Data analysis-based senile chronic disease judgment method and system

Abstract

The invention discloses an old-age chronic disease judgment method and system based on data analysis, and belongs to the technical field of old-age chronic diseases, and the method comprises the steps: collecting and processing real-time data of an old-age patient, and then determining feature data of the old-age patient; training and optimizing an old-age chronic disease judgment model, analyzing and judging the feature data of the old-age patient, predicting the onset risk of the old-age chronic disease, determining the judgment result of the old-age chronic disease, and performing early warning and health management on the old-age patient. According to the invention, the problem of poor senile chronic disease diagnosis and management effect caused by incapability of judging senile chronic diseases and timely health management in the prior art is solved. According to the method, the senile chronic disease judgment model for predicting the onset risk of the senile chronic disease and judging the senile chronic disease is constructed, the feature data of the senile patient is analyzed and judged, the onset risk of the senile chronic disease is predicted, the senile chronic disease judgment result is determined, the senile chronic disease can be effectively judged, and health management and treatment can be timely performed; and the senile chronic disease diagnosis management effect can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of elderly chronic diseases, and specifically to a method and system for judging elderly chronic diseases based on data analysis. Background Art

[0002] The prevalence of multiple chronic diseases in the elderly has been increasing year by year, and common diseases include hypertension, diabetes, cardiovascular and cerebrovascular diseases, etc. Therefore, the prevention and management of elderly chronic diseases have become important public health issues.

[0003] Chinese Patent with publication number CN117393131A discloses a management method and system for elderly chronic disease follow-up care services. The method includes: a medical service institution pushing an invitation for elderly chronic disease follow-up care services to the elderly, based on the division of the nursing staff in the medical service institution and corresponding allocation to the elderly with different required nursing services, and then conducting follow-up care. Enter the follow-up care data into the system each time, submit the information in the system and the follow-up care service evaluation form to the elderly who require nursing services in different ways, and based on the analysis of the follow-up care service evaluation form, judge the quality of the follow-up care service and optimize it, so as to improve the timeliness and rehabilitation of patient treatment. However, this patent has the following defects: The existing technology cannot effectively judge elderly chronic diseases and provide timely health management and treatment, resulting in poor diagnosis and management effects of elderly chronic diseases. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for judging elderly chronic diseases based on data analysis, which can effectively judge elderly chronic diseases and provide timely health management and treatment, and can improve the diagnosis and management effects of elderly chronic diseases, solving the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions: A method for judging elderly chronic diseases based on data analysis, including: Collecting real-time data of elderly patients and determining the characteristic data of elderly patients after processing; Training and optimizing an elderly chronic disease judgment model, analyzing and judging the characteristic data of elderly patients, predicting the incidence risk of elderly chronic diseases, determining the judgment result of elderly chronic diseases, and giving early warnings and health management to elderly patients.

[0006] Preferably, collecting real-time data of elderly patients includes: Based on intelligent collection devices, real-time monitoring and collection of the diet, exercise and sleep conditions of elderly patients to obtain the life data of elderly patients; Based on intelligent collection devices, real-time monitoring and collection of the body temperature, heart rate, blood pressure, blood oxygen saturation, blood sugar, blood lipid and body mass index of elderly patients to obtain the physiological data of elderly patients; Determine the real-time data of the elderly patient based on the living data and physiological data of the elderly patient.

[0007] Preferably, real-time monitoring and collection of the body temperature, heart rate, blood pressure, and blood oxygen saturation of the elderly patient are performed based on an intelligent collection device, including: Real-time collect the body temperature data of the elderly patient; Compare the body temperature data of the elderly patient with the standard value of healthy body temperature, where the value of the standard value of healthy body temperature is 37.3 degrees Celsius; When the body temperature data of the elderly patient exceeds the standard value of healthy body temperature, collect the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient; Compare the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient with the growth ratio of the body temperature data of the elderly patient; Judge whether to adjust the data collection frequency according to the quantitative relationship between the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient and the growth ratio of the body temperature data of the elderly patient.

[0008] Preferably, judging whether to adjust the data collection frequency according to the quantitative relationship between the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient and the growth ratio of the body temperature data of the elderly patient includes: Perform data scale compression processing on the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient, so that the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient are projected onto the value range (0, 0.5]; Among them, the data value after the data scale compression processing of the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation is obtained through the following formula: Among them, R represents the data value after the data scale compression processing corresponding to the heart rate, blood pressure, and blood oxygen saturation; x represents the data value before the data scale compression processing corresponding to the heart rate, blood pressure, and blood oxygen saturation; Compare the data value after the data scale compression processing of the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation with the growth ratio of the body temperature data of the elderly patient; Extract the data with the data value after the data scale compression processing of the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation not lower than the growth ratio of the body temperature data of the elderly patient as the target data; Adjust the data collection frequencies of heart rate, blood pressure, and blood oxygen saturation by combining the change growth ratio of the target data with the growth ratio of the body temperature data of elderly patients. Among them, the adjusted data collection frequencies of heart rate, blood pressure, and blood oxygen saturation are obtained through the following formula: Among them, F represents the adjusted data collection frequencies of heart rate, blood pressure, and blood oxygen saturation; F 0 represents the data collection frequencies of heart rate, blood pressure, and blood oxygen saturation before adjustment; T b represents the growth ratio of the body temperature data of elderly patients; n represents the number of data whose data values after data scale compression processing are not lower than the growth ratio of the body temperature data of elderly patients; R i represents the data value after data scale compression processing corresponding to the i-th target data; R p represents the average value of the data after data scale compression processing corresponding to heart rate, blood pressure, and blood oxygen saturation.

[0009] Preferably, the real-time data of elderly patients is processed, including: Clean the real-time data of elderly patients based on Pandas, identify duplicate values, missing values, and outliers in the real-time data of elderly patients, delete the duplicate values, missing values, and outliers that are useless for judging elderly chronic diseases, and fill and correct the missing values and outliers that are useful for judging elderly chronic diseases; Standardize the real-time data of elderly patients based on Min-Max standardization, scale the real-time data of elderly patients to the interval [0, 1], remove the dimensional differences between the real-time data of elderly patients, and determine the standardized real-time data of elderly patients.

[0010] Preferably, the processing of the real-time data of elderly patients further includes: Integrate the real-time data of elderly patients, integrate the real-time data of elderly patients into a unified data view, and perform integrity verification on the integrated real-time data of elderly patients to determine whether there are any omissions in the integrated real-time data of elderly patients. When the data integrity verification is qualified, safely store the integrated real-time data of elderly patients in the database; Extract features from the real-time data of elderly patients, extract features related to the judgment of elderly chronic diseases from the real-time data of elderly patients, and determine the characteristic data of elderly patients, including blood pressure volatility and blood glucose change trend.

[0011] Preferably, training and optimizing the elderly chronic disease judgment model includes: According to the needs of elderly chronic disease judgment, collect the historical data of elderly patients, divide the historical data of elderly patients, and determine the training set and the test set; Based on deep learning technology, a training set is used to train a deep learning model, enabling the deep learning model to autonomously learn the behavior of elderly chronic disease judgment and predict the incidence risk of elderly chronic diseases, thereby determining an elderly chronic disease judgment model; Based on a test set, performance testing is conducted on the elderly chronic disease judgment model, and it is determined whether the elderly chronic disease judgment model can achieve the expected effect based on accuracy, recall rate, and F1 score; When the elderly chronic disease judgment model fails to achieve the expected effect, the parameters and structure of the elderly chronic disease judgment model are adjusted. After continuous iterative optimization, an optimal elderly chronic disease judgment model is determined.

[0012] Preferably, the characteristic data of elderly patients is analyzed and judged to predict the incidence risk of elderly chronic diseases, including: Obtain the optimal elderly chronic disease judgment model and deploy the optimal elderly chronic disease judgment model in the actual elderly chronic disease judgment environment; Input the characteristic data of elderly patients into the optimal elderly chronic disease judgment model, analyze and judge the characteristic data of elderly patients according to the optimal elderly chronic disease judgment model, predict the incidence risk of elderly chronic diseases, and determine the elderly chronic disease judgment result.

[0013] Preferably, early warning and health management for elderly patients are carried out, including: According to the elderly chronic disease judgment result, timely warnings are given to elderly patients with a high incidence risk of elderly chronic diseases, the characteristic data of elderly patients is analyzed to form an elderly patient chronic disease report, a health management treatment plan is formulated for elderly patients according to the elderly patient chronic disease report, and the health management treatment situation of elderly patients is monitored in real time. The health management treatment plan is dynamically adjusted according to the real-time monitoring feedback of elderly patients.

[0014] According to another aspect of the present invention, an elderly chronic disease judgment system based on data analysis is provided for implementing the elderly chronic disease judgment method based on data analysis as described above. The system includes: a data collection module, a data processing module, a model construction module, a chronic disease judgment module, and a warning management module; The data collection module is configured to determine the real-time data of elderly patients based on the living data and physiological data of elderly patients; The data processing module is configured to clean, standardize, integrate, and extract features from the real-time data of elderly patients to determine the characteristic data of elderly patients; The model construction module is configured to construct an elderly chronic disease judgment model that predicts the incidence risk of elderly chronic diseases and judges elderly chronic diseases; The chronic disease judgment module is configured to analyze and judge the characteristic data of elderly patients according to the elderly chronic disease judgment model, predict the incidence risk of elderly chronic diseases, and determine the elderly chronic disease judgment result; The warning management module is configured to timely warn and provide health management for elderly patients with a high risk of developing chronic diseases in the elderly according to the judgment results of chronic diseases in the elderly.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: Based on the living data and physiological data of elderly patients, the present invention determines the real-time data of elderly patients. By cleaning, standardizing, integrating, and feature extracting the real-time data of elderly patients, the characteristic data of elderly patients is determined. According to the judgment requirements of chronic diseases in the elderly, a judgment model for chronic diseases in the elderly is constructed to predict the onset risk of chronic diseases in the elderly and judge chronic diseases in the elderly. The characteristic data of elderly patients is analyzed and judged according to the judgment model of chronic diseases in the elderly to predict the onset risk of chronic diseases in the elderly, determine the judgment results of chronic diseases in the elderly, and timely warn and provide health management for elderly patients with a high risk of developing chronic diseases in the elderly. It can effectively judge chronic diseases in the elderly and provide timely health management and treatment, and improve the diagnostic management effect of chronic diseases in the elderly. Description of the Drawings

[0016] Figure 1 It is a flowchart of the method for judging chronic diseases in the elderly based on data analysis of the present invention; Figure 2 It is a module diagram of the system for judging chronic diseases in the elderly based on data analysis of the present invention. Detailed Embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] In order to solve the problem that the existing technology cannot effectively judge chronic diseases in the elderly and provide timely health management and treatment, resulting in poor diagnostic management effect of chronic diseases in the elderly, please refer to Figure 1 - Figure 2 , the following technical solutions are provided in this embodiment: A system for judging chronic diseases in the elderly based on data analysis includes: a data acquisition module, a data processing module, a model construction module, a chronic disease judgment module, and a warning management module; The data acquisition module is configured to determine the real-time data of the elderly patient based on the life data and physiological data of the elderly patient; the data processing module is configured to clean, standardize, integrate, and extract features from the real-time data of the elderly patient to determine the feature data of the elderly patient; the model construction module is configured to construct an elderly chronic disease judgment model that predicts the onset risk of elderly chronic diseases and judges elderly chronic diseases; the chronic disease judgment module is configured to analyze and judge the feature data of the elderly patient according to the elderly chronic disease judgment model, predict the onset risk of elderly chronic diseases, and determine the elderly chronic disease judgment result; the early warning management module is configured to timely warn and provide health management for elderly patients with a high risk of onset of elderly chronic diseases according to the elderly chronic disease judgment result.

[0019] Specifically, based on the life data and physiological data of the elderly patient, the real-time data of the elderly patient is determined. By cleaning, standardizing, integrating, and extracting features from the real-time data of the elderly patient, the feature data of the elderly patient is determined. According to the judgment requirements of elderly chronic diseases, an elderly chronic disease judgment model that predicts the onset risk of elderly chronic diseases and judges elderly chronic diseases is constructed. The feature data of the elderly patient is analyzed and judged according to the elderly chronic disease judgment model, the onset risk of elderly chronic diseases is predicted, the elderly chronic disease judgment result is determined, and timely warning and health management are provided for elderly patients with a high risk of onset of elderly chronic diseases. Effective judgment and timely health management and treatment of elderly chronic diseases can be carried out, and the diagnosis and management effect of elderly chronic diseases can be improved.

[0020] To better demonstrate the process of judging elderly chronic diseases based on data analysis, this embodiment now provides a method for judging elderly chronic diseases based on data analysis, which is implemented using a system for judging elderly chronic diseases based on data analysis, including: collecting the real-time data of elderly patients and determining the feature data of elderly patients after processing; training and optimizing the elderly chronic disease judgment model, analyzing and judging the feature data of elderly patients, predicting the onset risk of elderly chronic diseases, determining the elderly chronic disease judgment result, and warning and providing health management for elderly patients.

[0021] In this embodiment, collecting the real-time data of elderly patients includes: Based on intelligent acquisition devices, the diet, exercise, and sleep conditions of elderly patients are monitored and collected in real time to obtain the life data of elderly patients; It should be noted that the real-time monitoring and collection of the diet, exercise, and sleep conditions of elderly patients are important means for chronic disease management and health intervention; by combining Internet of Things, wearable devices, and big data analysis technologies, comprehensive collection and real-time monitoring of the health data of the elderly can be achieved.

[0022] Specifically, devices such as smart bowls and smart chopsticks are used to record the types, weights, and intake times of foods. Food ingredients and calories are analyzed through image recognition technology, and the eating behaviors of elderly patients, such as chewing times and swallowing frequencies, are monitored through smart bracelets or watches.

[0023] Specifically, the number of steps, calorie consumption, and exercise distance of elderly patients during exercise are monitored in real time through smart bracelets or watches. The gait, walking distance, and pressure distribution of elderly patients during exercise are monitored through smart insoles to prevent falls, and the activities of elderly patients indoors are monitored through infrared sensors or cameras.

[0024] Specifically, the sleeping postures, breathing frequencies, and heart rates of elderly patients are monitored through smart mattresses. The sleep duration, proportions of deep sleep and light sleep, and the number of awakenings are recorded through smart bracelets or watches. The temperature, humidity, and light in the bedroom are monitored through environmental sensors to optimize the sleep environment.

[0025] Based on smart acquisition devices, the body temperature, heart rate, blood pressure, blood oxygen saturation, blood glucose, blood lipids, and body mass index of elderly patients are monitored and collected in real time to obtain the physiological data of elderly patients; It should be noted that the real-time monitoring and collection of the body temperature, heart rate, blood pressure, blood oxygen saturation, blood glucose, blood lipids, and body mass index (BMI) of elderly patients are important means for chronic disease management and health intervention. By combining Internet of Things, wearable devices, and big data analysis technologies, comprehensive collection and real-time monitoring of these physiological indicators can be achieved.

[0026] Specifically, when monitoring body temperature, a smart thermometer is used to monitor the body temperature of elderly patients in real time, supporting continuous monitoring and abnormal warning. The body temperature can also be measured regularly through a non-contact infrared thermometer.

[0027] Specifically, when monitoring heart rate, an optical sensor PPG is used to monitor the heart rate in real time, supporting the monitoring of resting heart rate and exercise heart rate. A portable ECG device can also be used to monitor the electrocardiogram signal.

[0028] Specifically, when monitoring blood pressure, an upper-arm or wrist-type electronic sphygmomanometer is used to measure blood pressure regularly, supporting data synchronization to a mobile App. A wearable device can also be used for non-invasive continuous blood pressure monitoring.

[0029] Specifically, when monitoring blood oxygen saturation, an optical sensor PPG is used to monitor the blood oxygen saturation in real time. A portable finger clip oximeter can also be used to measure the blood oxygen saturation regularly.

[0030] Specifically, when monitoring blood glucose, an implantable or patch-type CGM device is used to monitor the blood glucose level in real time. A fingertip blood sampling blood glucose meter can also be used to measure the blood glucose regularly.

[0031] Specifically, when monitoring blood lipids, a portable device is used to regularly measure blood lipid indicators such as cholesterol and triglycerides.

[0032] Specifically, when monitoring the body mass index (BMI), a smart weighing scale is used to measure body weight and body fat percentage, and the BMI is automatically calculated.

[0033] In this embodiment, based on the living data and physiological data of the elderly patients, the real-time data of the elderly patients is determined, providing data support for the subsequent chronic disease judgment of the elderly patients.

[0034] Specifically, based on the intelligent acquisition device, the body temperature, heart rate, blood pressure and blood oxygen saturation of the elderly patients are monitored and collected in real time, including: Real-time collection of the body temperature data of the elderly patients; Compare the body temperature data of the elderly patients with the standard value of healthy body temperature, where the value of the standard value of healthy body temperature is 37.3 degrees Celsius; When the body temperature data of the elderly patients exceeds the standard value of healthy body temperature, collect the change growth ratios of the heart rate, blood pressure and blood oxygen saturation of the elderly patients; Compare the change growth ratios of the heart rate, blood pressure and blood oxygen saturation of the elderly patients with the growth ratio of the body temperature data of the elderly patients; Judge whether to adjust the data collection frequency according to the quantitative relationship between the change growth ratios of the heart rate, blood pressure and blood oxygen saturation of the elderly patients and the growth ratio of the body temperature data of the elderly patients.

[0035] The technical effects of the above technical solution are as follows: By collecting physiological data such as the body temperature, heart rate, blood pressure, and blood oxygen saturation of elderly patients in real time, it can ensure that the information obtained accurately reflects the current physical condition of the patients, avoiding information deviation caused by untimely collection or data loss. Comparing the body temperature data with the standard value of healthy body temperature and further comparing the growth ratios of heart rate, blood pressure, and blood oxygen saturation with the body temperature data helps to more accurately judge the physical state of elderly patients and provide accurate data support for subsequent medical decisions. Collecting body temperature data in real time and the change growth ratios of other physiological data in a timely manner when the body temperature is abnormal can quickly detect abnormal changes in the physical condition of elderly patients, realizing early warning of potential health problems so that medical staff can take corresponding measures in a timely manner. Judging whether to adjust the data collection frequency according to the relationship between the growth ratios of various physiological data can make the collection frequency match the changes in the patient's condition. When the patient's physical condition changes greatly, increasing the collection frequency can more closely monitor the development of the condition; when the condition is stable, appropriately reducing the collection frequency can, while ensuring the effectiveness of the data, reasonably utilize resources and ensure that the dynamic changes of the condition can be captured in a timely manner. Deciding whether to adjust the data collection frequency according to the changes in the patient's physiological data avoids unnecessary high-frequency data collection when the patient's physical condition is stable, thereby reducing the resource occupancy of intelligent collection devices such as power consumption and storage resource occupancy, and extending the service time and service life of the devices. Targeted data collection and frequency adjustment make the collected data more valuable, reduce the collection and processing of invalid data, improve the working efficiency of the entire medical monitoring system, and enable medical staff to more efficiently focus on the actual condition of the patients. Considering multiple physiological indicators such as body temperature, heart rate, blood pressure, and blood oxygen saturation and their change growth ratios comprehensively, and evaluating the physical condition of elderly patients from multiple dimensions can, compared with the monitoring of a single indicator, more comprehensively and accurately reflect the health condition of the patients and improve the reliability of the monitoring results. Judging whether to adjust the data collection frequency by comparing the quantitative relationship between various indicators can timely detect abnormal correlations between physiological indicators and early warn of possible health problems, providing more reliable protection for the health of elderly patients.

[0036] Specifically, judging whether to adjust the data collection frequency according to the quantitative relationship between the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient and the growth ratio of the body temperature data of the elderly patient includes: Performing data scale compression processing on the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient, so that the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation of the elderly patient are projected onto the numerical range (0, 0.5]; Among them, the data value after the data scale compression processing of the change growth ratios of the heart rate, blood pressure, and blood oxygen saturation is obtained through the following formula: Among them, R represents the data value after data scale compression processing of the data corresponding to heart rate, blood pressure, and blood oxygen saturation; x represents the data value before data scale compression processing of the data corresponding to heart rate, blood pressure, and blood oxygen saturation; Compare the data value after data scale compression processing of the change growth ratio of the heart rate, blood pressure, and blood oxygen saturation with the growth ratio of the body temperature data of the elderly patients; Extract the data with the data value after data scale compression processing in the change growth ratio of heart rate, blood pressure, and blood oxygen saturation not lower than the growth ratio of the body temperature data of the elderly patients as the target data; Adjust the data acquisition frequency of heart rate, blood pressure, and blood oxygen saturation by combining the change growth ratio of the target data with the growth ratio of the body temperature data of the elderly patients. Among them, the adjusted data acquisition frequency of heart rate, blood pressure, and blood oxygen saturation is obtained through the following formula: Among them, F represents the adjusted data acquisition frequency of heart rate, blood pressure, and blood oxygen saturation; F 0 represents the data acquisition frequency of heart rate, blood pressure, and blood oxygen saturation before adjustment; T b represents the growth ratio of the body temperature data of the elderly patients; n represents the number of data with the data value after data scale compression processing not lower than the growth ratio of the body temperature data of the elderly patients; R i represents the data value after data scale compression processing corresponding to the i-th target data; R p represents the average value of the data after data scale compression processing corresponding to heart rate, blood pressure, and blood oxygen saturation.

[0037] The technical effects of the above technical solutions are as follows: By performing data scale compression processing on the change growth ratio of the heart rate, blood pressure, and blood oxygen saturation of elderly patients and projecting it onto the numerical interval (0, 0.5], these data can be compared and analyzed on the same scale, simplifying the complexity of the data. This processing method facilitates subsequent calculations and judgments, improves the efficiency of data processing, avoids analysis difficulties caused by large data scale differences, and enables the system to process and evaluate the changes of these physiological indicators more quickly. Extract the data with the data value after data scale compression processing not lower than the growth ratio of the body temperature data of the elderly patients as the target data, clarifying the scope of data to be focused on. This screening method can focus on the physiological index data that is closely related to the body temperature change and has a large change degree, reducing unnecessary data interference, and further improving the pertinence and effectiveness of data processing.

[0038] Meanwhile, the data acquisition frequencies of heart rate, blood pressure, and blood oxygen saturation are adjusted by combining the change growth ratio of the target data with the growth ratio of the body temperature data of elderly patients, comprehensively considering the relationships among multiple physiological indicators. Compared with the judgment based on a single indicator, this multi-indicator comprehensive analysis method can more comprehensively and accurately reflect the changes in the physical conditions of elderly patients, thereby more precisely adjusting the data acquisition frequency. When the changes in certain physiological indicators are consistent with the body temperature change trend and are relatively significant, increasing the acquisition frequency can more timely and accurately monitor the development of the patient's condition, improving the accuracy of monitoring. By calculating the adjusted data acquisition frequencies of heart rate, blood pressure, and blood oxygen saturation through the above technical solution, a quantitative scientific basis is provided for the adjustment of the acquisition frequency. The formula takes into account multiple factors such as the acquisition frequency before adjustment, the growth ratio of body temperature data, the number of target data, the value corresponding to each target data, and the average value after data scale compression processing, making the adjustment of the acquisition frequency more reasonable and scientific, capable of being dynamically optimized according to the actual situation of the patient, and further improving the accuracy of monitoring. Adjusting the data acquisition frequency according to the changes in physiological indicator data avoids unnecessary high-frequency data acquisition when the patient's physical condition is stable, thus saving resources of intelligent acquisition devices such as power and storage capacity. When the patient's condition is relatively stable and the changes in various physiological indicators are small, reducing the acquisition frequency can extend the device's usage time and reduce resource waste while ensuring that the changes in the condition can be detected in a timely manner, improving resource utilization efficiency. Through the optimized adjustment of the data acquisition frequency, the acquisition device can allocate resources more reasonably to different physiological indicator monitoring. For physiological indicators with obvious changes and related to body temperature changes, increase the acquisition frequency to ensure more detailed data is obtained; for indicators with small changes, appropriately reduce the frequency to make more reasonable use of the device resources, improving the performance and stability of the entire monitoring system.

[0039] In this embodiment, the real-time data of elderly patients is processed, including: Clean the real-time data of elderly patients based on Pandas, identify duplicate values, missing values, and outliers in the real-time data of elderly patients, and delete the duplicate values, missing values, and outliers that are useless for the judgment of elderly chronic diseases, and fill and correct the missing values and outliers that are useful for the judgment of elderly chronic diseases; Standardize the real-time data of elderly patients based on Min-Max standardization, scale the real-time data of elderly patients to the interval [0, 1], remove the dimensional differences between the real-time data of elderly patients, and determine the standardized real-time data of elderly patients; Integrate the real-time data of elderly patients, integrate the real-time data of elderly patients into a unified data view, and perform integrity verification on the integrated real-time data of elderly patients to determine whether there are any omissions in the integrated real-time data of elderly patients. When the data integrity verification is qualified, securely store the integrated real-time data of elderly patients in the database; Extract features from the real-time data of elderly patients, extract features related to the judgment of elderly chronic diseases from the real-time data of elderly patients, and determine the characteristic data of elderly patients, including blood pressure volatility and blood glucose change trend.

[0040] It should be noted that by cleaning, standardizing, integrating, and extracting features from the real-time data of elderly patients, the characteristic data of elderly patients is determined, which facilitates subsequent analysis and judgment of the characteristic data of elderly patients using the elderly chronic disease judgment model, predicting the incidence risk of elderly chronic diseases, and determining the elderly chronic disease judgment result.

[0041] In this embodiment, train and optimize the elderly chronic disease judgment model, including: According to the elderly chronic disease judgment requirements, collect the historical data of elderly patients, divide the historical data of elderly patients, and determine the training set and test set; Based on deep learning technology, use the training set to train the deep learning model, enable the deep learning model to autonomously learn the elderly chronic disease judgment behavior and predict the incidence risk of elderly chronic diseases, and determine the elderly chronic disease judgment model; Based on the test set, perform performance testing on the elderly chronic disease judgment model, and judge whether the elderly chronic disease judgment model can achieve the expected effect based on the accuracy rate, recall rate, and F1 score; When the elderly chronic disease judgment model cannot achieve the expected effect, adjust the parameters and structure of the elderly chronic disease judgment model. After continuous iterative optimization, determine the optimal elderly chronic disease judgment model.

[0042] In this embodiment, analyze and judge the characteristic data of elderly patients and predict the incidence risk of elderly chronic diseases, including: Obtain the optimal elderly chronic disease judgment model and deploy the optimal elderly chronic disease judgment model in the actual elderly chronic disease judgment environment; Input the characteristic data of elderly patients into the optimal elderly chronic disease judgment model, analyze and judge the characteristic data of elderly patients according to the optimal elderly chronic disease judgment model, predict the incidence risk of elderly chronic diseases, and determine the elderly chronic disease judgment result.

[0043] In this embodiment, give early warnings and provide health management for elderly patients, including: Based on the judgment results of elderly chronic diseases, timely warnings are given to elderly patients with a high risk of developing elderly chronic diseases. The characteristic data of elderly patients are analyzed to form a chronic disease report for elderly patients. According to the chronic disease report of elderly patients, a health management treatment plan is formulated for elderly patients, and the health management treatment situation of elderly patients is monitored in real time. The health management treatment plan is dynamically adjusted according to the real-time monitoring feedback of elderly patients.

[0044] In summary, by collecting the living data and physiological data of elderly patients, determining the real-time data of elderly patients, cleaning, standardizing, integrating and feature extracting the real-time data of elderly patients, determining the characteristic data of elderly patients, and according to the judgment requirements of elderly chronic diseases, constructing an elderly chronic disease judgment model for predicting the onset risk of elderly chronic diseases and judging elderly chronic diseases, analyzing and judging the characteristic data of elderly patients according to the elderly chronic disease judgment model, predicting the onset risk of elderly chronic diseases, determining the elderly chronic disease judgment results, and giving timely warnings and health management to elderly patients with a high risk of developing elderly chronic diseases, the elderly chronic diseases can be effectively judged and timely health management treatment can be carried out, and the diagnosis and management effect of elderly chronic diseases can be improved; it can be applied to hospital and clinic scenarios, community health management scenarios and personal health management scenarios. When applied to hospital and clinic scenarios, it can assist doctors in the early screening and diagnosis of chronic diseases, improve the diagnosis and treatment efficiency and reduce the misdiagnosis rate; when applied to community health management scenarios, it can provide regular health assessments and disease risk predictions for elderly patients, and support community doctors in health intervention and follow-up; when applied to personal health management scenarios, through mobile apps or wearable devices, health data can be monitored in real time, and personalized health advice and warnings can be provided.

[0045] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0046] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for judging chronic diseases in the elderly based on data analysis, characterized in that: include: Collect real-time data of elderly patients and determine characteristic data of elderly patients after processing; Train and optimize the elderly chronic disease judgment model, analyze and judge the characteristic data of elderly patients, predict the risk of elderly chronic diseases, determine the judgment results of elderly chronic diseases, and provide early warning and health management for elderly patients.

2. The method for determining chronic diseases in the elderly based on data analysis according to claim 1, characterized in that: Collect real-time data of elderly patients, including: Based on intelligent data collection equipment, real-time monitoring and collection of elderly patients' diet, exercise and sleep conditions are carried out to obtain elderly patients' life data; Based on intelligent data collection equipment, the body temperature, heart rate, blood pressure, blood oxygen saturation, blood sugar, blood lipids and body mass index of elderly patients are monitored and collected in real time to obtain physiological data of elderly patients; Determine the real-time data of elderly patients based on their life data and physiological data.

3. The method for determining chronic diseases in the elderly based on data analysis according to claim 2, characterized in that: Real-time monitoring and collection of body temperature, heart rate, blood pressure and blood oxygen saturation of elderly patients based on intelligent collection equipment, including: Collect body temperature data of elderly patients in real time; Comparing the body temperature data of the elderly patient with a standard value of healthy body temperature, wherein the standard value of healthy body temperature is 37.3 degrees Celsius; When the body temperature data of the elderly patient exceeds the standard value of healthy body temperature, the change growth rate of the elderly patient's heart rate, blood pressure and blood oxygen saturation is collected; Comparing the change growth rate of the elderly patient's heart rate, blood pressure and blood oxygen saturation with the growth rate of the elderly patient's body temperature data; Whether to adjust the data collection frequency is determined based on the quantitative relationship between the change growth rate of the elderly patient's heart rate, blood pressure and blood oxygen saturation and the growth rate of the elderly patient's body temperature data.

4. The method for determining chronic diseases in the elderly based on data analysis according to claim 3, characterized in that: Determining whether to adjust the data collection frequency according to the quantitative relationship between the change growth rate of the elderly patient's heart rate, blood pressure and blood oxygen saturation and the growth rate of the elderly patient's body temperature data includes: The change growth ratio of the heart rate, blood pressure and blood oxygen saturation of the elderly patient is subjected to data scale compression processing, so that the change growth ratio of the heart rate, blood pressure and blood oxygen saturation of the elderly patient is projected to a value of (0, 0.5]; Compare the data values ​​of the change growth ratios of the heart rate, blood pressure and blood oxygen saturation after data scale compression processing with the growth ratio of the body temperature data of the elderly patient; Extract the data whose corresponding data values ​​after data scale compression processing in the change growth ratio of heart rate, blood pressure and blood oxygen saturation are not lower than the growth ratio of body temperature data of elderly patients as target data; The data collection frequency of heart rate, blood pressure and blood oxygen saturation is adjusted by utilizing the change growth rate of the target data combined with the growth rate of the body temperature data of the elderly patient.

5. The method for determining chronic diseases in the elderly based on data analysis as claimed in claim 2, characterized in that: Processing of real-time data of elderly patients, including: Based on Pandas, the real-time data of elderly patients are cleaned, and duplicate values, missing values ​​and outliers in the real-time data of elderly patients are identified. The duplicate values, missing values ​​and outliers that are useless for the judgment of elderly chronic diseases are deleted, and the missing values ​​and outliers that are useful for the judgment of elderly chronic diseases are filled and corrected. The real-time data of elderly patients are standardized based on Min-Max standardization, so that the real-time data of elderly patients are scaled to the interval [0, 1], the dimension differences between the real-time data of elderly patients are removed, and the standardized real-time data of elderly patients are determined.

6. The method for determining chronic diseases in the elderly based on data analysis according to claim 5, characterized in that: Processing of real-time data of elderly patients also includes: Integrate the real-time data of elderly patients into a unified data view, and verify the integrity of the integrated real-time data of elderly patients to determine whether the integrated real-time data of elderly patients is missing. When the data integrity verification is qualified, the integrated real-time data of elderly patients will be securely stored in the database; Feature extraction is performed on the real-time data of elderly patients. Features related to the judgment of elderly chronic diseases are extracted from the real-time data of elderly patients to determine the characteristic data of elderly patients, including blood pressure fluctuation rate and blood sugar change trend.

7. The method for determining chronic diseases in the elderly based on data analysis according to claim 6, characterized in that: Train and optimize the elderly chronic disease judgment model, including: According to the needs of elderly chronic diseases, historical data of elderly patients are collected, divided, and training and test sets are determined; Based on deep learning technology, the deep learning model is trained with a training set, so that the deep learning model can autonomously learn the judgment behavior of elderly chronic diseases and predict the risk of elderly chronic diseases, and determine the judgment model of elderly chronic diseases; The performance of the elderly chronic disease judgment model is tested based on the test set, and the accuracy, recall rate and F1 score are used to determine whether the elderly chronic disease judgment model can achieve the expected effect; When the elderly chronic disease judgment model cannot achieve the expected effect, the parameters and structure of the elderly chronic disease judgment model are adjusted, and the optimal elderly chronic disease judgment model is determined after continuous iterative optimization.

8. The method for determining chronic diseases in the elderly based on data analysis according to claim 7, characterized in that: Analyze and judge the characteristic data of elderly patients to predict the risk of chronic diseases in the elderly, including: Obtain the optimal model for judging chronic diseases in the elderly, and deploy it in the actual environment for judging chronic diseases in the elderly; The characteristic data of elderly patients are input into the optimal model for judging elderly chronic diseases. The characteristic data of elderly patients are analyzed and judged according to the optimal model for judging elderly chronic diseases, the risk of elderly chronic diseases is predicted, and the judgment results of elderly chronic diseases are determined.

9. The method for determining chronic diseases in the elderly based on data analysis according to claim 8, characterized in that: Provide early warning and health management for elderly patients, including: Based on the results of the judgment of chronic diseases in the elderly, timely warnings are given to elderly patients with high risks of chronic diseases, and the characteristic data of elderly patients are analyzed to form chronic disease reports of elderly patients. Health management and treatment plans are formulated for elderly patients based on the chronic disease reports of elderly patients, and the health management and treatment of elderly patients are monitored in real time. The health management and treatment plans are dynamically adjusted according to the real-time monitoring feedback of elderly patients.

10. A system for judging chronic diseases in the elderly based on data analysis, used to implement the method for judging chronic diseases in the elderly based on data analysis as claimed in claim 9, characterized in that: The system includes: a data acquisition module, a data processing module, a model building module, a chronic disease judgment module and an early warning management module; The data acquisition module is configured to determine the real-time data of the elderly patient based on the life data and physiological data of the elderly patient; The data processing module is configured to clean, standardize, integrate and extract features from the real-time data of elderly patients to determine the feature data of elderly patients; The model building module is configured to build a geriatric chronic disease judgment model for predicting the risk of geriatric chronic diseases and judging geriatric chronic diseases; The chronic disease judgment module is configured to analyze and judge the characteristic data of elderly patients according to the elderly chronic disease judgment model, predict the risk of elderly chronic diseases, and determine the elderly chronic disease judgment results; The early warning management module is configured to provide timely early warning and health management for elderly patients with high risk of developing chronic diseases according to the judgment results of elderly chronic diseases.

Images