualized dynamic baseline model to obtain warning dynamic thresholds; performing deviation warning identification on physiological indicator deviation values ​​according to the warning dynamic thresholds to obtain a real-time risk assessment report;

[0092] Step S4: Perform standardized feature extraction on the real-time risk assessment report and the patient's multi-dimensional health portrait to obtain standardized feature data; perform DBSCAN clustering analysis on the standardized feature data to obtain clustering results; perform clustering subtype stratification based on the clustering results to obtain subtype feature data; generate an individualized data report based on the subtype feature data and the real-time risk assessment report to obtain an individualized data report to implement endocrine patient health management operations.

[0093] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart of the steps of the endocrine patient health management method integrated with electronic medical records of the present invention. In this example, the endocrine patient health management method integrated with electronic medical records includes the following steps:

[0094] Step S1: Collect multi-dimensional data of endocrine patients through the integrated electronic medical records in the hospital information system, and construct a multi-dimensional portrait of the patient to obtain a multi-dimensional health portrait of the patient;

[0095] In an embodiment of the present invention, the electronic medical record data of the patient is extracted through the hospital information system, including demographic information, diagnosis information, medication information, test results, and hospitalization information. At the same time, the patient's real-time physiological data, such as blood sugar, heart rate, blood pressure, etc., are synchronized through wearable medical devices, and the patient's lifestyle data, such as diet, exercise, smoking, drinking, etc., are obtained through questionnaires or mobile phone applications. The collected multi-dimensional data is cleaned and preprocessed, such as removing duplicate values, processing missing values, and performing data standardization. Finally, the pre-processed data is integrated to construct a multi-dimensional health portrait of the patient, for example, using JSON format to represent it, including dimensions such as demographic characteristics, medical history, physiological indicators, and lifestyle.

[0096] Step S2: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; obtaining the patient's historical physiological data; constructing an individualized physiological rhythm model based on the patient's historical physiological data to obtain an individualized physiological rhythm model; performing physiological rhythm-based non-uniform interpolation on the time series feature data according to the individualized physiological rhythm model to obtain interpolated data; generating an individualized dynamic baseline model based on the interpolated data to obtain an individualized dynamic baseline model;

[0097] In an embodiment of the present invention, time series data features, such as blood sugar value, blood pressure value, heart rate, etc., are extracted from the multidimensional health portrait of the patient, and the time granularity is unified, such as every hour. The patient's historical physiological data, such as blood sugar data for at least three months, is obtained. Postprandial blood sugar data is extracted, the peak time and peak height are identified, peak feature analysis is performed, and the blood sugar drop rate is calculated. Gaussian process regression is used to construct an individualized physiological rhythm model with peak features and drop rate as input. Missing values ​​in the unified data of time granularity are marked and located, the time of the most recent meal is determined, and the missing time interval is calculated. The most recent meal time and time interval are input into the individualized physiological rhythm model, and the blood sugar value is predicted for preliminary interpolation. Exercise and medication information are extracted from the multidimensional health portrait of the patient, and the preliminary interpolation results are corrected. Finally, the corrected blood sugar value is used to interpolate the unified data of time granularity to obtain complete time series data. The data is used for time series segmentation, and a recurrent neural network model (such as LSTM) is trained to predict the fluctuation range of the target physiological indicator. According to the fluctuation range and the recurrent neural network model, an individualized dynamic baseline model is generated.

[0098] Step S3: acquiring real-time physiological indicator data; calculating physiological indicator deviations according to the individualized dynamic baseline model and the real-time physiological indicator data to obtain physiological indicator deviation values; setting dynamic warning thresholds according to the patient's historical physiological data and the individualized dynamic baseline model to obtain warning dynamic thresholds; performing deviation warning identification on physiological indicator deviation values ​​according to the warning dynamic thresholds to obtain a real-time risk assessment report;

[0099] In an embodiment of the present invention, the wearable medical device is used to obtain the patient's physiological index data, such as blood sugar, heart rate, blood pressure, etc. in real time, and obtain relevant context information, such as meal time, exercise type, etc. The individualized dynamic baseline model and the indicator context information are used to predict the dynamic baseline value and fluctuation range of the current time. The deviation value between the real-time physiological index data and the dynamic baseline prediction value is calculated. The dynamic warning threshold is set according to the patient's historical physiological data and the individualized dynamic baseline model. Specifically, the baseline range data is first extracted from the individualized dynamic baseline model, the volatility index (such as standard deviation) of the patient's historical physiological data is calculated, the initial warning threshold is set according to the baseline range data, and then the initial threshold is dynamically adjusted according to the volatility index. The physiological index deviation value is compared with the dynamic warning threshold. If the deviation value exceeds the threshold, the warning is triggered and the warning information is generated. Real-time risk assessment is performed based on the warning information, the real-time physiological index value, the patient's medical history and medication status. Finally, the real-time risk assessment results, warning information and indicator context information are integrated to generate a real-time risk assessment report.

[0100] Step S4: extract standardized features from the real-time risk assessment report and the multi-dimensional health portrait of the patient to obtain standardized feature data; perform DBSCAN cluster analysis on the standardized feature data to obtain clustering results; perform clustering subtype stratification according to the clustering results to obtain subtype feature data; generate an individualized data report according to the subtype feature data and the real-time risk assessment report to obtain an individualized data report to implement health management operations for endocrine patients;

[0101] In an embodiment of the present invention, features such as risk level, demographic characteristics, medical history, physiological indicators, lifestyle, etc. are extracted from the real-time risk assessment report and the multi-dimensional health portrait of the patient to form the feature data to be clustered. The PCA method is used to reduce the dimension of the feature data, and the Z-score method is used to standardize it. The DBSCAN algorithm is used to perform cluster analysis on the standardized feature data. Among them, the k nearest neighbor distance of each data point is calculated, the k distance graph is drawn, and the adaptive neighborhood radius is determined according to the k distance graph. The time decay factor of each data point is calculated, and the time weighted distance is calculated according to the time decay factor. DBSCAN clustering is performed using the time weighted distance and the adaptive neighborhood radius. Subtype stratification is performed according to the clustering results, and the characteristic statistical indicators of each subtype are calculated as subtype characteristic data. The patient is divided into different subtype groups, and the corresponding subtype group characteristic data is extracted from the preset subtype group characteristic database. Real-time risk data is extracted from the real-time risk assessment report. Finally, an individualized data report is generated by combining the subtype group characteristic data and the real-time risk data, and data visualization processing is performed, such as using charts to display the patient's physiological indicators, risk level and personalized health management information.

[0102] Preferably, step S1 comprises the following steps:

[0103] Step S11: extracting the electronic medical record data of endocrine patients through the integrated electronic medical record in the hospital information system to obtain the electronic medical record data;

[0104] Step S12: synchronizing the device data of the wearable medical device of the endocrine patient through the wireless communication protocol to obtain real-time physiological data;

[0105] Step S13: Acquire lifestyle data; perform data cleaning and preprocessing on the electronic medical record data, real-time physiological data, and lifestyle data to obtain preprocessed patient data;

[0106] Step S14: construct a multi-dimensional portrait of the patient based on the pre-processed patient data to obtain a multi-dimensional health portrait of the patient.

[0107] In an embodiment of the present invention, the electronic medical record data of endocrine patients is extracted through the database interface of the hospital information system (HIS), for example, using SQL query statements. The extracted data includes but is not limited to: basic patient information (name, age, sex, medical history, family history, etc.), diagnostic information (disease name, diagnosis time, ICD code, etc.), medication information (drug name, dosage, usage, medication time, etc.), test results (blood sugar, blood pressure, blood lipids, etc.), hospitalization information (admission time, discharge time, hospitalization diagnosis, etc.) and other relevant clinical data. The extracted data is stored in a structured data format, such as a CSV file or a database table, for subsequent processing and analysis. For example, for a patient diagnosed with type 2 diabetes, all blood sugar records, medication records, and related test results, such as glycosylated hemoglobin, liver and kidney function, etc., are extracted for the past 3 years and stored in a CSV file, where each row represents a record and each column represents a data field.

[0108] Data is synchronized with the wearable medical devices (e.g., blood glucose monitors, smart watches, sports bracelets, etc.) of endocrine patients through Bluetooth or other wireless communication protocols. Real-time acquisition of patients' physiological data, such as blood glucose levels, heart rate, blood pressure, sleep duration, exercise steps, etc. Set the frequency of data synchronization, such as synchronization every 5 minutes, and timestamp the acquired data to ensure the timing of the data. After the synchronized data is converted into a format, it is stored in the database, such as using JSON format to store data such as blood glucose levels, heart rate, blood pressure, and the corresponding timestamp is recorded. For example, every 15 minutes, blood glucose data is automatically synchronized from the continuous glucose monitor (CGM) worn by the patient, and the data is stored in the database in the form of a timestamp-blood glucose value pair, such as "2024-10-27, 10:00:00, 100mg / dL".

[0109] Obtain the patient's lifestyle data through questionnaires, mobile phone applications or other data collection methods, including but not limited to: eating habits (e.g., daily intake of carbohydrates, fats, and proteins, meal times, etc.), exercise status (e.g., exercise type, exercise duration, exercise intensity, etc.), smoking status, drinking status, sleep quality, etc. Quantify the collected lifestyle data, such as converting eating habits into daily calories and converting exercise status into weekly exercise energy consumption. Store the quantified data as structured data, for example, use numerical variables to record daily carbohydrate intake, and use enumeration types to record smoking status (e.g., never smoked, quit smoking, still smoking). For example, record the patient's daily diet through a mobile phone APP, including food types, intake, etc., and use the food database to calculate the total calories, carbohydrates, fats, and protein intake ratios per day.

[0110] Based on the pre-processed patient data obtained in steps S11, S12 and S13, a multi-dimensional health portrait of the patient is constructed. First, the data is cleaned, such as removing duplicate values, processing missing values ​​(such as using mean filling or KNN interpolation), correcting erroneous data, etc. Then, the data is standardized, such as converting the data to the same dimension for comparison and analysis. Finally, based on the pre-processed data, a multi-dimensional health portrait of the patient is constructed, including: demographic characteristics, medical history, physiological indicators, lifestyle, etc. For example, the patient's age, gender, BMI, blood sugar history data, exercise habits, eating habits and other information are integrated into a unified data structure to form a health portrait of the patient, such as using JSON format, where each dimension contains corresponding specific data. For example, "{'demographic': {'age': 50, 'gender': 'male'}, 'medical history': {'diabetes': 'type 2'}, 'physiological indicators': {'average blood sugar': 150}, 'lifestyle': {'exercise': 'low'}}".

[0111] Preferably, step S2 comprises the following steps:

[0112] Step S21: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; performing time granularity uniform processing on the time series feature data to obtain time granularity uniform data;

[0113] Step S22: Acquire historical physiological data of the patient; construct an individualized physiological rhythm model according to the historical physiological data of the patient to obtain an individualized physiological rhythm model;

[0114] Step S23: performing physiological rhythm-based non-uniform interpolation on the time granularity unified data according to the individualized physiological rhythm model to obtain interpolated data;

[0115] Step S24: Generate time series data according to the interpolated data and the unified time granularity data to obtain time series data; perform time series data segmentation on the time series data to obtain time series segmentation data;

[0116] Step S25: training a recurrent neural network model on the time series segmentation data to obtain a recurrent neural network model;

[0117] Step S26: inputting the time series data into the recurrent neural network model to predict the fluctuation range of the target physiological index, and obtaining the fluctuation range data of the physiological index;

[0118] Step S27: Generate an individualized dynamic baseline model based on the physiological indicator fluctuation range data and the recurrent neural network model to obtain an individualized dynamic baseline model.

[0119] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0120] Step S21: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; performing time granularity uniform processing on the time series feature data to obtain time granularity uniform data;

[0121] In an embodiment of the present invention, time-related physiological indicator data, such as blood sugar value, blood pressure value, heart rate, etc., and time-related events, such as medication time, meal time, exercise time, etc., are extracted from the multi-dimensional health portrait of the patient to form time series feature data. All time series feature data are unified to the same time granularity, for example, once an hour. If the time granularity of the original data is smaller than the target granularity, an aggregation operation is performed, such as calculating the average blood sugar value per hour; if the time granularity of the original data is larger than the target granularity, an interpolation operation is performed, such as using a linear interpolation method to supplement missing values. For example, blood sugar data recorded every 15 minutes is converted into average blood sugar data per hour, and daily medication records are converted into medication dosages per hour (the dosage at the medication time point is the actual dosage, and the dosage at other time points is 0). Finally, data with unified time granularity is obtained.

[0122] Step S22: Acquire historical physiological data of the patient; construct an individualized physiological rhythm model according to the historical physiological data of the patient to obtain an individualized physiological rhythm model;

[0123] In an embodiment of the present invention, historical physiological data of the patient for at least three months, such as blood sugar level, heart rate, blood pressure, etc., are obtained. An individualized physiological rhythm model is constructed using the Gaussian process regression method. Taking blood sugar as an example, the historical blood sugar data is used as a training set, time is used as an input variable, and blood sugar level is used as an output variable to train the Gaussian process regression model. The kernel function of the model selects the radial basis function (RBF), and the hyperparameters are optimized using the gradient descent method. Through training, an individualized blood sugar physiological rhythm model of the patient is obtained, which can predict the blood sugar fluctuation trend in the future.

[0124] Step S23: performing physiological rhythm-based non-uniform interpolation on the time granularity unified data according to the individualized physiological rhythm model to obtain interpolated data;

[0125] In an embodiment of the present invention, according to the individualized physiological rhythm model, non-uniform interpolation based on physiological rhythm is performed on the uniform data of time granularity. For example, if a patient's postprandial blood sugar fluctuates greatly, more intensive interpolation is performed in the postprandial time period, and sparser interpolation is performed in other time periods. The specific interpolation method can use cubic spline interpolation or interpolation based on the predicted value of the physiological rhythm model. For example, for a diabetic patient, according to his individualized blood sugar physiological rhythm model, a blood sugar value is interpolated every 15 minutes within 2 hours after a meal, and a blood sugar value is interpolated every hour in other time periods.

[0126] Step S24: Generate time series data according to the interpolated data and the unified time granularity data to obtain time series data; perform time series data segmentation on the time series data to obtain time series segmentation data;

[0127] In an embodiment of the present invention, the interpolated data is merged with the unified time granularity data to generate complete time series data. Then, the time series data is segmented according to a fixed time window, for example, with 24 hours as a time window, the time series data is segmented into multiple data segments of length 24, each data segment represents the physiological index data of one day, and forms time series segmented data. For example, a month's blood sugar data is segmented into 30 data segments according to 24 hours per day, and each data segment contains 24 blood sugar values.

[0128] Step S25: training a recurrent neural network model on the time series segmentation data to obtain a recurrent neural network model;

[0129] In an embodiment of the present invention, a recurrent neural network model is trained using time series segmentation data, such as a long short-term memory network (LSTM) or a gated recurrent unit (GRU). Taking blood sugar as an example, the blood sugar data of each time period is used as the input sequence, the blood sugar value at the next time point is used as the output, the mean square error (MSE) is used as the loss function, and the Adam optimizer is used for model training. A recurrent neural network model that can predict future blood sugar values ​​is obtained through training. For example, a recurrent neural network containing two LSTM layers is constructed using the PyTorch framework, with an input dimension of 24 and an output dimension of 1, and the model is trained using three months of historical blood sugar data.

[0130] Step S26: inputting the time series data into the recurrent neural network model to predict the fluctuation range of the target physiological index, and obtaining the fluctuation range data of the physiological index;

[0131] In an embodiment of the present invention, the time series data is input into a recurrent neural network model to predict the fluctuation range of the target physiological index in the future. For example, the blood sugar fluctuation range in the next 24 hours is predicted, and the maximum and minimum values ​​of the blood sugar value per hour can be obtained. For example, the blood sugar data of the past week is input into the trained LSTM model to predict the blood sugar fluctuation range per hour in the next 24 hours, for example, the blood sugar range at 10 o'clock is predicted to be 90-120 mg / dL.

[0132] Step S27: generating an individualized dynamic baseline model according to the physiological index fluctuation range data and the recurrent neural network model to obtain an individualized dynamic baseline model;

[0133] In an embodiment of the present invention, an individualized dynamic baseline model is constructed based on the physiological indicator fluctuation range data and the recurrent neural network model. The dynamic baseline model can dynamically adjust the baseline range according to factors such as time and physiological state. For example, the median of the physiological indicator fluctuation range can be used as the dynamic baseline value, and the upper and lower quartiles of the fluctuation range can be used as the fluctuation range of the dynamic baseline. For example, based on the predicted 24-hour blood sugar fluctuation range, the median of blood sugar per hour is calculated as the dynamic baseline value of the hour, and the upper and lower quartiles of the fluctuation range are calculated as the fluctuation range of the dynamic baseline.

[0134] Preferably, step S22 comprises the following steps:

[0135] Step S221: extracting postprandial blood glucose data from the patient's historical physiological data to obtain a postprandial blood glucose data set;

[0136] Step S222: performing peak time recognition on the postprandial blood glucose data set to obtain peak time data; performing peak height recognition on the postprandial blood glucose data set to obtain peak height data;

[0137] Step S223: performing peak characteristic analysis according to the peak time data and the peak height data to obtain peak characteristic data;

[0138] Step S224: Calculating the blood sugar drop rate for the post-meal blood sugar data set to obtain drop rate data;

[0139] Step S225: Gaussian process regression is used to construct an individualized physiological rhythm model for the peak characteristic data and the fall-back speed data to obtain an individualized physiological rhythm model.

[0140] In an embodiment of the present invention, postprandial blood glucose data is extracted from the patient's historical physiological data to construct a postprandial blood glucose data set. First, the postprandial time window is determined, such as 2 hours after a meal. Then, based on the patient's meal record, the blood glucose data within 2 hours after the meal is extracted. If the patient uses a continuous blood glucose monitor (CGM), the blood glucose data of the corresponding time period is directly extracted; if the patient uses a traditional blood glucose meter, the blood glucose data of 0.5 hours, 1 hour and 2 hours after the meal are extracted. The extracted postprandial blood glucose data and its corresponding timestamp are stored in the postprandial blood glucose data set. For example, all blood glucose records marked as "postprandial" for the patient with patient ID 123 in the past three months are queried from the database, and the timestamps and blood glucose values ​​of these records are stored in a new data table to form a postprandial blood glucose data set.

[0141] The peak time and peak height are identified for each postprandial blood glucose sequence in the postprandial blood glucose dataset. The peak time is defined as the time point when the postprandial blood glucose reaches the highest value, and the peak height is defined as the highest value of the postprandial blood glucose. The peak is identified using the local maximum algorithm. For example, traverse each postprandial blood glucose sequence and find the local maximum, that is, the blood glucose value at this time point is greater than the blood glucose values ​​at the two time points before and after it. Record the time point corresponding to the local maximum as the peak time, and record the local maximum as the peak height. If there are multiple local maxima, select the local maximum with the largest value as the peak.

[0142] Perform peak feature analysis on the peak time data and peak height data. Calculate the difference between the peak time and meal time of each postprandial blood glucose sequence as the peak occurrence time. Calculate the difference between the peak height and the pre-meal blood glucose value as the peak amplitude. Use the peak occurrence time and peak amplitude as peak feature data. For example, calculate the peak occurrence time and peak amplitude of each postprandial blood glucose sequence, and store these data in a new data table. For example, a patient's postprandial blood glucose peak occurs 1 hour after the meal, with a peak value of 180 mg / dL, and the pre-meal blood glucose is 90 mg / dL, then the peak occurrence time is 1 hour, and the peak amplitude is 90 mg / dL.

[0143] The blood glucose drop rate is calculated for each postprandial blood glucose sequence in the postprandial blood glucose data set. The blood glucose drop rate is defined as the time taken for the peak blood glucose value to drop to the baseline blood glucose value, or as the time taken for the peak blood glucose value to drop to a specific value (such as the pre-meal blood glucose value). The linear regression method can be used to fit the curve of the peak blood glucose value drop, and the slope of the curve is calculated as the blood glucose drop rate. For example, the least squares method is used to fit the curve of the peak blood glucose value dropping to the pre-meal blood glucose value, and the slope of the curve is the blood glucose drop rate, in mg / dL / hour.

[0144] Use the Gaussian process regression method to build an individualized physiological rhythm model. Use peak feature data (peak time and peak amplitude) and fall rate data as input features, and use the postprandial blood glucose sequence as output. Use the radial basis function (RBF) as the kernel function, and use the gradient descent method to optimize the hyperparameters. Through training, a personalized physiological rhythm model that can predict postprandial blood glucose fluctuations based on peak features and fall rate is obtained. For example, use the GaussianProcessRegressor function in Python's scikit-learn library, use the peak time, peak amplitude and fall rate as input features, and use the postprandial blood glucose sequence as output to train the Gaussian process regression model.

[0145] Preferably, step S23 includes the following steps:

[0146] Step S231: marking missing values ​​on the unified time granularity data to obtain missing value marked data; locating blood glucose missing values ​​on the missing value marked data to obtain blood glucose missing value location data;

[0147] Step S232: determining the most recent meal time for the blood sugar missing value location data to obtain the most recent meal time data;

[0148] Step S233: Calculate the missing time interval according to the blood glucose missing value position data and the most recent meal time data to obtain time interval data; input the most recent meal time data and the time interval data into the individualized physiological rhythm model to predict the blood glucose value to obtain a blood glucose prediction value; use the blood glucose prediction value as a preliminary interpolation of the blood glucose missing value, and generate preliminary interpolation blood glucose data to obtain preliminary interpolation blood glucose data;

[0149] Step S234: extracting exercise and medication information from the patient's multi-dimensional health portrait to obtain exercise and medication information data;

[0150] Step S235: correcting the interpolation result of the preliminary interpolated blood sugar data according to the sports medication information data to obtain corrected blood sugar data;

[0151] Step S236: performing physiological index interpolation processing of the time granularity unified data according to the individualized physiological rhythm model, the missing value marked data and the corrected blood glucose data to obtain the interpolated data.

[0152] In the embodiment of the present invention, the unified data of time granularity is traversed, and the missing blood glucose values ​​are marked as special values, such as NaN (Not a Number), to generate missing value marking data. The position of the missing blood glucose value in the time series is recorded, such as a timestamp or sequence index, to generate blood glucose missing value position data. For example, in a blood glucose data sequence with a time granularity of hours, if the blood glucose value at 10:00 is missing, the blood glucose value at that time point is marked as NaN, and 10:00 is recorded in the blood glucose missing value position data.

[0153] According to the missing blood sugar value location data, find the most recent meal time to the missing value. Obtain meal time data from the patient's diet record. Calculate the time difference between each missing value time point and all meal time points, and select the meal time with the smallest time difference as the most recent meal time. For example, if the missing blood sugar value location is 10:00, and the patient's meal records are 7:00 and 12:00, the most recent meal time is 7:00.

[0154] Calculate the time interval between the missing blood glucose value location and the most recent meal time. Convert the missing value location and the most recent meal time into minutes, and then calculate the difference between the two to obtain the time interval data. Input the most recent meal time and time interval data into the personalized physiological rhythm model to predict the blood glucose value at that time point. Use the predicted blood glucose value as a preliminary interpolation of the missing value to generate preliminary interpolated blood glucose data. For example, if the missing blood glucose value location is 10:00 and the most recent meal time is 7:00, the time interval is 180 minutes. Input 7:00 and 180 minutes into the personalized physiological rhythm model to obtain a predicted blood glucose value of 120 mg / dL. Use 120 mg / dL as the blood glucose value at 10:00 to generate preliminary interpolated blood glucose data.

[0155] Extract exercise and medication information from the patient's multi-dimensional health portrait. Extract exercise type, exercise start time, exercise end time, and exercise intensity from exercise records. Extract medication time, drug name, and dosage from medication records. Integrate the extracted information into exercise medication information data. For example, extract that the patient started moderate-intensity running at 9:00, lasted for 30 minutes, and took 10 mg of glimepiride at 8:00, and record this information into exercise medication information data.

[0156] The preliminary interpolated blood glucose data is corrected based on the exercise and medication information data. For example, if the patient exercised or took hypoglycemic drugs during the missing value period, the preliminary interpolated blood glucose value is adjusted based on information such as exercise type, exercise intensity, drug type and dosage. Corrections can be made using pre-set rules or machine learning-based models. For example, if the patient performed moderate-intensity exercise during the missing value period, the preliminary interpolated blood glucose value is reduced by 10 mg / dL.

[0157] According to the individualized physiological rhythm model, missing value marked data and corrected blood glucose data, physiological index interpolation processing is performed on the unified data with time granularity. For data points marked as missing values, the corrected blood glucose value is used to fill them. For data points with non-missing values, their original values ​​are kept unchanged. Finally, the interpolated data is obtained, in which all missing values ​​have been reasonably interpolated according to the physiological rhythm model and exercise medication information. For example, the blood glucose value of 110mg / dL is filled into the blood glucose data at 10:00, and the blood glucose data at other time points remain unchanged to generate the final interpolated data.

[0158] Preferably, step S3 comprises the following steps:

[0159] Step S31: acquiring real-time physiological index data of the patient through the wearable medical device, and acquiring context information related to the index, to obtain real-time physiological index data and index context information;

[0160] Step S32: using the individualized dynamic baseline model, performing dynamic baseline model prediction according to the indicator context information to obtain dynamic baseline model prediction data;

[0161] Step S33: performing deviation calculation on the real-time physiological index data and the dynamic baseline model prediction data to obtain a physiological index deviation value;

[0162] Step S34: setting a dynamic warning threshold according to the patient's historical physiological data and the individualized dynamic baseline model to obtain a warning dynamic threshold; triggering a warning according to the warning dynamic threshold to obtain warning information;

[0163] Step S35: Perform real-time risk assessment according to the early warning information to obtain real-time risk assessment results;

[0164] Step S36: Generate a real-time risk assessment report based on the real-time risk assessment results, warning information, and indicator context information to obtain a real-time risk assessment report.

[0165] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0166] Step S31: acquiring real-time physiological index data of the patient through the wearable medical device, and acquiring context information related to the index, to obtain real-time physiological index data and index context information;

[0167] In an embodiment of the present invention, a Bluetooth or other wireless connection is established with the patient's wearable medical device (e.g., a continuous blood glucose monitor, a smart watch) to obtain the patient's physiological indicator data, such as blood glucose level, heart rate, blood pressure, etc. in real time. At the same time, contextual information related to the indicator is obtained, such as: meal time, meal amount, exercise type, exercise duration, medication time, medication dosage, sleep duration, stress level, etc. The acquired physiological indicator data and contextual information are timestamped to ensure the timing and consistency of the data. For example, the blood glucose value is obtained every 5 minutes from the continuous blood glucose monitor worn by the patient, and the meal time, meal amount and other information entered by the patient through the mobile phone APP are recorded at the same time.

[0168] Step S32: using the individualized dynamic baseline model, performing dynamic baseline model prediction according to the indicator context information to obtain dynamic baseline model prediction data;

[0169] In an embodiment of the present invention, an individualized dynamic baseline model is used to predict the dynamic baseline value and fluctuation range of the current time based on the indicator context information. For example, the current time, the time of the last meal, the amount of meal, exercise information, etc. are used as input variables and input into the individualized dynamic baseline model to predict the dynamic baseline value and fluctuation range of blood glucose at the current time. For example, if the current time is 10:00, the patient eats at 8:00, the meal amount is 50g of carbohydrates, and at 9:00, 30 minutes of moderate intensity exercise is performed, then this information is input into the dynamic baseline model, and the dynamic baseline value of blood glucose at 10:00 is predicted to be 110mg / dL, and the fluctuation range is 90-130mg / dL.

[0170] Step S33: performing deviation calculation on the real-time physiological index data and the dynamic baseline model prediction data to obtain a physiological index deviation value;

[0171] In an embodiment of the present invention, the deviation value between the real-time physiological index data and the dynamic baseline model prediction data is calculated. The real-time physiological index data is subtracted from the baseline value predicted by the dynamic baseline model to obtain the deviation value. The deviation value can reflect the degree to which the real-time physiological index deviates from the baseline. For example, if the real-time blood glucose value is 140 mg / dL and the baseline value predicted by the dynamic baseline model is 110 mg / dL, the deviation value is 30 mg / dL.

[0172] Step S34: setting a dynamic warning threshold according to the patient's historical physiological data and the individualized dynamic baseline model to obtain a warning dynamic threshold; triggering a warning according to the warning dynamic threshold to obtain warning information;

[0173] In an embodiment of the present invention, a dynamic warning threshold is set according to the patient's historical physiological data and an individualized dynamic baseline model. The dynamic warning threshold can be dynamically adjusted according to the patient's physiological state and historical data. For example, the blood sugar warning threshold can be set to the dynamic baseline value plus or minus a certain proportion of the standard deviation based on the patient's blood sugar fluctuations over the past period of time. For example, if the patient's blood sugar standard deviation over the past week is 20 mg / dL, the blood sugar warning threshold is set to the dynamic baseline value ±2*20 mg / dL. According to the comparison between the warning dynamic threshold and the physiological index deviation value, if the deviation value exceeds the warning threshold, the warning is triggered and warning information is generated, including warning time, warning type (such as high blood sugar warning or low blood sugar warning), real-time physiological index value, dynamic baseline value and warning threshold.

[0174] Step S35: Perform real-time risk assessment according to the early warning information to obtain real-time risk assessment results;

[0175] In an embodiment of the present invention, a real-time risk assessment is performed based on the warning information. For example, the patient's current health risk level is assessed based on the warning type, real-time physiological index values, and the patient's medical history, medication status, and other information. Risk assessment can be performed using pre-set rules or machine learning-based models. For example, if a patient triggers a high blood sugar warning and the real-time blood sugar value is higher than 250 mg / dL, the patient's risk level is assessed as high risk.

[0176] Step S36: Generate a real-time risk assessment report based on the real-time risk assessment results, warning information, and indicator context information to obtain a real-time risk assessment report;

[0177] In an embodiment of the present invention, the real-time risk assessment results, early warning information, and indicator context information are integrated to generate a real-time risk assessment report. The report content includes: basic information of the patient, real-time physiological indicator data, dynamic baseline values, early warning information, risk assessment results, and recommendations and intervention measures for risks. For example, a real-time risk assessment report is generated that includes the patient's name, age, real-time blood sugar value, dynamic baseline value, high blood sugar early warning information, high risk assessment results, and a recommendation that the patient take hypoglycemic drugs immediately or seek medical help.

[0178] Preferably, step S34 includes the following steps:

[0179] Step S341: extracting an individualized baseline range according to the individualized dynamic baseline model to obtain individualized baseline range data;

[0180] Step S342: Calculating the volatility index of the patient's historical physiological data to obtain volatility index data;

[0181] Step S343: setting an initial threshold value according to the individualized baseline range data to obtain an initial warning threshold value.

[0182] Step S344: dynamically adjusting the initial warning threshold according to the volatility index data to obtain a dynamic warning threshold;

[0183] Step S345: using the early warning dynamic threshold to compare the deviation of the physiological index, and trigger an early warning to obtain early warning information.

[0184] In an embodiment of the present invention, individualized baseline range data is extracted from an individualized dynamic baseline model. The individualized dynamic baseline model outputs a baseline value and a fluctuation range at a specific time point. For example, the blood glucose baseline value at 10:00 is 110 mg / dL, and the fluctuation range is 90-130 mg / dL. The baseline values ​​and fluctuation ranges at multiple time points are extracted to form individualized baseline range data. For example, the blood glucose baseline value and fluctuation range for each hour in the next 24 hours are extracted to form a data set containing 24 baseline values ​​and fluctuation ranges.

[0185] Calculate the volatility index of the patient's historical physiological data. Common volatility indicators include standard deviation, coefficient of variation, glucose excursion, etc. For example, calculate the patient's average blood glucose standard deviation every day in the past three months, and take the average of these standard deviations as the patient's blood glucose volatility index. You can also choose other volatility indicators according to specific needs, such as calculating the postprandial blood glucose fluctuation range or the nighttime blood glucose fluctuation range.

[0186] The initial threshold for warning is set according to the individualized baseline range data. The initial threshold can be set as the boundary value of the baseline range plus or minus a fixed value or ratio. For example, the initial threshold for blood glucose warning is set to the upper limit of the baseline range plus 15 mg / dL, or to the lower limit of the baseline range minus 15 mg / dL. For example, if the blood glucose baseline range at 10:00 is 90-130 mg / dL, the initial threshold for blood glucose warning at 10:00 is set to 145 mg / dL and 75 mg / dL.

[0187] The initial warning threshold is dynamically adjusted according to the volatility index data. For example, if the patient's blood sugar volatility is large, the warning threshold is set more leniently to avoid frequent triggering of warnings; if the patient's blood sugar volatility is small, the warning threshold is set more strictly to detect abnormal fluctuations more promptly. For example, the warning dynamic threshold is set to the initial warning threshold plus or minus a multiple of the volatility index. For example, if the patient's blood sugar volatility index is 20mg / dL, the warning dynamic threshold is set to the initial warning threshold ±2*20mg / dL.

[0188] Compare the deviation value of the physiological indicator with the early warning dynamic threshold. If the deviation value exceeds the early warning dynamic threshold, the early warning is triggered and the early warning information is generated. The early warning information includes the early warning time, the early warning type (such as high blood sugar early warning or low blood sugar early warning), the real-time physiological indicator value, the dynamic baseline value and the early warning threshold. For example, if the real-time blood sugar value at 10:00 is 150mg / dL, the dynamic baseline value is 110mg / dL, and the early warning dynamic thresholds are 145mg / dL and 75mg / dL, then the deviation value is 40mg / dL, which exceeds the early warning dynamic threshold and triggers a high blood sugar early warning. The early warning information includes the early warning time of 10:00, the early warning type is high blood sugar early warning, the real-time blood sugar value is 150mg / dL, the dynamic baseline value is 110mg / dL, and the early warning threshold is 145mg / dL.

[0189] Preferably, step S4 comprises the following steps:

[0190] Step S41: performing feature selection and extraction on the real-time risk assessment report and the multi-dimensional health portrait of the patient to obtain feature data to be clustered;

[0191] Step S42: performing feature dimensionality reduction on the clustered feature data to obtain reduced-dimensional feature data; performing feature standardization on the reduced-dimensional feature data to obtain standardized feature data;

[0192] Step S43: performing DBSCAN cluster analysis on the standardized feature data to obtain clustering results;

[0193] Step S44: performing subtype stratification according to the clustering results to obtain subtype stratification data; performing sub-feature analysis on the subtype stratification data to obtain subtype feature data;

[0194] Step S45: grouping the patients into subtypes according to the subtype stratification data and the subtype characteristic data to obtain patient subtype grouping data; extracting subtype group characteristics from a preset subtype group characteristic database according to the patient subtype grouping data to obtain subtype group characteristic data;

[0195] Step S46: extracting real-time risk data from the real-time risk assessment report to obtain real-time risk data;

[0196] Step S47: Generate an individualized data report for the subtype group characteristic data and the real-time risk data to obtain an individualized data report; perform data visualization processing on the individualized data report to implement health management operations for endocrine patients.

[0197] In an embodiment of the present invention, features such as real-time risk level and early warning information are extracted from the real-time risk assessment report. Features such as demographic characteristics (age, gender, BMI, etc.), medical history (type of diabetes, course of disease, etc.), physiological indicators (average blood sugar, blood pressure, blood lipids, etc.), and lifestyle (eating habits, exercise habits, etc.) are extracted from the multi-dimensional health portrait of the patient. The extracted features are combined into feature data to be clustered, for example, age, gender, BMI, type of diabetes, average blood sugar, risk level, etc. are combined into a feature vector. All features need to be converted to numerical types, for example, using one-hot encoding to process categorical variables.

[0198] Use the principal component analysis (PCA) method to reduce the dimension of the clustered feature data. Set the number of principal components to be retained, for example, retain the principal components with a variance contribution rate of 95%. Project the high-dimensional feature data into the low-dimensional principal component space to obtain the reduced-dimensional feature data. Then, standardize the reduced-dimensional feature data, for example, use the Z-score standardization method to convert the mean of each feature to 0 and the standard deviation to 1 to obtain the standardized feature data.

[0199] Use the DBSCAN algorithm to cluster the standardized feature data. Set the parameters of the DBSCAN algorithm, such as the neighborhood radius (eps) and the minimum number of samples (min_samples). Use the Euclidean distance to calculate the distance between data points. According to the set parameters, divide the data points into different clusters, as well as noise points. For example, set eps to 0.5 and min_samples to 5, and use the DBSCAN algorithm to cluster the standardized feature data, and get three clusters and some noise points.

[0200] Subtype stratification is performed based on clustering results. Each cluster is considered as a subtype. Samples within each subtype are analyzed for characteristics, such as calculating statistical indicators such as the mean, standard deviation, and median of each feature. These statistical indicators are used as subtype feature data to describe the characteristics of each subtype. For example, the average age, average blood sugar, and risk level distribution of patients in subtype 1 are calculated as feature data of subtype 1.

[0201] According to the subtype stratification data and subtype characteristic data, the patients are divided into different subtype groups. The characteristic vector of each patient is compared with the characteristic data of each subtype, for example, the distance between the characteristic vector and the subtype center point is calculated, and the patient is divided into the subtype group with the closest distance to obtain the patient subtype grouping data. According to the patient subtype grouping data, the corresponding subtype group characteristic data is extracted from the preset subtype group characteristic database. The subtype group characteristic database contains information such as typical characteristics and risk factors of each subtype. For example, the characteristic vector of patient A is compared with the characteristic data of the three subtypes, and it is found that the distance between patient A and subtype 2 is the closest. Then patient A is divided into subtype 2 group, and the characteristic data of subtype 2 is extracted from the subtype group characteristic database. For example, the typical characteristics of subtype 2 are hyperglycemia, hypertension, and hyperlipidemia, and the risk factors are obesity and lack of exercise, such as controlling diet, increasing exercise, taking hypoglycemic drugs, etc.

[0202] Extract real-time risk data from the real-time risk assessment report, such as real-time risk level, warning information, real-time physiological indicator data, etc. For example, extract that the patient's current risk level is high risk, triggering a high blood sugar warning, and the real-time blood sugar value is 180 mg / dL.

[0203] Generate an individualized data report by combining subtype group characteristic data and real-time risk data. The report content includes: basic patient information, subtype grouping information, real-time risk data, typical characteristics of subtype groups, risk factors, and personalized recommendations and interventions for the patient's current risk. For example, generate an individualized data report containing the patient's name, age, subtype group (subtype 2), real-time blood sugar value, hyperglycemia warning information, high risk level, typical characteristics and risk factors of subtype 2, and personalized diet, exercise and medication recommendations for the patient's hyperglycemia. Perform data visualization processing on the individualized data report, such as using charts and graphs to display the patient's physiological indicator data, risk level, and personalized recommendations, so that patients and medical staff can more intuitively understand and use the report content.

[0204] Preferably, step S43 includes the following steps:

[0205] Step S431: performing k-nearest neighbor distance calculation on each data point in the standardized feature data to obtain a k-nearest neighbor distance list;

[0206] Step S432: Draw a k distance graph according to the k nearest neighbor distance list to obtain a k distance graph;

[0207] Step S433: Adaptively determine the neighborhood radius according to the k-distance graph to obtain a neighborhood radius list;

[0208] Step S434: Calculate the time decay factor for each data point in the standardized feature data to obtain the time decay factor;

[0209] Step S435: performing time-weighted distance calculation on the standardized feature data according to the time attenuation factor to obtain time-weighted distance data;

[0210] Step S436: Perform DBSCAN clustering analysis on the standardized feature data according to the time-weighted distance data and the neighborhood radius list to obtain clustering results.

[0211] In an embodiment of the present invention, for each data point in the standardized feature data, the Euclidean distance to all other data points is calculated. The distance of each data point is sorted in ascending order. The kth distance value after sorting is selected as the k nearest neighbor distance of the data point. The k nearest neighbor distances of all data points are stored in a list to obtain a k nearest neighbor distance list. For example, the k value is set to 4, the distance from data point A to all other data points is calculated, and the distance list [0.2, 0.3, 0.5, 0.6, 0.7, ...] is obtained after sorting, then the k nearest neighbor distance of data point A is 0.6.

[0212] Sort the k nearest neighbor distance list in ascending order. Draw a k distance graph with the sorted k nearest neighbor distance value as the ordinate and the data point index as the abscissa. The k distance graph can intuitively show how the k nearest neighbor distance changes with the data point.

[0213] According to the k-distance graph, determine the neighborhood radius (eps) of the DBSCAN algorithm. In the k-distance graph, find the inflection point of the distance curve, that is, the point where the slope of the curve changes significantly. The k-nearest neighbor distance value corresponding to the inflection point is used as the adaptive neighborhood radius. Since the k-nearest neighbor distances of different data points may be different, different neighborhood radii can be set for each data point to obtain a neighborhood radius list. For example, in the k-distance graph, it is observed that the k-nearest neighbor distance has an obvious inflection point near 0.8, so 0.8 is used as the adaptive neighborhood radius.

[0214] Calculate the time decay factor for each data point in the normalized feature data. The time decay factor is used to reduce the weight of older data points in cluster analysis. The time decay factor can be calculated using the exponential decay function: `w(t) = exp(-t / τ)`, where t is the difference between the timestamp of the data point and the current time, and τ is the time decay constant. For example, if τ is set to 7 days, for a data point 14 days ago, its time decay factor is exp(-14 / 7) = 0.135.

[0215] According to the time decay factor, the time-weighted distance calculation is performed on the standardized feature data. The Euclidean distance between data points is multiplied by the time decay factor to obtain the time-weighted distance. The time-weighted distance can reduce the impact of older data points on the clustering results. For example, the Euclidean distance between data points A and B is 0.5, and the time decay factor of data point A is 0.135, then the time-weighted distance between A and B is 0.5*0.135=0.0675.

[0216] Use DBSCAN algorithm to cluster the standardized feature data. Use time-weighted distance as the distance metric and a list of neighborhood radius as the eps parameter. Set the minimum number of samples (min_samples). Divide the data points into different clusters, as well as noise points, based on the time-weighted distance and the neighborhood radius. For example, setting min_samples to 5, using time-weighted distance and an adaptive neighborhood radius list, and using DBSCAN algorithm to cluster the standardized feature data, we get three clusters and some noise points.

[0217] Preferably, the present invention further provides an endocrine patient health management system integrated with electronic medical records, which is used to execute the endocrine patient health management method integrated with electronic medical records as described above, and the endocrine patient health management system integrated with electronic medical records comprises:

[0218] The multi-dimensional data collection module is used to collect multi-dimensional data of endocrine patients through the integrated electronic medical records in the hospital information system, and to construct a multi-dimensional portrait of the patient to obtain a multi-dimensional health portrait of the patient;

[0219] The time series data modeling module is used to extract time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; obtain the patient's historical physiological data; construct an individualized physiological rhythm model based on the patient's historical physiological data to obtain an individualized physiological rhythm model; perform non-uniform interpolation based on physiological rhythm on the time series feature data according to the individualized physiological rhythm model to obtain interpolated data; generate an individualized dynamic baseline model based on the interpolated data to obtain an individualized dynamic baseline model;

[0220] Deviation warning identification module, used to obtain real-time physiological index data; calculate physiological index deviation according to individualized dynamic baseline model and real-time physiological index data to obtain physiological index deviation value; set dynamic warning threshold according to patient's historical physiological data and individualized dynamic baseline model to obtain warning dynamic threshold; perform deviation warning identification on physiological index deviation value according to warning dynamic threshold to obtain real-time risk assessment report;

[0221] The subtype hierarchical clustering module is used to extract standardized features from real-time risk assessment reports and multi-dimensional health portraits of patients to obtain standardized feature data; perform DBSCAN clustering analysis on the standardized feature data to obtain clustering results; perform clustering subtype stratification based on the clustering results to obtain subtype feature data; generate individualized data reports based on subtype feature data and real-time risk assessment reports to obtain individualized data reports, so as to realize endocrine patient health management operations.

[0222] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0223] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A health management method for endocrine patients integrated with electronic medical records, characterized in that: The following steps are involved: Step S1: Collect multi-dimensional data of endocrine patients through the integrated electronic medical records in the hospital information system, and construct a multi-dimensional portrait of the patient to obtain a multi-dimensional health portrait of the patient; Step S2: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; Obtain patient historical physiological data; An individualized physiological rhythm model is constructed based on the patient's historical physiological data to obtain an individualized physiological rhythm model; non-uniform interpolation based on physiological rhythm is performed on the time series feature data based on the individualized physiological rhythm model to obtain interpolated data; an individualized dynamic baseline model is generated based on the interpolated data to obtain an individualized dynamic baseline model; Step S3: acquiring real-time physiological index data; calculating physiological index deviations according to the individualized dynamic baseline model and the real-time physiological index data to obtain physiological index deviation values; setting dynamic warning thresholds according to the patient's historical physiological data and the individualized dynamic baseline model to obtain warning dynamic thresholds; According to the early warning dynamic threshold, the deviation value of the physiological index is identified by early warning, and a real-time risk assessment report is obtained; Step S4: extracting standardized features from the real-time risk assessment report and the multi-dimensional health portrait of the patient to obtain standardized feature data; Perform DBSCAN cluster analysis on the standardized feature data to obtain clustering results; According to the clustering results, cluster subtypes are stratified to obtain subtype characteristic data; Generate individualized data reports based on subtype characteristic data and real-time risk assessment reports to obtain individualized data reports to achieve health management operations for endocrine patients.

2. The endocrine patient health management method integrated with electronic medical records according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: extracting the electronic medical record data of endocrine patients through the integrated electronic medical record in the hospital information system to obtain the electronic medical record data; Step S12: synchronizing the device data of the wearable medical device of the endocrine patient through the wireless communication protocol to obtain real-time physiological data; Step S13: Acquire lifestyle data; perform data cleaning and preprocessing on the electronic medical record data, real-time physiological data, and lifestyle data to obtain preprocessed patient data; Step S14: construct a multi-dimensional portrait of the patient based on the pre-processed patient data to obtain a multi-dimensional health portrait of the patient.

3. The endocrine patient health management method integrated with electronic medical records according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; performing time granularity uniform processing on the time series feature data to obtain time granularity uniform data; Step S22: Acquire historical physiological data of the patient; construct an individualized physiological rhythm model according to the historical physiological data of the patient to obtain an individualized physiological rhythm model; Step S23: performing physiological rhythm-based non-uniform interpolation on the time granularity unified data according to the individualized physiological rhythm model to obtain interpolated data; Step S24: Generate time series data according to the interpolated data and the unified time granularity data to obtain time series data; perform time series data segmentation on the time series data to obtain time series segmentation data; Step S25: training a recurrent neural network model on the time series segmentation data to obtain a recurrent neural network model; Step S26: inputting the time series data into the recurrent neural network model to predict the fluctuation range of the target physiological index, and obtaining the fluctuation range data of the physiological index; Step S27: Generate an individualized dynamic baseline model based on the physiological indicator fluctuation range data and the recurrent neural network model to obtain an individualized dynamic baseline model.

4. The endocrine patient health management method integrated with electronic medical records according to claim 3 is characterized in that: Step S22 includes the following steps: Step S221: extracting postprandial blood glucose data from the patient's historical physiological data to obtain a postprandial blood glucose data set; Step S222: performing peak time recognition on the postprandial blood glucose data set to obtain peak time data; performing peak height recognition on the postprandial blood glucose data set to obtain peak height data; Step S223: performing peak characteristic analysis according to the peak time data and the peak height data to obtain peak characteristic data; Step S224: Calculating the blood sugar drop rate for the post-meal blood sugar data set to obtain drop rate data; Step S225: Gaussian process regression is used to construct an individualized physiological rhythm model for the peak characteristic data and the fall-back speed data to obtain an individualized physiological rhythm model.

5. The endocrine patient health management method integrated with electronic medical records according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: marking missing values ​​on the unified time granularity data to obtain missing value marked data; locating blood glucose missing values ​​on the missing value marked data to obtain blood glucose missing value location data; Step S232: determining the most recent meal time for the blood sugar missing value location data to obtain the most recent meal time data; Step S233: Calculate the missing time interval according to the blood glucose missing value position data and the most recent meal time data to obtain time interval data; input the most recent meal time data and the time interval data into the individualized physiological rhythm model to predict the blood glucose value to obtain a blood glucose prediction value; use the blood glucose prediction value as a preliminary interpolation of the blood glucose missing value, and generate preliminary interpolation blood glucose data to obtain preliminary interpolation blood glucose data; Step S234: extracting exercise and medication information from the patient's multi-dimensional health portrait to obtain exercise and medication information data; Step S235: correcting the interpolation result of the preliminary interpolated blood sugar data according to the sports medication information data to obtain corrected blood sugar data; Step S236: performing physiological index interpolation processing of the time granularity unified data according to the individualized physiological rhythm model, the missing value marked data and the corrected blood glucose data to obtain the interpolated data.

6. The endocrine patient health management method integrated with electronic medical records according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: acquiring real-time physiological index data of the patient through the wearable medical device, and acquiring context information related to the index, to obtain real-time physiological index data and index context information; Step S32: using the individualized dynamic baseline model, performing dynamic baseline model prediction according to the indicator context information to obtain dynamic baseline model prediction data; Step S33: performing deviation calculation on the real-time physiological index data and the dynamic baseline model prediction data to obtain a physiological index deviation value; Step S34: setting a dynamic warning threshold according to the patient's historical physiological data and the individualized dynamic baseline model to obtain a warning dynamic threshold; triggering a warning according to the warning dynamic threshold to obtain warning information; Step S35: Perform real-time risk assessment according to the early warning information to obtain real-time risk assessment results; Step S36: Generate a real-time risk assessment report based on the real-time risk assessment results, warning information, and indicator context information to obtain a real-time risk assessment report.

7. The endocrine patient health management method integrated with electronic medical records according to claim 6, characterized in that: Step S34 includes the following steps: Step S341: extracting an individualized baseline range according to the individualized dynamic baseline model to obtain individualized baseline range data; Step S342: Calculating the volatility index of the patient's historical physiological data to obtain volatility index data; Step S343: setting an initial threshold value according to the individualized baseline range data to obtain an initial warning threshold value. Step S344: dynamically adjusting the initial warning threshold according to the volatility index data to obtain a dynamic warning threshold; Step S345: using the early warning dynamic threshold to compare the deviation of the physiological index, and trigger an early warning to obtain early warning information.

8. The endocrine patient health management method integrated with electronic medical records according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing feature selection and extraction on the real-time risk assessment report and the multi-dimensional health portrait of the patient to obtain feature data to be clustered; Step S42: performing feature dimensionality reduction on the clustered feature data to obtain reduced-dimensional feature data; performing feature standardization on the reduced-dimensional feature data to obtain standardized feature data; Step S43: performing DBSCAN cluster analysis on the standardized feature data to obtain clustering results; Step S44: performing subtype stratification according to the clustering results to obtain subtype stratification data; performing sub-feature analysis on the subtype stratification data to obtain subtype feature data; Step S45: performing patient subtype grouping according to the subtype stratification data and the subtype characteristic data to obtain patient subtype grouping data; performing subtype group feature extraction on a preset subtype group characteristic database according to the patient subtype grouping data to obtain subtype group characteristic data; Step S46: extracting real-time risk data from the real-time risk assessment report to obtain real-time risk data; Step S47: Generate an individualized data report for the subtype group characteristic data and the real-time risk data to obtain an individualized data report; perform data visualization processing on the individualized data report to implement health management operations for endocrine patients.

9. The endocrine patient health management method integrated with electronic medical records according to claim 8, characterized in that: Step S43 includes the following steps: Step S431: performing k-nearest neighbor distance calculation on each data point in the standardized feature data to obtain a k-nearest neighbor distance list; Step S432: Draw a k distance graph according to the k nearest neighbor distance list to obtain a k distance graph; Step S433: Adaptively determine the neighborhood radius according to the k-distance graph to obtain a neighborhood radius list; Step S434: Calculate the time decay factor for each data point in the standardized feature data to obtain the time decay factor; Step S435: performing time-weighted distance calculation on the standardized feature data according to the time attenuation factor to obtain time-weighted distance data; Step S436: Perform DBSCAN clustering analysis on the standardized feature data according to the time-weighted distance data and the neighborhood radius list to obtain clustering results.

10. An endocrine patient health management system integrated with electronic medical records, characterized in that: For executing the endocrine patient health management method integrated with electronic medical records as claimed in claim 1, the endocrine patient health management system integrated with electronic medical records comprises: The multi-dimensional data collection module is used to collect multi-dimensional data of endocrine patients through the integrated electronic medical records in the hospital information system, and to construct a multi-dimensional portrait of the patient to obtain a multi-dimensional health portrait of the patient; The time series data modeling module is used to extract time series data features from the multi-dimensional health portrait of the patient to obtain time series feature data; obtain the patient's historical physiological data; construct an individualized physiological rhythm model based on the patient's historical physiological data to obtain an individualized physiological rhythm model; perform non-uniform interpolation based on physiological rhythm on the time series feature data according to the individualized physiological rhythm model to obtain interpolated data; generate an individualized dynamic baseline model based on the interpolated data to obtain an individualized dynamic baseline model; Deviation warning identification module, used to obtain real-time physiological index data; calculate physiological index deviation according to individualized dynamic baseline model and real-time physiological index data to obtain physiological index deviation value; set dynamic warning threshold according to patient's historical physiological data and individualized dynamic baseline model to obtain warning dynamic threshold; perform deviation warning identification on physiological index deviation value according to warning dynamic threshold to obtain real-time risk assessment report; The subtype hierarchical clustering module is used to extract standardized features from real-time risk assessment reports and multi-dimensional health portraits of patients to obtain standardized feature data; perform DBSCAN clustering analysis on the standardized feature data to obtain clustering results; perform clustering subtype stratification based on the clustering results to obtain subtype feature data; generate individualized data reports based on subtype feature data and real-time risk assessment reports to obtain individualized data reports, so as to realize endocrine patient health management operations.

Images