Radar map-based intelligent community health management system for senile chronic disease patients

Abstract

The invention relates to the technical field of data processing, and provides an intelligent community health management system for senile chronic disease patients based on a radar map, and the system comprises the steps: regularly obtaining the monitoring data of a plurality of health indexes of the senile chronic disease patients; obtaining standardized data of each health index of the patient; determining the illness state reflecting degree of each health index of the patient; generating a radar map of each time of monitoring of the patient; determining the intervention degree of each monitoring of the patient according to the difference of the adjacent monitoring radar maps of the same patient and the change trend of the continuous monitoring radar maps; the medication adjustment degree of the patient is obtained, and then the illness state change degree of the patient is obtained; based on the disease change degree and the medication adjustment degree of the patient, obtaining health management suggestions for the patient; and the hospital timely shares the health management suggestions to the community after obtaining the health management suggestions of the patient. The objective of the invention is to solve the problem that health state monitoring management is affected by difference of radar map expressions caused by different illness states of patients.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an intelligent community health management system for elderly patients with chronic diseases based on radar charts. BACKGROUND

[0002] The chronic disease management system is mainly aimed at hospital patients, and through the connection with the regional information platform and the hospital HIS system, a trinity chronic disease management service mode of hospital, community and family is constructed to realize remote monitoring, chronic disease evaluation and individual intervention, and a dynamic, long-term and closed-loop chronic disease management process is constructed. The chronic disease management is mainly aimed at target groups such as patients with hypertension, diabetes, dyslipidemia, hyperuricemia and osteoporosis, and through the tracking and monitoring of health indicators of chronic disease patients outside the hospital, the target groups are helped to reduce the probability of chronic diseases and delay the development process of chronic diseases.

[0003] For the intelligent community management of elderly patients with chronic diseases, the patient's chronic disease file is established, the multi-dimensional health indicators of the patient are continuously monitored based on the chronic disease file, and a radar chart is constructed. The trend analysis of the disease condition of the patient with chronic diseases is carried out through the change of the radar chart, and the treatment intervention in the continuous monitoring process is recorded. However, the focused health indicators are different in the continuous tracking and monitoring of different patients with chronic diseases, and the radar chart with unified form and fixed health indicators cannot completely reflect the health indicators with large change amplitude of the patients with chronic diseases, resulting in inaccurate analysis results of the disease condition change of the patients with chronic diseases based on the radar chart, and further affecting the health status monitoring results of the patients. SUMMARY

[0004] The present application provides an intelligent community health management system for elderly patients with chronic diseases based on radar charts to solve the problem that the existing radar chart performance is different due to different disease conditions of patients, which affects health status monitoring and management. The technical solution adopted is as follows:

[0005] The present application provides an intelligent community health management system for elderly patients with chronic diseases based on radar charts to solve the problem that the existing radar chart performance is different due to different disease conditions of patients, which affects health status monitoring and management. The technical solution adopted is as follows:

[0006] The data acquisition module is used for regularly acquiring monitoring data of multiple health indicators of elderly patients with chronic diseases.

[0007] The data standardization module is used for standardizing the monitoring data of the same health indicators of a large number of patients to obtain standardized data of each health indicator of the patient.

[0008] The radar chart construction and analysis module is used for determining the disease manifestation degree of each health indicator of the patient according to the numerical performance difference of the standardized data of different health indicators of the same patient, and generating a radar chart of each monitoring of the patient based on the standardized data of each health indicator of the patient and the disease manifestation degree.

[0009] Based on the differences in radar charts from adjacent monitoring sessions for the same patient, as well as the changing trends of radar charts from consecutive monitoring sessions, and combined with the degree of disease manifestation of various health indicators of the patient, the degree of intervention for each monitoring session is determined; based on the degree of intervention and the radar chart performance of the corresponding monitoring sessions, the degree of medication adjustment for the patient is obtained, thereby obtaining the degree of change in the patient's condition;

[0010] The health management module is used to obtain health management suggestions for patients based on the degree of change in their condition and the degree of medication adjustment.

[0011] The data sharing module is used to share radar charts generated from each patient's monitoring between the hospital and the community, and the hospital can also promptly share the patient's health management recommendations with the community after obtaining them.

[0012] Optionally, the standardization process for monitoring data of a large number of patients with the same health indicators to obtain standardized data of various health indicators includes the following specific methods:

[0013] For any health indicator, obtain the normal range of the monitoring data for that health indicator; obtain the standardized range of the radar chart;

[0014] By using linear transformation, the normal range of this health indicator is transformed to the standardized range. Then, the monitoring data of this health indicator for each patient are linearly transformed to obtain the standardized data of this health indicator for each patient.

[0015] Optionally, the specific method for obtaining the degree of manifestation of the patient's condition in various health indicators is as follows:

[0016] For any elderly patient with chronic disease, the standardized data of the patient's various health indicators are sorted in time sequence to obtain the standardized sequence of each health indicator; the Pearson correlation coefficient between any two standardized sequences of health indicators is obtained, and the health indicator with the largest mean Pearson correlation coefficient with the standardized sequence of other health indicators is taken as the normal health indicator of the patient.

[0017] Based on the standardized sequence of various health indicators of the patient, and the distribution of the standardized data values ​​within the standardized range, the degree of disease manifestation of the patient's various health indicators is obtained.

[0018] Optionally, the specific methods for obtaining the degree of disease manifestation of various health indicators of the patient based on the standardized sequence of various health indicators of the patient and the distribution of the standardized data values ​​within the standardized range include:

[0019]

[0020] Where, γ ic represents the degree of manifestation of the i-th health indicator for any elderly patient with chronic disease. i,0 This represents the Pearson correlation coefficient between the i-th health indicator of the patient and the standardized sequence of their normal health indicators, where n is the number of indicators. ' i Δg represents the number of standardized data points for the i-th health indicator of the patient that are outside its standardized range, N represents the number of standardized data points for each health indicator of the patient, and Δg represents the number of standardized data points for each health indicator of the patient. i This indicates that all standardized data for the i-th health indicator of this patient are of very poor quality.

[0021] Optionally, the specific method for generating radar charts for each patient monitoring session includes:

[0022] For any elderly patient with chronic disease, the degree of disease manifestation of all health indicators is linearly normalized, and the result is used as the adjustment range of each health indicator.

[0023] For any health indicator of the patient, the sum of 1 plus the adjustment range is multiplied by the upper limit of the standardized range and rounded up. This product is used as the upper limit of the radar chart data range for that health indicator, and the lower limit of the standardized range is directly used as the lower limit of the radar chart data range, thus obtaining the radar chart data range for that health indicator.

[0024] Obtain the radar chart data range of the patient's various health indicators, and construct the patient's radar chart accordingly. Combine the standardized data of the patient's various health indicators from each monitoring session to generate radar charts for each monitoring session.

[0025] Optionally, the method for determining the degree of intervention for each monitoring session by analyzing the differences in radar charts from adjacent monitoring sessions for the same patient, as well as the trends in radar chart changes from consecutive monitoring sessions, combined with the severity of the patient's condition across various health indicators, includes the following specific methods:

[0026] The degree of change in radar charts for each monitoring session of the same patient was obtained by considering the differences in radar charts between adjacent monitoring sessions and the changing trends of radar charts in consecutive monitoring sessions, combined with the degree of disease manifestation of various health indicators of the patient.

[0027] Obtain the analysis range of any elderly patient with chronic disease during the j-th monitoring session, and the intervention level β of that patient during the j-th monitoring session. j The calculation method is as follows:

[0028]

[0029] in, This indicates the number of monitoring sessions within the analysis range for the j-th monitoring session of this patient. δ represents the mean value of the change in radar chart values ​​for the patient up to the j-th monitoring session. j This indicates the degree of change in the radar chart during the j-th monitoring of the patient, δ j,m This represents the degree of change in the radar chart of the m-th monitoring within the analysis range of the j-th monitoring of the patient, where || represents the absolute value function.

[0030] Optionally, the specific methods for obtaining the degree of change in the radar chart of the patient at each monitoring session include:

[0031]

[0032] Where, δ j γ represents the degree of change in the radar chart of any elderly patient with chronic disease during the j-th monitoring session, I represents the number of health indicators monitored, and γ i Δg represents the degree of disease manifestation of the i-th health indicator for the patient. i (j,j-1) represents the absolute value of the difference between the standardized data of the i-th health indicator of the patient in the j-th and j-1-th monitoring sessions, g max The upper limit of the standardization range is represented by , and softmax() represents the weight normalization function.

[0033] Optionally, the degree of medication adjustment for the patient can be obtained using the following method:

[0034] For any elderly patient with chronic disease, the j-th monitoring is performed, and standardized predicted values ​​of various health indicators for the j-th monitoring are obtained by fitting and predicting based on the analysis range. A radar chart is then generated as the predicted radar chart for the j-th monitoring.

[0035] The degree of change in the radar chart of the patient's j-th monitoring is calculated by comparing the radar chart with the predicted radar chart. The standardized data of each health indicator in the radar chart of the patient's (j-1)-th monitoring are replaced with the standardized predicted values ​​of each health indicator in the predicted radar chart of the patient's j-th monitoring. The results are then used as the degree of intervention performance of the patient in the j-th monitoring by taking the absolute value.

[0036] The maximum value of the intervention performance across all monitoring sessions for that patient will be used as the level of medication adjustment for that patient.

[0037] Optionally, the specific methods for obtaining the degree of change in the patient's condition include:

[0038] All monitoring sessions of the patient were clustered according to the degree of intervention performance, resulting in two clusters. Several monitoring sessions from the cluster with the largest mean intervention performance were selected as the corresponding monitoring sessions for the treatment intervention and used as segmentation points to segment all monitoring sessions of the patient.

[0039] For any segment, the mean of the change in the radar chart of the segment (excluding the first monitoring) is obtained as the overall change in the radar chart of that segment. The overall change in the radar chart of all segments is arranged in chronological order, and a straight line is fitted using the least squares method to obtain the fitting slope, which is used as the change in the patient's condition.

[0040] Optionally, the specific method for obtaining the health management recommendations for patients is as follows:

[0041] For any elderly patient with chronic disease, if the degree of medication adjustment as of the most recent monitoring is greater than the degree of change in the condition, the existing regular monitoring and regular treatment intervention should be maintained; if the degree of medication adjustment is less than or equal to the degree of change in the condition, the patient should be admitted to the hospital for treatment in a timely manner.

[0042] The beneficial effects of this invention are as follows: This invention continuously monitors multiple health indicators of a large number of elderly patients with chronic diseases, and constructs a radar chart that can intuitively reflect changes in patients' conditions through data standardization and quantification of the degree of disease manifestation of each health indicator. By analyzing the trend of changes in the radar chart and the changes in multiple health indicators after hospital treatment intervention, the intervention effect and changes in patients' conditions are quantified. Specifically, by analyzing the standardized data changes and numerical performance of different health indicators of the same patient, significant changes are used to reflect the patient's condition, and the radar chart generation process is further adjusted to ensure that the radar chart intuitively reflects the patient's condition. Based on the changes in the radar chart and the changes in patients' health indicators under treatment intervention, the degree of hospital intervention under corresponding monitoring is analyzed, and the intervention effect is further quantified. At the same time, by eliminating the influence of intervention effect, the changes in patients' conditions are analyzed to accurately monitor the changes in the conditions of patients with chronic diseases, thereby providing health management suggestions, realizing intelligent community-assisted health management for elderly patients with chronic diseases, and reducing the incidence of chronic diseases in the target population. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a structural block diagram of an intelligent community health management system for elderly patients with chronic diseases based on radar charts, provided as an embodiment of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Please see Figure 1 This diagram illustrates a structural block diagram of an intelligent community health management system for elderly patients with chronic diseases based on radar charts, according to an embodiment of the present invention. The system includes:

[0047] Data acquisition module 101: Regularly acquires monitoring data of multiple health indicators of elderly patients with chronic diseases.

[0048] The purpose of this embodiment is to establish chronic disease records for elderly patients with chronic diseases by using health indicator data from regular monitoring at hospitals and community health stations. Through data sharing between hospitals and communities, and by constructing radar charts, the changes in the condition of elderly patients with chronic diseases can be quantified based on the performance and changes of the radar charts. In turn, intelligent health management suggestions can be generated through the community. The first step is to obtain monitoring data of multiple health indicators of elderly patients with chronic diseases during regular treatment in the community and hospitals.

[0049] Specifically, the hospital collaborates with the community to establish chronic disease records for a large number of elderly patients with chronic diseases. Through data sharing, the records are uploaded to the hospital's database. Patients undergo medical treatment and regularly monitor multiple health indicators at health stations set up in the community. This embodiment targets patients with hypertension, diabetes, dyslipidemia, hyperuricemia, and osteoporosis, collecting monitoring data on multiple health indicators, including blood pressure, blood sugar, blood oxygen, blood lipids, and blood uric acid. The specific items collected here are only examples. The interval between regular collections and the collection of more health indicators are determined by the hospital and will not be elaborated on in this embodiment. This results in monitoring data on multiple health indicators for a large number of elderly patients with chronic diseases.

[0050] Data standardization module 102: Standardizes monitoring data of a large number of patients with the same health indicators to obtain standardized data of various health indicators of patients.

[0051] It should be noted that during the subsequent radar chart construction process, the monitoring data of different health indicators have different dimensions, while the radar chart has the same specifications in all directions. Therefore, it is necessary to standardize the monitoring data to ensure the normal construction of the radar chart and to prevent large distortions or deviations in the radar chart due to differences in dimensions.

[0052] Specifically, for any health indicator, the normal range of the monitoring data for that health indicator is obtained. The normal ranges of all health indicators are directly obtained from the hospital database, which is an existing method and will not be described in detail in this embodiment. In this embodiment, the standardized range of the radar chart is set to [0,10]. The normal range of the health indicator is transformed into the standardized range through linear transformation. Then, the monitoring data of the health indicator for each patient is linearly transformed to obtain the standardized data of the health indicator for each patient. It should be noted that since there are monitoring data that are greater than the upper limit of the normal range, there are also standardized data that are greater than the upper limit of the standardized range after linear transformation.

[0053] Radar chart construction and analysis module 103:

[0054] It should be noted that after standardizing the monitoring data of multiple health indicators for patients with chronic diseases, the ability of changes in various health indicators to represent the trend of disease changes varies among patients due to differences in their conditions and symptoms. Therefore, it is necessary to perform change analysis on the standardized data of each health indicator. The greater the change in a health indicator, the more likely it is to be related to the symptoms of the corresponding chronic disease. At the same time, for patients with hypertension, diabetes, etc., whose blood pressure or blood sugar often remains at abnormally high levels, it is necessary to consider whether the value exceeds the normal range in addition to the magnitude of the change, so as to quantify the degree of disease manifestation of the health indicator, and construct radar charts for the standardized data of each health indicator based on the degree of disease manifestation.

[0055] (1) Based on the differences in the numerical performance of standardized data of different health indicators of the same patient, determine the degree of disease manifestation of each health indicator of the patient; based on the standardized data of each health indicator of the patient and the degree of disease manifestation, generate radar charts of each monitoring of the patient.

[0056] Preferably, in one embodiment of the present invention, the degree of disease manifestation of various health indicators of a patient is determined based on the differences in the numerical performance of standardized data of different health indicators of the same patient, including the following specific methods:

[0057] For any elderly patient with chronic disease, the standardized data of various health indicators are sorted chronologically to obtain standardized sequences for each health indicator. The Pearson correlation coefficient between any two standardized sequences of health indicators is obtained. The health indicator with the highest mean Pearson correlation coefficient with the standardized sequences of other health indicators is taken as the patient's normal health indicator. Then, the degree of disease manifestation γ of the i-th health indicator for this patient is determined. i The calculation method is as follows:

[0058]

[0059] Among them, c i,0 This represents the Pearson correlation coefficient between the i-th health indicator of the patient and a standardized sequence of normal health indicators, n'. i Δg represents the number of standardized data points for the i-th health indicator of the patient that are outside its standardized range, N represents the number of standardized data points for each health indicator of the patient, and Δg represents the number of standardized data points for each health indicator of the patient. i This indicates that all standardized data for the i-th health indicator of this patient are of very poor quality.

[0060] It should be noted that the chronic diseases of elderly patients do not affect all of their health indicators. The monitoring data of most health indicators remain within the normal range and fluctuate within a certain range, with relatively similar temporal relationships. However, several health indicators reflecting the severity of chronic diseases usually change frequently, leading to significant differences in their relationship with normal health indicators. At the same time, the magnitude of the changes also changes significantly, forming a large range. The health indicators reflecting the severity of chronic diseases often show corresponding monitoring data that exceed the normal range. The more monitoring data that exceed the range, the more correlated it is with the corresponding chronic disease, and the greater the degree of the corresponding disease manifestation.

[0061] Preferably, in one embodiment of the present invention, a radar chart of each monitoring session of the patient is generated based on standardized data of various health indicators of the patient and the degree of manifestation of their condition. The specific method includes:

[0062] For any elderly patient with chronic disease, the degree of disease manifestation of all health indicators is linearly normalized, and the result is used as the adjustment range for each health indicator.

[0063] It should be further noted that the standardized range of each health indicator is the same, which is set to [0,10] in this embodiment. The radar chart is constructed based on the standardized range, and the adjustment range is based on the degree of disease manifestation, which requires expanding the range of the radar chart to more intuitively discover the standardized data changes of the corresponding health indicators.

[0064] Specifically, for any health indicator of the patient, the sum obtained by adding 1 to the adjustment range, the product of the product with the upper limit of the standardized range and rounded up, is used as the upper limit of the radar chart data range of that health indicator, and the lower limit of the standardized range is directly used as the lower limit of the radar chart data range, thus obtaining the radar chart data range of that health indicator.

[0065] Furthermore, the radar chart data range of various health indicators of the patient is obtained, and a radar chart of the patient is constructed based on this. Combined with the standardized data of various health indicators of the patient under each monitoring, radar charts of the patient under each monitoring are generated.

[0066] (2) Based on the differences in radar charts between adjacent monitoring sessions for the same patient, as well as the trend of radar chart changes in consecutive monitoring sessions, and combined with the degree of disease manifestation of various health indicators of the patient, determine the degree of intervention for each monitoring session; based on the degree of intervention and the radar chart performance of the corresponding monitoring sessions, obtain the degree of medication adjustment for the patient, and thus obtain the degree of change in the patient's condition.

[0067] It should be noted that during the continuous monitoring of health indicators for elderly patients with chronic diseases, there is a process of treatment intervention by the hospital. The relevant data of health indicator monitoring during the treatment process are shared and synchronized in the patient's chronic disease record. Each monitoring will cause the standardized data of the corresponding health indicator to change, no longer meeting the patient's past disease trend. Therefore, this is used to analyze the degree of intervention of treatment for the patient in each monitoring. At the same time, under the premise of intervention, based on the data performance and changes of various health indicators in the radar chart, the effect of the intervention is quantified, and the trend of the patient's disease is further analyzed to provide health management suggestions based on the patient's radar chart.

[0068] Preferably, in one embodiment of the present invention, the degree of intervention for each monitoring session is determined by considering the differences in radar charts from adjacent monitoring sessions for the same patient, as well as the changing trends of radar charts from consecutive monitoring sessions, combined with the degree of disease manifestation of various health indicators of the patient. The specific method includes:

[0069] For any elderly patient with chronic disease, the radar chart generated during the j-th monitoring session is combined with the radar chart generated during the preceding monitoring session to obtain the degree of change δ of the radar chart during the j-th monitoring session. j The calculation method is as follows:

[0070]

[0071] Where I represents the number of health indicators monitored, γ i Δg represents the degree of disease manifestation of the i-th health indicator for the patient. i (j,j-1) represents the absolute value of the difference between the standardized data of the i-th health indicator of the patient in the j-th and j-1-th monitoring sessions, g max The upper limit of the standardization range is represented by , and softmax() represents the weight normalization function. The normalization object is the degree to which the patient's various health indicators reflect the severity of the disease.

[0072] It should be noted that the differences in various health indicators between two adjacent monitoring radar charts can comprehensively reflect the degree of change in the radar chart. The degree of disease manifestation limits the differences in changes in various health indicators. The greater the degree of disease manifestation, the better it reflects the condition of chronic diseases. Accordingly, the data changes are more important for quantifying the changes in the radar chart, thereby obtaining the degree of change in the radar chart.

[0073] Furthermore, the radar chart change rate of the elderly patient with chronic disease is obtained for each monitoring session using the method described above. An analysis range is preset. In this embodiment, the analysis range is described as 5. The five monitoring sessions preceding any given monitoring session are taken as the analysis range for that monitoring session. It should be noted that the radar chart change rate is set to 0 for the first monitoring session since there are no other monitoring sessions before it. If the number of monitoring sessions before that monitoring session is less than the analysis range, the existing monitoring sessions and their radar chart change rates are used to construct the analysis range.

[0074] Furthermore, obtain the intervention level β of the patient during the j-th monitoring. j The calculation method is as follows:

[0075]

[0076] in, This indicates the number of monitoring sessions within the analysis range for the j-th monitoring session of this patient. δ represents the mean value of the change in radar chart values ​​for the patient up to the j-th monitoring session. j This indicates the degree of change in the radar chart during the j-th monitoring of the patient, δ j，m This represents the degree of change in the radar chart of the m-th monitoring within the analysis range of the j-th monitoring of the patient, where || represents the absolute value function.

[0077] It should be noted that, within the scope of the analysis, the greater the difference between the degree of change in the radar chart of a particular monitoring session and the degree of change in the radar chart of another monitoring session, the greater the likelihood of intervention. Since the changes in the condition of chronic diseases in the elderly are slow, sudden changes are more likely to be caused by hospital treatment interventions. At the same time, treatment interventions cause the standardized data of health indicators reflecting the condition to fall back from high or out-of-range to the standardized range. Therefore, the degree of change in the radar chart under intervention is negative, while normal changes in the condition will make the radar chart change appear as a small positive value. Therefore, the greater the degree of intervention obtained after absolute value, the more likely it is that the hospital has treated the patient, resulting in a large change in the radar chart.

[0078] Preferably, in one embodiment of the present invention, the degree of medication adjustment for the patient is obtained based on the degree of intervention and the corresponding radar chart performance, thereby obtaining the degree of change in the patient's condition. The specific method includes:

[0079] It should be noted that for the corresponding monitoring that has undergone treatment intervention, it is necessary to predict the monitoring based on the radar charts of previous monitoring in the analysis range to obtain the radar chart under no treatment intervention. Then, the intervention effect is quantified by combining the actual radar chart. The maximum value among multiple treatment interventions is used as the degree of medication adjustment for the patient, that is, the intervention effect calculated by eliminating the normal changes in the condition under non-treatment intervention, which does not actually exist.

[0080] Specifically, for the j-th monitoring of any elderly patient with chronic disease, the analysis range includes multiple previous monitoring sessions. Using the least squares method, a linear fit is performed on the standardized data of multiple monitoring sessions of any health indicator in the radar chart within the analysis range, and the standardized predicted value of that health indicator in the j-th monitoring is predicted. The least squares method for linear fitting and prediction is a well-known technique, and will not be elaborated on in this embodiment. Based on the standardized predicted values ​​of each health indicator in the j-th monitoring, a radar chart is generated as the predicted radar chart for the j-th monitoring.

[0081] Furthermore, following the calculation method for the degree of change in the radar chart, the standardized data of each health indicator in the radar chart of the patient's (j-1)th monitoring are replaced with the standardized predicted values ​​of each health indicator in the predicted radar chart of the patient's jth monitoring. The result is then taken as the degree of intervention performance of the patient in the jth monitoring by taking the absolute value. The maximum value of the degree of intervention performance of the patient in all monitoring is taken as the degree of medication adjustment for the patient.

[0082] It should be further explained that each treatment intervention resulted in a significant change in the radar chart, and also demonstrated a certain degree of intervention. By segmenting the treatment intervention, the mean value of the radar chart change in each segment was calculated. Based on the mean values ​​of each consecutive segment, the overall trend of the radar chart change was analyzed to reflect the degree of change in the patient's condition.

[0083] K-means clustering was performed on all monitoring sessions for the patient based on the intervention performance level. In this embodiment, K=2 is used for description. The distance metric is the absolute value of the difference between the intervention performance levels, resulting in two clusters. Several monitoring sessions in the cluster with the largest mean intervention performance level were selected as the corresponding monitoring sessions for the treatment intervention and used as segmentation points to segment all monitoring sessions for the patient. Other monitoring data were obtained from regular community monitoring of multiple health indicators of the patient. The corresponding monitoring session for the treatment intervention used the segmentation point as the first monitoring session in each segment. It should be noted that the segmentation is constructed up to the current monitoring session, that is, the last monitoring session of the last segment is the most recent monitoring session.

[0084] Furthermore, for any segment, the mean value of the radar chart change in that segment, excluding the first monitoring (i.e., the corresponding monitoring for treatment intervention), is obtained as the overall radar chart change in that segment. The overall radar chart change in all segments is arranged in chronological order, and a coordinate system is constructed with the overall radar chart change as the vertical axis and the number of regular monitoring sessions as the horizontal axis. The median value of each segment, corresponding to the number of monitoring sessions and the radar chart change, is mapped onto the coordinate system to obtain several data points. The least squares method is used to fit a straight line to all data points to obtain the fitting slope, which is used as the degree of change in the patient's condition.

[0085] It should be noted that the overall change in the radar chart reflects the changes in the condition after each treatment intervention. The overall change in the condition after consecutive treatment interventions can reflect the development of the patient's condition, and this can be used as the degree of change in the condition for subsequent judgment.

[0086] Thus, by analyzing the standardized data changes and numerical performance of different health indicators of the same patient, the significant changes are used to reflect the patient's condition. The radar chart generation process is further adjusted to ensure that the radar chart intuitively reflects the patient's condition. Based on the changes in the radar chart, combined with the changes in the patient's health indicators under treatment intervention, the degree of hospital intervention under the corresponding monitoring is analyzed, and the intervention effect is further quantified. At the same time, by eliminating the influence of the intervention effect, the changes in the patient's condition are analyzed to accurately monitor the changes in the condition of patients with chronic diseases.

[0087] Health Management Module 104: Based on the degree of change in the patient's condition and the degree of medication adjustment, obtain health management suggestions for the patient.

[0088] Specifically, for any elderly patient with chronic disease, if the degree of medication adjustment as of the most recent monitoring is greater than the degree of disease change, the patient's disease has not yet deteriorated beyond control, and the existing regular monitoring and treatment intervention should be maintained; if the degree of medication adjustment is less than or equal to the degree of disease change, the patient's treatment intervention is no longer able to effectively curb the disease progression, and timely hospitalization for treatment of the corresponding symptoms is required.

[0089] Thus, by continuously monitoring multiple health indicators of a large number of elderly patients with chronic diseases, and through data standardization and quantification of the degree of disease manifestation of each health indicator, a radar chart that can intuitively reflect the changes in patients' conditions is constructed. By observing the trends in the radar chart and the changes in multiple health indicators after hospital treatment and intervention, the effectiveness of the intervention and the changes in patients' conditions are quantified, thereby providing health management suggestions and realizing intelligent community-assisted health management for elderly patients with chronic diseases, reducing the probability of chronic disease onset in the target population.

[0090] Data sharing module 105: Shares radar charts generated from each patient monitoring session between the hospital and the community, and the hospital promptly shares the patient's health management recommendations with the community after obtaining them.

[0091] Specifically, when the community monitors multiple health indicators of elderly patients with chronic diseases regularly, the monitoring data is uploaded to the patient's corresponding chronic disease record. The chronic disease record is then synchronized to the hospital through data sharing. After treatment intervention, the hospital needs to analyze the degree of change in the patient's condition and obtain health management suggestions for the patient, which are then synchronized back to the community to achieve data sharing.

[0092] This concludes the embodiment.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A radar chart-based intelligent community health management system for elderly patients with chronic diseases, characterized in that, The system comprises: a data acquisition module configured to periodically acquire monitoring data of multiple health indicators of an elderly patient with chronic diseases; a data standardization module configured to standardize the monitoring data of the same health indicators of a large number of patients to obtain standardized data of the health indicators of the patient; a radar chart construction and analysis module configured to determine a disease manifestation degree of each health indicator of the patient according to the numerical difference of the standardized data of the different health indicators of the same patient, generate a radar chart of each monitoring of the patient based on the standardized data of the health indicators of the patient and the disease manifestation degree of the health indicators of the patient; determine an intervention degree of each monitoring of the patient according to the difference of the radar charts of the adjacent monitoring of the same patient and the change trend of the radar charts of the continuous monitoring of the patient, in combination with the disease manifestation degree of the health indicators of the patient; acquire a medication adjustment degree of the patient according to the intervention degree and the radar chart of the corresponding monitoring, and further obtain a disease change degree of the patient; a health management module configured to acquire a health management suggestion for the patient based on the disease change degree and the medication adjustment degree of the patient; a data sharing module configured to share the radar charts generated by each monitoring of the patient between a hospital and a community, and share the health management suggestion for the patient from the hospital to the community in time after the health management suggestion is acquired. 2.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 1, wherein, The method for standardizing the monitoring data of the same health indicators of a large number of patients to obtain the standardized data of the health indicators of the patient comprises the following steps: for any health indicator, acquiring a normal range of the monitoring data of the health indicator; and acquiring a standardization range of the radar chart; linearly transforming the normal range of the health indicator into the standardization range, and then linearly transforming the monitoring data of the health indicator of each patient to obtain the standardized data of the health indicator of each patient. 3.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 2, wherein, The method for obtaining the disease manifestation degree of the health indicators of the patient comprises the following steps: for any elderly patient with chronic diseases, sorting the standardized data of the health indicators of the patient in time sequence to obtain a standardized sequence of each health indicator; acquiring a Pearson correlation coefficient between any two standardized sequences of the health indicators; and selecting the corresponding health indicator with the maximum mean value of the Pearson correlation coefficients between the standardized sequences of the other health indicators as the normal health indicator of the patient; obtaining the disease manifestation degree of the health indicators of the patient based on the standardized sequences of the health indicators of the patient and the distribution of the numerical values of the standardized data in the standardization range. 4.The radar chart-based intelligent community health management system for elderly patients with chronic diseases according to claim 3, characterized in that, The method for generating the radar chart of each monitoring of the patient comprises the following steps: wherein γ i represents the degree of illness of the i-th health indicator of any elderly patient with chronic diseases, c i,0 represents the Pearson correlation coefficient between the i-th health indicator of the patient and the standardized sequence of the normal health indicator, n i represents the number of standardized data of the i-th health indicator of the patient that is not within the standardized range, N represents the number of standardized data of each health indicator of the patient, Δg i represents the range of all standardized data of the i-th health indicator of the patient. 5.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 2, wherein, linearly normalizing the disease manifestation degrees of all the health indicators of any elderly patient with chronic diseases to obtain an adjustment amplitude of each health indicator as the result. ​ For any one health indicator of the patient, a sum of 1 and a product of the adjustment range and an upper limit of the standardized range is taken as an upper limit of the radar chart data range of the health indicator, and a lower limit of the standardized range is directly taken as a lower limit of the radar chart data range, to obtain the radar chart data range of the health indicator; The radar chart data ranges of the health indicators of the patient are obtained, and a radar chart of the patient is constructed based on the radar chart data ranges, and the standardized data of the health indicators of the patient in each monitoring are combined to generate the radar charts of the patient in each monitoring. 6.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 2, wherein, The specific method for determining the intervention degree of the patient in each monitoring includes: The specific method for obtaining the radar chart change degree of the patient in each monitoring includes: Obtaining the analysis range of the jth monitoring of any elderly patient with chronic diseases, the intervention degree β of the jth monitoring of the patient j The calculation method is: wherein, represents the number of monitoring times in the analysis range of the jth monitoring of the patient, represents the average of radar chart variation degrees of all monitoring times before the jth monitoring of the patient, δ j represents the radar chart variation degree of the jth monitoring of the patient, δ j,m represents the radar chart variation degree of the mth monitoring in the analysis range of the jth monitoring of the patient, || represents the absolute value function. 7.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 6, wherein, The specific method for obtaining the medication adjustment degree of the patient includes: wherein, δ j represents the radar chart change degree of the jth monitoring of any elderly patient with chronic diseases, I represents the number of health indicators monitored, γ i represents the condition embodiment degree of the ith health indicator of the patient, Δ gi (j, j-1) represents the absolute value of the difference between the standardized data of the ith health indicator of the patient at the jth monitoring and the (j-1)th monitoring, g max represents the upper limit of the standardized range, and softmax() represents a weight normalization function. 8.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 7, wherein, For the jth monitoring of any one elderly patient with a chronic disease, the standardized prediction values of the health indicators in the jth monitoring are obtained by fitting prediction according to the analysis range, and a radar chart is generated as the prediction radar chart of the jth monitoring; The radar chart change degree of the patient in the jth monitoring is calculated, the standardized data of the health indicators in the jth monitoring are replaced by the standardized prediction values of the health indicators in the prediction radar chart of the jth monitoring, and the result is taken as the intervention performance degree of the patient in the jth monitoring by taking the absolute value. The maximum value of the intervention performance degrees of the patient in all the monitoring is taken as the medication adjustment degree of the patient. The specific method for obtaining the disease change degree of the patient includes: 9.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 8, wherein, The intervention performance degrees of the patient in all the monitoring are clustered to obtain two clusters, and the cluster with the maximum mean intervention performance degree is taken as the corresponding monitoring of the therapeutic intervention and as a segmentation point, and all the monitoring of the patient is segmented; For any one segment, the mean value of the radar chart change degrees of the monitoring other than the first monitoring in the segment is taken as the overall radar chart change degree of the segment, the overall radar chart change degrees of all the segments are arranged in chronological order, a straight line is fitted by the least square method, a fitting slope is obtained, and the fitting slope is taken as the disease change degree of the patient. The specific method for obtaining the health management suggestion of the patient includes: 10.The radar chart based intelligent community health management system for elderly patients with chronic diseases according to claim 1, wherein, For any one elderly patient with a chronic disease, if the medication adjustment degree obtained by the patient until the latest monitoring is greater than the disease change degree, the existing regular continuous monitoring and regular therapeutic intervention are maintained; if the medication adjustment degree is less than or equal to the disease change degree, the patient is timely hospitalized for treatment. ​

Images