Intelligent follow-up management system and method for elderly chronic diseases
By integrating data monitoring and processing modules in the intelligent follow-up management system for chronic diseases in the elderly, using household monitoring instruments to collect data in real time, calculate the control effect coefficient and cardiac injury index, and automatically issue intelligent access instructions, solving the problem of untimely monitoring of patients' health status. Real-time health management and personalized intervention for elderly patients with heart disease have been achieved, and health management efficiency and safety guarantees have been improved.
Patent Information
- Application Number
- CN202411253823.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-09
AI Technical Summary
In the existing intelligent follow-up management system for chronic diseases in the elderly, the problem of untimely monitoring and intervention of patients' health status has led to data lag and delayed diagnosis.
A system including data monitoring, data processing, daily control detection and follow-up management modules was designed, and the physical changes, cardiac electrical activity and blood lipid metabolism data of elderly patients with heart disease were collected in real time by controlling the effect coefficient. , calculation of electrical activity coefficient and cardiac injury index, automatically issue intelligent access instructions and conduct offline follow-up arrangements.
Real-time monitoring and personalized management of the health status of elderly patients with heart disease has been achieved, health management efficiency has been improved, potential health problems have been discovered and dealt with in a timely manner, the risk of disease deterioration has been reduced, and the use of medical resources has been optimized.
Smart Images

Figure CN118761300B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of chronic disease management, and in particular to an intelligent follow-up management system and method for elderly chronic diseases. Background Art
[0002] In the field of smart medical care and health management, this field is committed to using modern scientific and technological means to optimize medical services and improve the efficiency of patient health management. With the acceleration of the global aging process, the management of chronic diseases in the elderly has become an important challenge facing the medical and health system. Especially in the management of chronic diseases in the elderly, heart disease is a common and serious chronic disease, and its intelligent follow-up and management are particularly important. The health status of heart disease patients requires continuous monitoring and timely intervention to reduce complications and improve the quality of life.
[0003] Although this intelligent follow-up management system has unprecedented technical advantages, there are still some shortcomings in its current practical application. The existing traditional follow-up model usually relies on manual records and regular inspections, which may lead to data lags and untimely intervention, thus affecting the timely diagnosis and treatment of patients. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent follow-up management system and method for elderly chronic diseases, which solves the problem of untimely monitoring and intervention of patient health status in the above-mentioned background technology.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0006] In a first aspect, the present invention provides an intelligent follow-up management system for chronic diseases in the elderly, including: a data monitoring module, a data processing module, a daily control detection module, a regular medical care analysis module and a follow-up management module;
[0007] The data monitoring module is used to regularly monitor relevant physiological change data information, relevant cardiac electrical activity state data information and blood lipid metabolism data information of elderly heart disease patients using home monitoring instruments;
[0008] The data processing module is used to pre-process the data collected by the data monitoring module and transmit the pre-processed data;
[0009] The daily control detection module is used to construct a control effect coefficient Kxxs based on relevant physiological change data information. If the control effect coefficient Kxxs exceeds a threshold, an online intelligent access instruction will be issued externally;
[0010] The regular medical care analysis module is used to calculate the electrical activity coefficient Dhxs and the blood lipid state coefficient Xzxs respectively after receiving the online intelligent access instruction based on the relevant cardiac electrical activity state data information and blood lipid metabolism data information, and to obtain the cardiac injury index Xszs by fitting in combination with the trained chronic disease prediction model;
[0011] The follow-up management module is used to pre-set the evaluation threshold Y, and compare and analyze the heart injury index Xszs with the evaluation threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff.
[0012] Preferably, the home monitoring instruments include a blood lipid tester, a health bracelet, a weighing machine and a portable electrocardiogram device;
[0013] The data monitoring module includes a first monitoring unit, a second monitoring unit and a third monitoring unit;
[0014] The first monitoring unit is used to monitor and record relevant physiological change data information of elderly heart disease patients using a health bracelet and a weighing device, wherein the relevant physiological change data information includes the blood pressure value Xyz, weight value Tzz and blood sugar value Xtz of the elderly heart disease patients in each monitoring period, and combines with statistical algorithms to obtain the standard deviation of blood pressure in the monitoring period. , standard deviation of body weight during the monitoring period , Blood glucose standard deviation during the monitoring period , the average blood pressure value Mxy during the monitoring period, the average blood sugar value Mxt during the monitoring period, and the average body weight value Mtz during the monitoring period;
[0015] The second monitoring unit is used to regularly monitor and record the relevant cardiac electrical activity state data information of the elderly heart disease patients using a portable electrocardiogram device, wherein the relevant cardiac electrical activity state data information includes the QT interval in the electrocardiogram PR interval and ST segment deviation value Pc;
[0016] The third monitoring unit is used to regularly monitor and record blood lipid metabolism data information of elderly heart disease patients using a blood lipid tester, wherein the blood lipid metabolism data information includes triglyceride concentration in the blood of elderly heart disease patients during each monitoring period. and cholesterol concentration , and combined with statistical algorithms, the mean value of triglyceride concentration during the monitoring period was obtained. and the mean cholesterol concentration during the monitoring period .
[0017] Preferably, the data processing module includes a preprocessing unit and a transmission unit;
[0018] The preprocessing unit is used to preprocess the relevant physiological change data information, the relevant cardiac electrical activity state data information and the blood lipid metabolism data information in advance, and the preprocessing includes removing noise, filling missing values and data smoothing operations, and using dimensionless processing technology to scale the preprocessed information so that the information range in the patient's condition data set falls within Inside;
[0019] The transmission unit is used to transmit the pre-processed relevant physiological change data information, relevant cardiac electrical activity status data information and blood lipid metabolism data information to the cloud computing platform through the Internet of Things to construct a patient condition data set. Medical staff log in to the cloud computing platform through the electronic health record system in the hospital to access the patient condition data set of elderly patients in real time.
[0020] Preferably, the daily control detection module includes a daily management and control analysis unit and an early warning unit;
[0021] The daily control and analysis unit is used to obtain the blood pressure standardized deviation Xypc, the blood sugar standardized deviation Xtpc and the weight standardized deviation Tzpc according to the relevant physiological change data information, and calculate the control effect coefficient Kxxs according to the blood pressure standardized deviation Xypc, the blood sugar standardized deviation Xtpc and the weight standardized deviation Tzpc, which is specifically obtained according to the following formula:
[0022] ;
[0023] ;
[0024] In the formula, It is represented as the blood pressure value in the i-th monitoring period, It is expressed as the blood sugar value in the i-th period, It is represented as the weight value in the i-th monitoring period, It is expressed as the standard deviation of blood pressure during the monitoring period. It is expressed as the standard deviation of blood glucose during the monitoring period. It is expressed as the standard deviation of body weight during the monitoring period, Mxy is expressed as the average blood pressure value during the monitoring period, Mxt is expressed as the average blood sugar value during the monitoring period, and Mtz is expressed as the average body weight value during the monitoring period.
[0025] Preferably, the early warning unit is used to compare the control effect coefficient Kxxs with a preset threshold value to preliminarily determine whether there is an abnormality in the daily control of the current elderly heart disease patient. The specific comparison content is as follows:
[0026] If the control effect coefficient Kxxs exceeds the threshold, it is preliminarily judged that the daily control of the elderly heart disease patient is in an abnormal state, and an online intelligent access instruction will be issued;
[0027] If the control effect coefficient Kxxs does not exceed the threshold, it is preliminarily judged that the daily control of the current elderly heart disease patient is not in an abnormal state, and at this time, no online intelligent access instructions will be issued to the outside.
[0028] Preferably, the regular medical care analysis module includes a first analysis unit, a second analysis unit and a comprehensive unit;
[0029] The first analysis unit is used to analyze the QT interval according to the relevant cardiac electrical activity state data information. and PR interval After being associated and dimensionless processed, the electric activity coefficient Dhxs is obtained, and the electric activity coefficient Dhxs is obtained by the following formula:
[0030] ;
[0031] In the formula, and All are weight values, Pc represents the ST segment deviation value, is the first correction constant.
[0032] Preferably, the second analysis unit is used to construct the blood lipid status coefficient Xzxs according to the lipid metabolism data information in the blood, which is specifically obtained in the following manner:
[0033] ;
[0034] Where i=1, 2, 3, ..., n, n represents the monitoring period, Expressed as the cholesterol concentration during the i-th monitoring period, Expressed as the mean cholesterol concentration during the monitoring period, It is expressed as the triglyceride concentration in the i-th monitoring period, It is expressed as the mean value of triglyceride concentration during the monitoring period. and All are weight values.
[0035] Preferably, the comprehensive unit is used to construct a chronic disease prediction model based on the convolutional neural network technology, and input the electrical activity coefficient Dhxs, the blood lipid status coefficient Xzxs and the control effect coefficient Kxxs into the chronic disease prediction model, and after dimensionless processing, the heart damage index Xszs is obtained by fitting. The heart damage index Xszs is obtained by the following formula:
[0036] ;
[0037] In the formula, Expressed as ejection fraction, , , and are weight values, Expressed as the second correction constant.
[0038] Preferably, the follow-up management module includes a comparison unit and an execution unit;
[0039] The comparison unit is used to compare and analyze the heart injury index Xszs with the evaluation threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff. The specific analysis content is as follows:
[0040] If the heart injury index Xszs exceeds the assessment threshold Y, it means that the elderly patient's condition is currently abnormal. At this time, the medical staff will be notified to arrange an offline follow-up task within the specified time;
[0041] If the heart injury index Xszs does not exceed the assessment threshold Y, it means that the elderly patient's condition is not abnormal. At this time, the medical staff will not be notified to arrange offline follow-up tasks within the specified time.
[0042] The execution unit is used to decide whether it is necessary to arrange medical staff to perform corresponding offline follow-up tasks based on the analysis content in the comparison unit. At the same time, the hospital sorts the pending follow-up tasks, tracks the progress of the follow-up tasks in real time, and records the completion status of the tasks, where the completion status includes completed, in progress, and not started, and collects feedback on completed follow-up tasks from medical staff.
[0043] In a second aspect, the present invention also provides an intelligent follow-up management method for chronic diseases in the elderly, comprising:
[0044] Use home monitoring equipment to regularly monitor relevant physiological change data information, relevant cardiac electrical activity status data information and blood lipid metabolism data information of elderly heart disease patients;
[0045] Preprocess the data collected in the data monitoring module and transmit the preprocessed data;
[0046] The control effect coefficient Kxxs is constructed based on the relevant physiological change data information. If the control effect coefficient Kxxs exceeds the threshold, an online intelligent access instruction will be issued;
[0047] After receiving the online intelligent access command, the electrical activity coefficient Dhxs and the blood lipid status coefficient Xzxs are calculated based on the relevant cardiac electrical activity status data information and blood lipid metabolism data information, and the heart damage index Xszs is obtained by fitting in combination with the trained chronic disease prediction model;
[0048] The assessment threshold Y is set in advance, and the heart injury index Xszs is compared with the assessment threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff.
[0049] The present invention provides an intelligent follow-up management system and method for elderly chronic diseases, which has the following beneficial effects:
[0050] The data monitoring module, combined with home monitoring instruments, can regularly monitor the relevant physiological changes, cardiac electrical activity status and lipid metabolism information in the blood of elderly heart disease patients. By collecting data in real time, the system can obtain the patient's health status in a timely manner, providing an accurate data basis for subsequent analysis and intervention. The daily control detection module constructs the control effect coefficient Kxxs based on the physiological change data and sets a threshold for monitoring. When the control effect coefficient Kxxs exceeds the set threshold, the system can automatically issue an online intelligent access instruction to ensure that potential health problems are discovered and dealt with in a timely manner, further avoiding the deterioration of the disease. After receiving the intelligent access instruction, the regular medical analysis module uses the cardiac electrical activity status and blood lipid metabolism information to calculate the electrical activity coefficient Dhxs and blood lipid status coefficient Xzxs, and combines the trained chronic disease prediction model to fit the heart injury index Xszs. This process ensures an in-depth analysis and accurate assessment of the patient's health status, providing a scientific basis for medical staff and optimizing intervention measures. The follow-up management module compares and analyzes the heart injury index Xszs with the preset assessment threshold Y to comprehensively judge whether the patient's condition requires offline follow-up. This personalized management method can adjust the follow-up strategy according to the patient's specific health status, improve the efficiency and pertinence of follow-up work, and ensure that patients receive timely attention and intervention. In summary, the system integrates multiple functional modules to achieve real-time monitoring, accurate analysis, and personalized management of the health status of elderly heart disease patients, which not only improves the efficiency of health management, but also enhances the health and safety of patients.
[0051] The daily control and analysis unit uses blood pressure standard deviation, blood sugar standard deviation and weight standard deviation to measure the fluctuation of the patient's physiological data. Through the calculation of standardized deviation, the influence of measurement error or individual difference in the data can be effectively eliminated, so as to more accurately reflect the patient's health status. According to the above standardized deviation, the system calculates the control effect coefficient Kxxs, which provides a quantitative basis for further judging the health status and helps medical staff to quickly identify potential health problems. Through the intelligent early warning system, medical staff can take quick action when abnormalities are found, which not only improves the efficiency of monitoring the patient's health status, but also helps early intervention and reduces the risk of worsening of the disease. In short, the daily control detection module of the system further improves the monitoring ability of the health status of elderly heart disease patients through precise data analysis, intelligent early warning mechanism and real-time health management. The system can not only detect and deal with potential health problems in a timely manner, but also optimize the use of medical resources, thereby improving the health protection level of elderly patients.
[0052] The comprehensive unit integrates the electrical activity coefficient Dhxs and the blood lipid status coefficient Xzxs, and combines it with the trained chronic disease prediction model to calculate the heart damage index Xszs. This comprehensive index can combine the multi-dimensional information of cardiac electrical activity and blood lipid metabolism to provide a more comprehensive heart health assessment. This multi-level and multi-dimensional analysis method not only improves the accuracy of prediction, but also provides medical staff with a more comprehensive overview of the patient's health status, which helps to formulate more effective treatment and intervention measures. This forward-looking health management method helps to detect and deal with potential health problems early, reduce the risk of heart disease, and improve the quality of life and health protection level of elderly patients. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0054] Figure 1 A block diagram of an intelligent follow-up management system for chronic diseases in the elderly according to an embodiment of the present invention;
[0055] Figure 2 The present invention is a flowchart of an intelligent follow-up management method for chronic diseases in the elderly according to an embodiment of the present invention. DETAILED DESCRIPTION
[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0057] Example 1: Please refer to Figure 1 , the embodiment of the present invention provides an intelligent follow-up management system for elderly chronic diseases, including: a data monitoring module, a data processing module, a daily control detection module, a regular medical care analysis module and a follow-up management module;
[0058] The data monitoring module is used to regularly monitor relevant physiological change data information, relevant cardiac electrical activity state data information and blood lipid metabolism data information of elderly heart disease patients using home monitoring instruments;
[0059] The data processing module is used to pre-process the data collected by the data monitoring module and transmit the pre-processed data;
[0060] The daily control detection module is used to construct a control effect coefficient Kxxs based on relevant physiological change data information. If the control effect coefficient Kxxs exceeds a threshold, an online intelligent access instruction will be issued externally;
[0061] The regular medical care analysis module is used to calculate the electrical activity coefficient Dhxs and the blood lipid state coefficient Xzxs respectively after receiving the online intelligent access instruction based on the relevant cardiac electrical activity state data information and blood lipid metabolism data information, and to obtain the cardiac injury index Xszs by fitting in combination with the trained chronic disease prediction model;
[0062] The follow-up management module is used to pre-set the evaluation threshold Y, and compare and analyze the heart injury index Xszs with the evaluation threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff.
[0063] During the operation of this system, through the data monitoring module, the system combined with home monitoring instruments can regularly monitor the relevant physiological changes, cardiac electrical activity status and lipid metabolism information in the blood of elderly heart disease patients. This real-time monitoring not only provides comprehensive health data, but also realizes dynamic tracking and comprehensive understanding of the patient's health status, enhancing the real-time and accuracy of disease management. The data processing module pre-processes the data collected from the monitoring equipment and transmits the data. This efficient data processing process ensures the accuracy and timeliness of the data, while avoiding the loss or delay problems that may occur during the data transmission process, providing a reliable data basis for subsequent analysis and decision-making. The daily control detection module evaluates the impact of physiological changes by constructing the control effect coefficient Kxxs, and issues an online intelligent access instruction when the coefficient exceeds the set threshold. This intelligent control and early warning mechanism helps to detect abnormalities in the patient's health in a timely manner and automatically triggers further intervention measures, improving the response speed and the pertinence of intervention. The regular medical care analysis module calculates the electrical activity coefficient Dhxs and the blood lipid status coefficient Xzxs based on the cardiac electrical activity state and blood lipid metabolism data, and fits the heart damage index Xszs in combination with the trained chronic disease prediction model. This precise analysis and prediction capability enables medical staff to better assess the patient's heart damage status and provide a scientific basis for personalized treatment and intervention. The follow-up management module compares and analyzes the heart damage index Xszs with the preset assessment threshold Y to comprehensively judge whether the patient's health status requires offline follow-up. This intelligent follow-up decision support system can optimize the allocation of medical resources, ensure timely offline follow-up for patients who need special attention, and improve the efficiency and effectiveness of follow-up work. In summary, the system further improves the health management level of elderly patients with chronic diseases by realizing real-time monitoring, data processing, intelligent control, precise analysis and decision support, and provides strong technical support for early detection and intervention of diseases, thereby improving the quality of life and health prognosis of patients.
[0064] Example 2: Please refer to Figure 1 ,Specifically: Home monitoring instruments include blood lipid testers, health bracelets, weighing scales, and portable electrocardiogram devices;
[0065] The data monitoring module includes a first monitoring unit, a second monitoring unit and a third monitoring unit;
[0066] The first monitoring unit is used to monitor and record relevant physiological change data information of elderly heart disease patients using a health bracelet and a weighing device, wherein the relevant physiological change data information includes the blood pressure value Xyz, weight value Tzz and blood sugar value Xtz of the elderly heart disease patients in each monitoring period, and combines with statistical algorithms to obtain the standard deviation of blood pressure in the monitoring period. , standard deviation of body weight during the monitoring period , Blood glucose standard deviation during the monitoring period , the average blood pressure value Mxy during the monitoring period, the average blood sugar value Mxt during the monitoring period, and the average body weight value Mtz during the monitoring period;
[0067] The second monitoring unit is used to regularly monitor and record the relevant cardiac electrical activity state data information of the elderly heart disease patients using a portable electrocardiogram device, wherein the relevant cardiac electrical activity state data information includes the QT interval in the electrocardiogram PR interval and ST segment deviation value Pc;
[0068] The third monitoring unit is used to regularly monitor and record blood lipid metabolism data information of elderly heart disease patients using a blood lipid tester, wherein the blood lipid metabolism data information includes triglyceride concentration in the blood of elderly heart disease patients during each monitoring period. and cholesterol concentration , and combined with statistical algorithms, the mean value of triglyceride concentration during the monitoring period was obtained. and the mean cholesterol concentration during the monitoring period .
[0069] The data processing module includes a preprocessing unit and a transmission unit;
[0070] The preprocessing unit is used to preprocess the relevant physiological change data information, the relevant cardiac electrical activity state data information and the lipid metabolism data information in the blood. The preprocessing includes noise removal, missing value filling and data smoothing operations. The missing value filling methods include mean filling, median filling, interpolation filling and regression filling. The preprocessed information is scaled by using dimensionless processing technology so that the information range in the patient's condition data set falls within Inside;
[0071] The transmission unit is used to transmit the pre-processed relevant physiological change data information, relevant cardiac electrical activity state data information and blood lipid metabolism data information to the cloud computing platform through the Internet of Things to construct a patient condition data set. Medical staff log in to the cloud computing platform through the electronic health record (EHR) system in the hospital to access the patient condition data set of elderly patients in real time.
[0072] In this embodiment, through the first monitoring unit, the system uses a health bracelet and a weighing device to regularly monitor and record the patient's blood pressure, weight and blood sugar values. These data can provide the basic health status of elderly heart disease patients, and combine statistical algorithms to obtain the standard deviation of blood pressure, weight and blood sugar, providing a reliable data basis for further health analysis. The second monitoring unit uses a portable electrocardiogram device to regularly monitor the patient's QT interval, PR interval and ST segment deviation. These electrocardiogram parameters are of great significance for evaluating the state of cardiac electrical activity and can detect potential heart problems in a timely manner. The third monitoring unit monitors the triglyceride concentration and cholesterol concentration in the patient's blood through a blood lipid tester and calculates their mean. These indicators are crucial for evaluating lipid metabolism and cardiovascular health. The preprocessing unit in the data processing module is responsible for denoising, filling missing values and smoothing the data collected. The integrity and accuracy of the data are ensured by filling the mean, median, interpolation and regression methods. The dimensionless processing technology unifies the data range to make it suitable for further analysis. The transmission unit transmits the pre-processed data to the cloud computing platform through the Internet of Things technology to establish a patient condition data set. Through this data set, medical staff can access the patient's health information in real time and conduct in-depth analysis and evaluation. Medical staff can log in to the cloud computing platform through the hospital's electronic health record system to view and analyze the patient's condition data in real time. This integration method not only improves the timeliness of data acquisition, but also enhances the medical staff's comprehensive grasp of the patient's health status and timely intervention capabilities. Through integrated monitoring and data processing functions, the system can provide detailed and accurate patient health data, providing a scientific basis for chronic disease management. The system supports personalized analysis of patient health status, and can carry out targeted management and intervention based on the patient's specific data, thereby improving the effect of disease prevention and treatment. In summary, the system further improves the health management level of elderly heart disease patients through multi-faceted data monitoring, optimized data processing, and efficient data transmission and access functions, provides strong data support for medical staff, and thus improves the health protection of patients.
[0073] Example 3: Please refer to Figure 1 ,Specifically: the daily control detection module includes a daily control analysis unit and an early warning unit;
[0074] The daily control and analysis unit is used to obtain the blood pressure standardized deviation Xypc, the blood sugar standardized deviation Xtpc and the weight standardized deviation Tzpc according to the relevant physiological change data information, and calculate the control effect coefficient Kxxs according to the blood pressure standardized deviation Xypc, the blood sugar standardized deviation Xtpc and the weight standardized deviation Tzpc, which is specifically obtained according to the following formula:
[0075] ;
[0076] ;
[0077] In the formula, It is represented as the blood pressure value in the i-th monitoring period, It is expressed as the blood sugar value in the i-th period, It is represented as the weight value in the i-th monitoring period, It is expressed as the standard deviation of blood pressure during the monitoring period. It is expressed as the standard deviation of blood glucose during the monitoring period. It is expressed as the standard deviation of body weight during the monitoring period, Mxy is expressed as the average blood pressure value during the monitoring period, Mxt is expressed as the average blood sugar value during the monitoring period, and Mtz is expressed as the average body weight value during the monitoring period.
[0078] The early warning unit is used to compare the control effect coefficient Kxxs with a preset threshold value to preliminarily determine whether there is an abnormality in the daily control of the current elderly heart disease patient. The specific comparison content is as follows:
[0079] If the control effect coefficient Kxxs exceeds the threshold, it is preliminarily judged that the daily control of the elderly heart disease patient is in an abnormal state, and an online intelligent access instruction will be issued;
[0080] If the control effect coefficient Kxxs does not exceed the threshold, it is preliminarily judged that the daily control of the current elderly heart disease patient is not in an abnormal state, and at this time, no online intelligent access instructions will be issued to the outside.
[0081] In this embodiment, the daily management and analysis unit provides a standardized perspective for health data by calculating the standardized deviation of blood pressure Xypc, the standardized deviation of blood sugar Xtpc, and the standardized deviation of weight Tzpc. These standardized deviation values are used to measure the degree of deviation of health data in each monitoring period from the average level in the monitoring period, helping to accurately understand the stability of the patient's health status. Based on the standardized deviation, the system can calculate the control effect coefficient Kxxs, which combines the standardized deviations of blood pressure, blood sugar and weight, thereby providing a comprehensive indicator for evaluating the daily health control effect of the patient. The early warning unit compares the calculated control effect coefficient Kxxs with the preset threshold to achieve a preliminary judgment on the patient's health control status. If the control effect coefficient Kxxs exceeds the threshold, the system will automatically issue an online intelligent access instruction to prompt medical staff to further check the patient's health status. This mechanism can detect potential health abnormalities in time and prevent the condition from worsening. When the control effect coefficient Kxxs does not exceed the set threshold, the system will not issue an online access instruction, thereby further avoiding excessive intervention in the patient's health status under normal circumstances. This flexible management method effectively saves medical resources and improves the work efficiency of the system. The data-driven decision support provided by the system helps medical staff to accurately evaluate the health status of patients based on actual data, and then formulate more scientific management and intervention strategies. Through precise monitoring and timely warning, the system can optimize the health management and intervention of elderly heart disease patients, enhance the health protection of patients, and reduce the possibility of acute events. In summary, the system realizes accurate monitoring and timely warning of the health status of elderly heart disease patients through the standardized deviation calculation and threshold comparison warning mechanism of the daily control detection module, which not only improves the efficiency and effectiveness of health management, but also enhances the safety of patients.
[0082] Example 4: Please refer to Figure 1 ,Specifically: the regular medical care analysis module includes a first analysis unit, a second analysis unit and a comprehensive unit;
[0083] The first analysis unit is used to analyze the QT interval according to the relevant cardiac electrical activity state data information. and PR interval After being associated and dimensionless processed, the electric activity coefficient Dhxs is obtained, and the electric activity coefficient Dhxs is obtained by the following formula:
[0084] ;
[0085] In the formula, and are all weight values, Pc represents the ST segment deviation value, where 0 < ≤1,0< ≤1, and + =1, is the first correction constant.
[0086] The ST segment deviation value Pc mentioned above refers to the deviation value of the ST segment in the electrocardiogram relative to the baseline level, wherein the ST segment is from the end of the QRS complex to the beginning of the T wave; and the baseline level refers to the potential level in the electrocardiogram after ventricular depolarization (QRS complex) and before the beginning of the ST segment. In a healthy heart, there is usually no significant potential change during this period, forming a straight line, and this straight line is regarded as the baseline level.
[0087] QT interval The time from the beginning of the QRS complex to the end of the T wave, which represents the entire process from ventricular depolarization to repolarization.
[0088] PR interval It refers to the time from the onset of the P wave to the onset of the QRS complex wave, which represents the conduction time from atrial depolarization to ventricular depolarization.
[0089] The second analysis unit is used to construct the blood lipid state coefficient Xzxs according to the lipid metabolism data information in the blood, which is specifically obtained in the following manner:
[0090] ;
[0091] Where i=1, 2, 3, ..., n, n represents the monitoring period, Expressed as the cholesterol concentration during the i-th monitoring period, Expressed as the mean cholesterol concentration during the monitoring period, It is expressed as the triglyceride concentration in the i-th monitoring period, It is expressed as the mean value of triglyceride concentration during the monitoring period. and are weight values, where 0 < ≤1,0< ≤1, and + = 1. High cholesterol levels can lead to atherosclerosis and increase the risk of heart disease;
[0092] In this embodiment, the first analysis unit uses the QT interval and PR interval , and the electrical activity coefficient Dhxs is calculated in combination with the ST segment deviation value Pc. Through dimensionless processing and weight adjustment, this coefficient comprehensively reflects the state of cardiac electrical activity. This comprehensive evaluation can provide a deep understanding of cardiac electrical activity, help medical staff identify potential electrophysiological abnormalities, and more accurately assess the patient's cardiac health status. The second analysis unit constructs the blood lipid status coefficient Xzxs by combining cholesterol concentration and triglyceride concentration. The weight value in the formula and the mean calculation method within the monitoring period can effectively balance individual differences and data fluctuations, making the assessment of blood lipid status more accurate. This analysis can help medical staff fully understand the patient's lipid metabolism status, identify dyslipidemia, and formulate personalized intervention measures. Through further precise electrical activity coefficient Dhxs and blood lipid status coefficient Xzxs, potential problems can be discovered earlier, thereby improving early warning capabilities and timely intervention to prevent the disease from worsening. In short, the regular medical care analysis module of the system provides a deep understanding and accurate prediction of the health status of elderly heart disease patients through precise calculation and comprehensive evaluation. This module not only optimizes the data processing and analysis process, but also significantly improves the ability of early warning and personalized medical services.
[0093] Example 5: Please refer to Figure 1 Specifically: the comprehensive unit is used to construct a chronic disease prediction model according to the convolutional neural network technology, and input the electrical activity coefficient Dhxs, the blood lipid status coefficient Xzxs and the control effect coefficient Kxxs into the chronic disease prediction model, and after dimensionless processing, the heart damage index Xszs is obtained by fitting. The heart damage index Xszs is obtained by the following formula:
[0094] ;
[0095] In the formula, Expressed as ejection fraction, , , and are weight values, where 0 < ≤1,0< ≤1,0< ≤1,0< ≤1, and + + + =1, Expressed as the second correction constant.
[0096] The ejection fraction mentioned above It refers to the ratio of the blood pumped out by the ventricle during each heart contraction to the end-diastolic internal diameter, which is used to evaluate the ventricular contractile function.
[0097] A convolutional neural network is used to build an initial model, and the initial model is trained and tested with relevant data information in the patient's condition dataset. The trained initial model is used as a state recognition model, and feature information in the state recognition model is obtained. The state recognition model is trained and tested with the acquired feature information. Combined with the online intelligent access instructions issued by the cloud platform, the trained state recognition model is used as a chronic disease prediction model.
[0098] The follow-up management module includes a comparison unit and an execution unit;
[0099] The comparison unit is used to compare and analyze the heart injury index Xszs with the evaluation threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff. The specific analysis content is as follows:
[0100] If the heart injury index Xszs exceeds the assessment threshold Y, it means that the elderly patient's condition is currently abnormal. At this time, the medical staff will be notified to arrange an offline follow-up task within the specified time;
[0101] If the heart injury index Xszs does not exceed the assessment threshold Y, it means that the elderly patient's condition is not abnormal. At this time, the medical staff will not be notified to arrange offline follow-up tasks within the specified time.
[0102] The execution unit is used to decide whether it is necessary to arrange medical staff to perform corresponding offline follow-up tasks based on the analysis content in the comparison unit. At the same time, the hospital sorts the pending follow-up tasks so that medical staff can complete the tasks according to their priority, and tracks the progress of the follow-up tasks in real time, records the completion status of the tasks, including completed, in progress, and not started, and collects feedback on completed follow-up tasks from medical staff.
[0103] In this embodiment, the comprehensive unit constructs a chronic disease prediction model through convolutional neural network (CNN) technology, and comprehensively analyzes the electrical activity coefficient Dhxs, blood lipid status coefficient Xzxs and control effect coefficient Kxxs. This method enables the model to extract deep features from multi-dimensional data and realize accurate prediction of the heart injury index Xszs. The efficient feature extraction capability of the convolutional neural network improves the accuracy and stability of the prediction and provides a more reliable health warning for medical staff. The comparison unit in the follow-up management module can compare the heart injury index Xszs with the evaluation threshold Y in real time, and automatically determine whether the medical staff needs offline follow-up. This intelligent decision-making process reduces the need for manual intervention and improves the efficiency and accuracy of follow-up task arrangement. The execution unit not only determines whether it is necessary to arrange offline follow-up, but also prioritizes the tasks to be done and tracks the progress of the tasks in real time. By recording and collecting feedback on the completion of the task, the system can provide detailed follow-up task execution status. This efficient task management method ensures that medical staff can complete the task in an orderly manner, and comprehensively monitors the progress of the task, thereby improving the implementation effect of the follow-up. By collecting feedback on completed follow-up tasks, the system can continuously optimize the follow-up process and prediction model. This feedback-driven improvement mechanism enables the system to adjust according to problems in actual operations, improving the quality and efficiency of overall follow-up management. The system provides comprehensive health monitoring and early warning functions by comprehensively analyzing cardiac electrical activity, blood lipid status and control effects. It can detect potential health problems at an early stage and intervene in time, which helps to improve the quality of life and health level of elderly patients. In summary, the system further improves the prediction accuracy, task management efficiency and comprehensive health early warning capabilities of the intelligent follow-up management system for elderly chronic diseases through innovative convolutional neural network technology, intelligent follow-up decision-making, task management mechanism and feedback-driven improvement mechanism.
[0104] Example 6: Please refer to Figure 2 The embodiment of the present invention also provides an intelligent follow-up management method for chronic diseases in the elderly, comprising the following steps:
[0105] Step 1: Use home monitoring equipment to regularly monitor relevant physiological change data information, relevant cardiac electrical activity status data information and blood lipid metabolism data information of elderly heart disease patients;
[0106] Step 2: pre-process the data collected in the data monitoring module and transmit the pre-processed data;
[0107] Step 3: Construct a control effect coefficient Kxxs based on relevant physiological change data information. If the control effect coefficient Kxxs exceeds the threshold, an online intelligent access instruction will be issued;
[0108] Step 4: After receiving the online intelligent access instruction, the electrical activity coefficient Dhxs and the blood lipid state coefficient Xzxs are calculated based on the relevant cardiac electrical activity state data information and blood lipid metabolism data information, and the heart injury index Xszs is obtained by fitting in combination with the trained chronic disease prediction model;
[0109] Step 5: Pre-set the assessment threshold Y, and compare and analyze the heart injury index Xszs with the assessment threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff.
[0110] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. An intelligent follow-up management system for chronic diseases in the elderly, characterized in that: include: Data monitoring module, data processing module, daily control and detection module, regular medical care analysis module and follow-up management module; The data monitoring module is used to regularly monitor relevant physiological change data information, relevant cardiac electrical activity state data information and blood lipid metabolism data information of elderly heart disease patients using home monitoring instruments; The data processing module is used to pre-process the data collected by the data monitoring module and transmit the pre-processed data; The daily control detection module is used to construct a control effect coefficient Kxxs based on relevant physiological change data information. If the control effect coefficient Kxxs exceeds a threshold, an online intelligent access instruction will be issued externally; The regular medical care analysis module is used to calculate the electrical activity coefficient Dhxs and the blood lipid state coefficient Xzxs respectively after receiving the online intelligent access instruction based on the relevant cardiac electrical activity state data information and blood lipid metabolism data information, and to obtain the cardiac injury index Xszs by fitting in combination with the trained chronic disease prediction model; The follow-up management module is used to pre-set the evaluation threshold Y, and compare and analyze the heart injury index Xszs with the evaluation threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff; The home monitoring instruments include blood lipid testers, health bracelets, weighing scales and portable electrocardiogram devices; The data monitoring module includes a first monitoring unit, a second monitoring unit and a third monitoring unit; The first monitoring unit is used to monitor and record relevant physiological change data information of elderly heart disease patients using a health bracelet and a weighing device, wherein the relevant physiological change data information includes the blood pressure value Xyz, weight value Tzz and blood sugar value Xtz of the elderly heart disease patients in each monitoring period, and obtains the standard deviation of blood pressure in the monitoring period in combination with a statistical algorithm. , standard deviation of body weight during the monitoring period , Blood glucose standard deviation during the monitoring period , the average blood pressure value Mxy during the monitoring period, the average blood sugar value Mxt during the monitoring period, and the average body weight value Mtz during the monitoring period; The second monitoring unit is used to regularly monitor and record the relevant cardiac electrical activity state data information of the elderly heart disease patients using a portable electrocardiogram device, wherein the relevant cardiac electrical activity state data information includes the QT interval in the electrocardiogram PR interval and ST segment deviation value Pc; The third monitoring unit is used to regularly monitor and record blood lipid metabolism data information of elderly heart disease patients using a blood lipid tester, wherein the blood lipid metabolism data information includes triglyceride concentration in the blood of elderly heart disease patients during each monitoring period. and cholesterol concentration , and combined with statistical algorithms, the mean value of triglyceride concentration during the monitoring period was obtained. and the mean cholesterol concentration during the monitoring period ; The daily control and detection module includes a daily management and control analysis unit and an early warning unit; The daily control and analysis unit is used to obtain the blood pressure standardized deviation Xypc, the blood sugar standardized deviation Xtpc and the weight standardized deviation Tzpc according to the relevant physiological change data information, and calculate the control effect coefficient Kxxs according to the blood pressure standardized deviation Xypc, the blood sugar standardized deviation Xtpc and the weight standardized deviation Tzpc, which is specifically obtained according to the following formula: ; ; In the formula, It is represented as the blood pressure value in the i-th monitoring period, It is expressed as the blood sugar value in the i-th period, It is expressed as the weight value in the i-th monitoring period; The regular medical care analysis module includes a first analysis unit, a second analysis unit and a comprehensive unit; The first analysis unit is used to analyze the QT interval according to the relevant cardiac electrical activity state data information. and PR interval After being associated and dimensionless processed, the electric activity coefficient Dhxs is obtained, and the electric activity coefficient Dhxs is obtained by the following formula: ; In the formula, and All are weight values, Pc represents the ST segment deviation value, is the first correction constant; The second analysis unit is used to construct the blood lipid state coefficient Xzxs according to the lipid metabolism data information in the blood, which is specifically obtained in the following manner: ; Where i=1, 2, 3, ..., n, n represents the monitoring period, Expressed as the cholesterol concentration during the i-th monitoring period, It is expressed as the triglyceride concentration in the i-th monitoring period, and All are weight values; The comprehensive unit is used to construct a chronic disease prediction model based on the convolutional neural network technology, and input the electrical activity coefficient Dhxs, the blood lipid status coefficient Xzxs and the control effect coefficient Kxxs into the chronic disease prediction model, and after dimensionless processing, the heart damage index Xszs is obtained by fitting. The heart damage index Xszs is obtained by the following formula: ; In the formula, Expressed as ejection fraction, , , and are weight values, Expressed as the second correction constant.
2. The intelligent follow-up management system for chronic diseases in the elderly according to claim 1 is characterized in that: The data processing module includes a preprocessing unit and a transmission unit; The preprocessing unit is used to preprocess the relevant physiological change data information, the relevant cardiac electrical activity state data information and the blood lipid metabolism data information in advance, and the preprocessing includes removing noise, filling missing values and data smoothing operations, and using dimensionless processing technology to scale the preprocessed information so that the information range in the patient's condition data set falls within Inside; The transmission unit is used to transmit the pre-processed relevant physiological change data information, relevant cardiac electrical activity status data information and blood lipid metabolism data information to the cloud computing platform through the Internet of Things to construct a patient condition data set. Medical staff log in to the cloud computing platform through the electronic health record system in the hospital to access the patient condition data set of elderly patients in real time.
3. The intelligent follow-up management system for chronic diseases in the elderly according to claim 2 is characterized in that: The early warning unit is used to compare the control effect coefficient Kxxs with a preset threshold value to preliminarily determine whether there is an abnormality in the daily control of the current elderly heart disease patient. The specific comparison content is as follows: If the control effect coefficient Kxxs exceeds the threshold, it is preliminarily judged that the daily control of the elderly heart disease patient is in an abnormal state, and an online intelligent access instruction will be issued; If the control effect coefficient Kxxs does not exceed the threshold, it is preliminarily judged that the daily control of the current elderly heart disease patient is not in an abnormal state, and at this time, no online intelligent access instructions will be issued to the outside.
4. The intelligent follow-up management system for chronic diseases in the elderly according to claim 3 is characterized in that: The follow-up management module includes a comparison unit and an execution unit; The comparison unit is used to compare and analyze the heart injury index Xszs with the evaluation threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff. The specific analysis content is as follows: If the heart injury index Xszs exceeds the assessment threshold Y, it means that the elderly patient's condition is currently abnormal. At this time, the medical staff will be notified to arrange an offline follow-up task within the specified time; If the heart injury index Xszs does not exceed the assessment threshold Y, it means that the elderly patient's condition is not abnormal. At this time, the medical staff will not be notified to arrange offline follow-up tasks within the specified time. The execution unit is used to decide whether it is necessary to arrange medical staff to perform corresponding offline follow-up tasks based on the analysis content in the comparison unit. At the same time, the hospital sorts the pending follow-up tasks, tracks the progress of the follow-up tasks in real time, and records the completion status of the tasks, where the completion status includes completed, in progress, and not started, and collects feedback on completed follow-up tasks from medical staff.
5. An intelligent follow-up management method for chronic diseases in the elderly, used to implement the intelligent follow-up management system for chronic diseases in the elderly as described in any one of claims 1 to 4, characterized in that: include: Use home monitoring equipment to regularly monitor relevant physiological change data information, relevant cardiac electrical activity status data information and blood lipid metabolism data information of elderly heart disease patients; Preprocess the data collected in the data monitoring module and transmit the preprocessed data; The control effect coefficient Kxxs is constructed based on the relevant physiological change data information. If the control effect coefficient Kxxs exceeds the threshold, an online intelligent access instruction will be issued; After receiving the online intelligent access command, the electrical activity coefficient Dhxs and the blood lipid status coefficient Xzxs are calculated based on the relevant cardiac electrical activity status data information and blood lipid metabolism data information, and the heart damage index Xszs is obtained by fitting in combination with the trained chronic disease prediction model; The assessment threshold Y is set in advance, and the heart injury index Xszs is compared with the assessment threshold Y to comprehensively analyze whether the current condition of the elderly patient requires offline follow-up by medical staff.
