Old people asthenia phenotype evaluation and nursing plan making method and device and medium

Abstract

The invention discloses an old people asthenia phenotype evaluation and nursing plan making method and device and a medium, and relates to the field of asthenia evaluation.The method comprises the steps that physiological health data, psychological state data and social interaction data of old people to be evaluated are collected, key features are extracted, and a plurality of key indexes are obtained; generating a weakness phenotype evaluation report (including a physiological evaluation result, a psychological evaluation result and a social interaction evaluation result) of the to-be-evaluated old people according to the plurality of key indexes; generating a nursing plan (including medical suggestion measures, psychological support suggestion measures and social activity suggestion measures) of the to-be-assessed old people according to the weakness phenotype assessment report; and nursing the to-be-evaluated old people based on the nursing plan, collecting health feedback data according to a set period, and optimizing and adjusting the nursing plan according to the health feedback data. According to the method and the device, the efficiency and the precision of asthenia phenotype evaluation of the elderly are improved, the personalized nursing plan is generated, and the nursing effect of the elderly is improved.

Description

Technical Field

[0001] The present application relates to the field of frailty assessment, and in particular to a method, device and medium for assessing frailty phenotypes and formulating care plans for the elderly. Background Art

[0002] Globally, frailty in the elderly has become an important factor affecting their health and quality of life. Frailty is usually manifested as a decline in the physiological functions of multiple systems, including weakened muscle strength, slower walking speed, and reduced physical activity. These problems not only seriously affect the self-care ability of the elderly, but also increase medical and nursing costs. With the aging of society, the problem of frailty in the elderly is becoming increasingly serious. There is an urgent need for an efficient and accurate assessment method to timely identify and intervene in the frail state and improve the quality of life of the elderly.

[0003] Existing methods for assessing frailty in the elderly mainly include physiological assessment, psychological assessment and comprehensive assessment. Among them, the physiological assessment method uses physiological indicators (such as grip strength, walking speed, body mass index, etc.) for assessment. Although this method is intuitive, it can only reflect some characteristics of frailty and lacks comprehensiveness; the psychological assessment method uses psychological scales (such as the Geriatric Depression Scale) to assess the psychological state of the elderly. Although psychological factors play an important role in the frail state, a single psychological assessment cannot fully reflect the overall health status of the elderly and cannot provide a comprehensive health status assessment. It lacks automation and data integration capabilities, and the assessment efficiency and accuracy are not high; the comprehensive assessment method (such as the Fried frailty phenotype model and the Rockwood cumulative score model) combines physiological, psychological and social factors for comprehensive assessment, and can assess the frail state of the elderly from multiple dimensions, but it usually relies on manual operation and subjective judgment. The assessment process is time-consuming and error-prone, lacks standardized and automated means, and is difficult to meet the needs of large-scale applications.

[0004] In summary, although existing technologies have made some progress in the assessment of frailty in the elderly, there are still several major problems:

[0005] (1) Low assessment efficiency: Traditional assessment methods mostly rely on manual operation and record-keeping, which is time-consuming and prone to human errors, and cannot meet the needs of rapid assessment of large elderly populations.

[0006] (2) Low assessment accuracy: Single-dimensional assessment methods cannot fully reflect the health status of the elderly. Although comprehensive assessments are more comprehensive, they are not highly standardized, which affects the accuracy and reliability of the assessment results.

[0007] (3) Lack of personalization: Existing care plans are unable to provide personalized care plans based on individual differences, which affects the improvement of the quality of life of the elderly.

[0008] (4) Lack of continuous feedback and optimization: Existing assessment and care programs lack continuous feedback and optimization mechanisms and are unable to dynamically adapt to changes in the health status of the elderly, resulting in poor care outcomes. Summary of the invention

[0009] The purpose of this application is to provide a method, device and medium for assessing the frailty phenotype and formulating care plans for the elderly, which can improve the efficiency and accuracy of the frailty phenotype assessment for the elderly, generate personalized care plans, and improve the care effect of the elderly.

[0010] To achieve the above objectives, this application provides the following solutions:

[0011] In the first aspect, the present application provides a method for assessing frailty phenotypes and formulating care plans for the elderly, comprising:

[0012] Collecting health data of the elderly to be evaluated to obtain a health data set; the health data includes physiological health data, psychological state data, and social interaction data;

[0013] Using a machine learning algorithm to extract key features from the health data set to obtain multiple key indicators;

[0014] Generating a frailty phenotype assessment report for the elderly to be assessed based on a plurality of key indicators; the frailty phenotype assessment report includes physiological assessment results, psychological assessment results, and social interaction assessment results;

[0015] Generate a care plan for the elderly to be evaluated using a machine learning algorithm based on the frailty phenotype assessment report; the care plan includes medical advice measures, psychological support advice measures, and social activity advice measures;

[0016] Based on the care plan, care is provided to the elderly to be evaluated, and during the implementation of the care, health feedback data of the elderly to be evaluated is collected according to a set period, and the care plan is optimized and adjusted according to the health feedback data.

[0017] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for assessing the frailty phenotype of the elderly and formulating a care plan.

[0018] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for assessing the frailty phenotype of the elderly and formulating a care plan.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0020] The present application provides a method, device and medium for assessing the frailty phenotype and formulating a care plan for the elderly. A frailty phenotype assessment report for the elderly to be assessed is generated based on the physiological health data, psychological state data and social interaction data of the elderly to be assessed. Data in three dimensions, namely physiological, psychological and social interaction, are taken into account, thereby improving the accuracy of the frailty phenotype assessment. In addition, the entire assessment process is completely automatic, without the need for manual operation and record-keeping, thereby improving the efficiency of the frailty phenotype assessment. Further, a personalized care plan suitable for the elderly to be assessed is generated based on the frailty phenotype assessment report of the elderly to be assessed. During the implementation of the care plan, the care plan is continuously adjusted based on the health feedback data, thereby improving the personalization of the care plan and thereby improving the care effect of the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is an application environment diagram of a method for assessing frailty phenotypes and formulating care plans for the elderly in one embodiment of the present application;

[0023] Figure 2 A flowchart of a method for assessing frailty phenotypes and formulating care plans for the elderly provided in one embodiment of the present application;

[0024] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0027] The method for evaluating the frailty phenotype of the elderly and formulating a care plan provided in the embodiments of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, or it can be integrated on the server 104, or it can be placed on the cloud or other servers. The terminal 102 can send the health data of the elderly to be evaluated to the server 104, and the server 104 receives the health data of the elderly to be evaluated, performs a frail phenotype assessment on the elderly to be evaluated and generates a care plan. The server 104 can feedback the obtained frail phenotype assessment report and care plan to the terminal 102. In addition, in some embodiments, the elderly frailty phenotype assessment and care plan formulation method can also be implemented separately by the server 104 or the terminal 102.

[0028] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0029] In an exemplary embodiment, Figure 2 As shown, a method for assessing the frailty phenotype of the elderly and formulating a care plan is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 205.

[0030] Step 201, collect health data of the elderly to be evaluated to obtain a health data set. The health data includes physiological health data, psychological state data and social interaction data.

[0031] In a specific example, the execution subject of step 201 is a data acquisition device and a computer.

[0032] Specifically, the initial physiological health data of the elderly to be evaluated is collected through physiological measurement instruments and activity tracking devices. Among them, the physiological measurement instruments include blood pressure monitors, blood glucose meters, electrocardiographs, etc. The activity tracking devices are wearable sensors. The initial physiological health data include blood pressure, blood glucose, electrocardiogram, etc.

[0033] The psychological state of the elderly to be evaluated is assessed using standardized psychological assessment tools (such as the Geriatric Depression Scale) to obtain the initial psychological state data of the elderly to be evaluated.

[0034] The social participation and support network data of the elderly to be evaluated are obtained through questionnaires or interviews, and the initial social interaction data of the elderly to be evaluated are obtained.

[0035] The initial psychological state data and initial social interaction data are entered into the computer by the nursing staff, and the physiological measurement instruments and activity tracking devices transmit the initial physiological health data to the central database through wireless or wired connections and store them in the computer to ensure the accuracy and completeness of the data.

[0036] Furthermore, the collection of physiological health data and psychological status data needs to be standardized to ensure the reliability of the data.

[0037] The initial physiological health data, the initial psychological state data and the initial social interaction data are then subjected to removal of duplicate values, removal of outliers, normalization, standardization and missing value processing in turn to obtain the physiological health data, psychological state data and social interaction data of the elderly to be evaluated.

[0038] This application first pre-processes all health data uniformly, and then pre-processes the pre-processed physiological health data, psychological state data, and social interaction data separately to ensure the quality of the health data.

[0039] The following is a detailed introduction to the processes of removing duplicate values, removing outliers, normalization, standardization and missing value processing.

[0040] (1) Removing duplicate values: Use database management software (such as MySQL, PostgreSQL) or data processing tools (such as Python's Pandas library) in the computer to detect and delete duplicate records in the initial data set (including initial physiological health data, initial psychological state data, and initial social interaction data). This is achieved by using the DELETE statement of the Structured Query Language (SQL) combined with DISTINCT or the drop_duplicates method of the Pandas library.

[0041] (2) Remove outliers: Identify outliers by calculating the statistical value of each data (such as mean, standard deviation), and process them (such as delete or replace) according to actual needs. Specifically, use statistical analysis tools (such as Python's Scipy library) to calculate the z score and delete data with an absolute value greater than the z score.

[0042] (3) Normalization: Convert the data to a uniform dimension range (usually between 0 and 1) to eliminate the dimension differences between different data. Specifically, MinMaxScaler in Python's Scikit-learn library is used for normalization.

[0043] (4) Standardization: The data is converted into a standard normal distribution with a mean of 0 and a standard deviation of 1 to ensure that the mean and variance of the data are consistent. Specifically, the StandardScaler in the Python Scikit-learn library is used for standardization.

[0044] (5) Missing value processing: Use data processing tools (such as Python's Pandas library) to detect the location and number of missing values ​​in the data set. Process missing values ​​according to actual needs (such as deleting records containing missing values, replacing missing values ​​with the mean or median). Specifically, use the dropna' method of the Pandas library to delete missing values, or use the fillna method to fill them.

[0045] This application stores health datasets in a structured database for subsequent analysis.

[0046] Step 202: extract key features from the health data set using a machine learning algorithm to obtain multiple key indicators.

[0047] Specifically, step 202 includes steps 301 to 303 .

[0048] Step 301, performing dimensionality reduction processing on the health data set to obtain a low-dimensional health data set.

[0049] In a specific example, the principal component analysis method (PCA) is used to reduce the dimension of the health data set. PCA is a dimensionality reduction technique used to convert high-dimensional data into low-dimensional data while retaining the main information of the data as much as possible. PCA projects the original data into a new orthogonal coordinate system through linear transformation, so that the variance of the projected data on the first principal component is the largest, the variance on the second principal component is the second, and so on. In the process of assessing the frail status of the elderly, PCA can be used to reduce the dimension of the data and extract the main features that best reflect the frail status of the elderly.

[0050] Specifically, the covariance matrix of the health data set is first calculated to represent the covariance between the health data. Then the covariance matrix is ​​decomposed to obtain the eigenvalues ​​and eigenvectors. The principal components are selected according to the size of the eigenvalues ​​(such as retaining the first few principal components with 95% variance). Finally, the health data in the health data set are projected into the new coordinate system composed of the principal components to obtain the reduced dimensionality data, that is, the low-dimensional health data set.

[0051] Step 302: cluster analysis is performed on the low-dimensional health data set to determine the frailty status category of each health data in the low-dimensional health data set. Specifically, the frailty status category includes pre-frailty, primary frailty, secondary frailty, and the like.

[0052] Cluster analysis is an unsupervised learning algorithm that is used to divide a data set into multiple non-intersecting clusters, so that the data points in the same cluster have high similarity and the data points in different clusters have low similarity. Commonly used clustering algorithms include K-means, hierarchical clustering, etc. In the assessment of frailty status in the elderly, cluster analysis can be used to identify different frailty status categories in the elderly population and provide specific health management recommendations for each category.

[0053] In a specific example, a K-means clustering algorithm is used to perform cluster analysis on the low-dimensional health data set. Specifically, the optimal number of clusters is determined by methods such as the elbow method or the silhouette coefficient. The K-means model is trained using the optimal number of clusters, the data is divided into K clusters, the center of each cluster is analyzed, and the characteristics of each cluster are understood to identify different frailty status categories.

[0054] This application further evaluates the K-means model to ensure the classification effect. Specifically, the data is divided into a training set and a test set, and the performance of the K-means model is evaluated using a cross-validation method. Indicators such as accuracy, precision, recall, and F1 score are calculated to evaluate the classification effect of the K-means model.

[0055] Step 303, for any frail status category, a multivariate statistical analysis method is used to determine the key indicators of the frail status category according to the health data corresponding to the frail status category, so as to obtain a plurality of key indicators.

[0056] This application uses multivariate statistical analysis methods to further analyze the clustered health data and identify key indicators related to the frailty phenotype.

[0057] In a specific example, the multivariate statistical analysis method is a logistic regression method or a linear regression method.

[0058] If the logistic regression method is used, the data set is first divided into a training set and a test set to evaluate the generalization ability of the logistic regression model. The training set is used to train the logistic regression model, and the test set data is used to evaluate the performance of the logistic regression model, and indicators such as accuracy, precision, recall, and F1 score are calculated. The regression coefficient and significance level of the logistic regression model are extracted to identify variables that have a significant impact on frailty status.

[0059] If the linear regression method is used, the data set is first divided into a training set and a test set to evaluate the generalization ability of the linear regression model. The linear regression model is trained using the training set data. The prediction performance of the linear regression model is evaluated using the test set data, and indicators such as the mean square error and the coefficient of determination are calculated. The regression coefficient and significance level of the linear regression model are extracted to identify the variables that have a significant impact on the frailty state.

[0060] This application verifies the relevance of extracted features through multivariate statistical analysis to ensure the scientific nature of the evaluation results.

[0061] Step 203: Generate a frailty phenotype assessment report of the elderly person to be assessed based on multiple key indicators. The frailty phenotype assessment report includes physiological assessment results, psychological assessment results, and social interaction assessment results.

[0062] Specifically, first, all the data involved in step 201 and step 202 are integrated, including the analysis results of multiple dimensions such as physiology, psychology and social interaction. Specifically, the Pandas library of Python is used to merge data from different sources into a data frame to ensure the integrity and consistency of the data. Then, a frailty phenotype assessment report is generated based on the integrated data, and the frailty phenotype assessment report includes detailed analysis results and key indicators of each dimension. Specifically, Python report generation tools such as ReportLab, Jinja2, etc. are used to automatically generate an assessment report in PDF format. Then the key indicators are visualized and charts are generated to display the assessment results of the frail status of the elderly in an intuitive way. Specifically, Python's Matplotlib or Seaborn library is used to generate charts of key indicators of physiological health, charts of key indicators of psychological status, and charts of key indicators of social interaction, and the ReportLab library is used to embed the charts into the frailty phenotype assessment report to ensure that the content of the frailty phenotype assessment report is clear and comprehensive, and can intuitively reflect the health status and frailty phenotype of the elderly to be assessed.

[0063] Step 204: Generate a care plan for the elderly person to be evaluated using a machine learning algorithm based on the frailty phenotype assessment report. The care plan includes medical advice measures, psychological support advice measures, and social activity advice measures.

[0064] Specifically, according to the frailty phenotype assessment report, a decision tree model is used to generate a care plan for the elderly to be assessed. The decision tree model is pre-trained using a training sample set, and the training sample set includes multiple sample assessment reports and a care plan corresponding to each sample assessment report.

[0065] The input data of the decision tree model are the key indicators of each frailty status category, and the output data of the decision tree model are the care plans. During training, the care plans in the training sample set are manually determined, and the care plans consider information such as medical history and key indicators to determine medical measures.

[0066] In a specific example, the frailty phenotype assessment report is first imported into a computer as input data for the development of a personalized advance medical care plan. Specifically, Python is used to read the data in the frailty phenotype assessment report and store it in a data frame. Then, specific measures in terms of medical treatment, psychological support, and social participation are generated based on the data in the frailty phenotype assessment report. Specifically, a decision tree algorithm is used to generate a personalized care plan based on the assessment results, and a rule engine or template generation tool is used to automatically generate a detailed care plan text.

[0067] Examples of what a care plan might look like:

[0068] Based on the physiological indicators of the elderly, such as blood pressure, heart rate, blood sugar, etc., corresponding medical examinations and treatments are recommended, such as adjusting drug dosages, increasing the frequency of regular physical examinations, etc.

[0069] According to the mental state of the elderly, we provide psychological counseling, emotional support, cognitive behavioral therapy and other suggestions to help them improve their emotional state and enhance their mental health.

[0070] Based on the social interaction of the elderly, it is recommended to participate in community activities, volunteer services, interest groups, etc. to enhance social interaction and improve the quality of life.

[0071] The present application can further integrate the care plan into the frailty phenotype assessment report to generate a final personalized advance medical care plan report. Specifically, a report generation tool such as ReportLab is used to embed the content of the care plan into the PDF report.

[0072] Furthermore, caregivers can adjust and optimize the care plan according to the actual situation of the elderly to be assessed to ensure its feasibility.

[0073] Step 205, providing care for the elderly to be evaluated based on the care plan, and during the implementation of the care, collecting health feedback data of the elderly to be evaluated according to a set period, and optimizing and adjusting the care plan according to the health feedback data.

[0074] Implement care plans in nursing homes or homes, regularly collect health feedback data, record care outcomes, analyze health feedback data, identify deficiencies in the care plan, and continuously optimize and adjust the care plan to ensure its effectiveness and adaptability.

[0075] First, collect health feedback data from the elderly to be evaluated after the implementation of the care plan, including data in multiple dimensions such as physiology, psychology, and social interaction. Then integrate the health feedback data with the initial health data to form a complete data set for subsequent analysis. Specifically, use Python's Pandas library to merge the health feedback data with the initial health data. Then clean, normalize, and standardize the health feedback data to ensure the quality of the data. Then use machine learning algorithms and statistical analysis methods to identify key variables in the health feedback data and analyze the implementation effect of the care plan.

[0076] In a specific example, a random forest algorithm is used to determine key variables based on the health feedback data, and a regression analysis method is used to quantify the impact of each key variable on the implementation effect of the care plan. Based on the key variables, a machine learning algorithm is used to adjust the care plan.

[0077] Specifically, the random forest algorithm is used to analyze health feedback data, identify key variables that significantly affect health status, and evaluate the effectiveness of the care plan. Regression analysis methods are used to quantify the impact of each key variable on the implementation of the care plan and identify deficiencies. Based on the analysis results, the machine learning model is optimized and specific measures in the care plan are adjusted. Specifically, the health feedback data is used to retrain the machine learning model and adjust the care plan to ensure that it is more targeted and effective. The optimized care plan is integrated into the final personalized advance medical care plan report to generate a new personalized advance medical care plan report.

[0078] This application integrates multiple dimensions such as physiological, psychological and social, and can provide a more comprehensive and scientific basis for health assessment. It uses data science and machine learning technology for data processing and analysis, which not only improves the efficiency and accuracy of frailty phenotype assessment, but also provides a scientific basis for the formulation of personalized care plans. Through the use of smart devices and computers, the assessment process can be automated and standardized, human errors can be reduced, and the quality of assessment can be improved, thereby more accurately identifying frailty characteristics and formulating personalized medical care plans.

[0079] In summary, compared with the prior art, the beneficial effects of the present application include at least the following points:

[0080] (1) Improved the efficiency of assessing the frailty phenotype of the elderly: Through automated data collection and processing, the efficiency of assessing the frailty phenotype of the elderly is improved, which saves assessment time and enables faster completion of frailty assessment of large-scale elderly populations.

[0081] (2) Improved the assessment accuracy of the frailty phenotype of the elderly: It comprehensively considers multiple dimensions such as physiology, psychology, and social interaction to provide more comprehensive and scientific health data. It avoids human errors through automated data collection and intelligent data analysis. It uses multivariate statistical analysis and machine learning technology to analyze data from multiple dimensions, which can more accurately identify and assess the frailty phenotype characteristics of the elderly. Compared with the subjectivity and limitations of traditional assessment methods, it improves the accuracy and reliability of the assessment results.

[0082] (3) Ability to provide personalized care plans: Based on the frailty phenotype assessment report and the professional adjustments of nursing staff, develop personalized advance medical care plans to ensure that care measures are more targeted and improve the quality of life and care satisfaction of the elderly.

[0083] (4) Achieve continuous optimization and feedback: Introduce a continuous feedback and optimization mechanism to regularly collect and analyze the implementation effects of the care plan, continuously optimize and adjust the care plan, ensure its dynamic adaptability and long-term effectiveness, enable the care plan to dynamically adapt to changes in the health status of the elderly, and improve the long-term effect of care.

[0084] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store health data of the elderly to be evaluated. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for evaluating the frailty phenotype of the elderly and formulating a care plan is implemented.

[0085] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0086] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0087] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0088] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0089] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0090] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0091] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0092] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for assessing frailty phenotypes and formulating care plans for the elderly, characterized in that: The method for assessing frailty phenotypes and formulating care plans for the elderly includes: Collecting health data of the elderly to be evaluated to obtain a health data set; the health data includes physiological health data, psychological state data, and social interaction data; Using a machine learning algorithm to extract key features from the health data set to obtain multiple key indicators; Generating a frailty phenotype assessment report for the elderly to be assessed based on a plurality of key indicators; the frailty phenotype assessment report includes physiological assessment results, psychological assessment results, and social interaction assessment results; Generate a care plan for the elderly to be evaluated using a machine learning algorithm based on the frailty phenotype assessment report; the care plan includes medical advice measures, psychological support advice measures, and social activity advice measures; Based on the care plan, care is provided to the elderly to be evaluated, and during the implementation of the care, health feedback data of the elderly to be evaluated is collected according to a set period, and the care plan is optimized and adjusted according to the health feedback data.

2. The method for assessing frailty phenotypes and formulating care plans for the elderly according to claim 1, characterized in that: Collect health data of the elderly to be evaluated, including: Collect initial physiological health data of the elderly to be evaluated through physiological measurement instruments and activity tracking devices; Use standardized psychological assessment tools to assess the psychological state of the elderly to be assessed, and obtain initial psychological state data of the elderly to be assessed; Obtain the social participation and support network data of the elderly to be evaluated through questionnaire surveys or interviews, and obtain the initial social interaction data of the elderly to be evaluated; The initial physiological health data, the initial psychological state data and the initial social interaction data are sequentially subjected to removal of duplicate values, removal of outliers, normalization, standardization and missing value processing to obtain the physiological health data, psychological state data and social interaction data of the elderly to be evaluated.

3. The method for assessing frailty phenotypes and formulating care plans for the elderly according to claim 1, characterized in that: A machine learning algorithm is used to extract key features from the health data set to obtain multiple key indicators, including: Performing dimensionality reduction processing on the health data set to obtain a low-dimensional health data set; Performing cluster analysis on the low-dimensional health data set to determine the frailty state category of each health data in the low-dimensional health data set; For any frail status category, a multivariate statistical analysis method is used to determine the key indicators of the frail status category according to the health data corresponding to the frail status category, so as to obtain multiple key indicators.

4. The method for assessing frailty phenotypes and formulating care plans for the elderly according to claim 3, characterized in that: The principal component analysis method is used to reduce the dimension of the health data set.

5. The method for assessing frailty phenotypes and formulating care plans for the elderly according to claim 3, characterized in that: The K-means clustering algorithm is used to perform cluster analysis on the low-dimensional health data set.

6. The method for assessing frailty phenotypes and formulating care plans for the elderly according to claim 3, characterized in that: The multivariate statistical analysis method is a logistic regression method or a linear regression method.

7. The method for assessing frailty phenotypes and formulating care plans for the elderly according to claim 1, characterized in that: Based on the frailty phenotype assessment report, a machine learning algorithm is used to generate a care plan for the elderly to be assessed, specifically including: According to the frailty phenotype assessment report, a decision tree model is used to generate a care plan for the elderly person to be assessed; the decision tree model is pre-trained using a training sample set, and the training sample set includes multiple sample assessment reports and a care plan corresponding to each sample assessment report.

8. The method for assessing frailty phenotypes and formulating care plans for the elderly according to claim 1, characterized in that: Optimizing and adjusting the care plan according to the health feedback data specifically includes: Based on the health feedback data, a random forest algorithm is used to determine key variables, and a regression analysis method is used to quantify the impact of each key variable on the implementation effect of the care plan; Based on the key variables, a machine learning algorithm is used to adjust the care plan.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for assessing the frailty phenotype and formulating a care plan for the elderly as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for assessing frailty phenotypes and formulating care plans for the elderly described in any one of claims 1-8 is implemented.

Images