Health management method with health data analysis function

Abstract

The invention provides a health management method with a health data analysis function. The health management method with the health data analysis function comprises the following steps: S1, collecting health data information of a user body through existing equipment, and establishing a personal health record according to the data information, wherein the body data information comprises but is not limited to blood pressure, heart rhythm and blood sugar; s2, the collected health data need to be cleaned, sorted and preprocessed before a personal health record is established, so that subsequent data analysis is facilitated; and S3, according to the health data of the user, performing health risk assessment by using a machine learning model and a deep learning model algorithm, and predicting possible health risks, including but not limited to cardiovascular diseases and diabetes, of the user. The health management method with the health data analysis function provided by the invention has the advantages that the accuracy and individuation level of health management can be improved, and the requirements of people on health are met.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and in particular relates to a health management method with a health data analysis function. Background Art

[0002] With the development of society and the improvement of people's living standards, people are paying more and more attention to their health. However, traditional health management methods often rely on the experience and knowledge of doctors and cannot meet people's needs for personalized and precise health management. Therefore, the present invention proposes a health management method with health data analysis function, aiming to improve the accuracy and personalization level of health management. Summary of the invention

[0003] The technical problem solved by the present invention is to provide a health management method with a health data analysis function that can improve the accuracy and personalization level of health management and meet people's needs for health.

[0004] In order to solve the above technical problems, the health management method with health data analysis function provided by the present invention comprises the following steps:

[0005] S1. Collect the user's health data information through existing equipment and establish a personal health profile based on this data information. The health data information is not limited to blood pressure, heart rate and blood sugar;

[0006] S2. The collected health data needs to be cleaned, sorted and pre-processed before establishing personal health records to facilitate subsequent data analysis;

[0007] S3. Based on the user's health data, use machine learning models and deep learning model algorithms to conduct health risk assessment and predict the user's possible health risks, including but not limited to cardiovascular disease and diabetes;

[0008] S4. Recommend personalized health management plans to users based on their health risk assessment results, including advice on diet, exercise, and daily routines;

[0009] S5. The user implements the recommended health management plan and tracks the implementation status through wearable devices and mobile application tools to record the user's health data in real time;

[0010] S6. Based on the health management plan and tracking data implemented by the user, continuously adjust and optimize the user's health management plan to improve the effect of health management.

[0011] As a further solution of the present invention, the personal health records must be converted according to relevant specifications before being stored, the format must be unified, and corresponding fields must be added to facilitate classified inquiries.

[0012] As a further solution of the present invention, the specific steps of performing health risk assessment based on the user's health data using a machine learning model and a deep learning model algorithm to predict the user's possible health risks are as follows:

[0013] (1) The collected user health data needs to be preprocessed, including data cleaning, missing value filling, outlier processing, and data standardization steps, in order to facilitate subsequent feature engineering and model training;

[0014] (2) Extract features related to health risks from the preprocessed data, such as age, gender, weight, heart rate, blood pressure, blood sugar, blood lipid physiological indicators, as well as information on diet, exercise, and daily routine. In addition, you can also consider using time series analysis methods to convert users' historical health data into useful features;

[0015] (3) Select appropriate machine learning models or deep learning models, such as logistic regression and neural networks, based on the problem context and data characteristics. Next, use the preprocessed data and extracted features to train the model and adjust the model parameters to optimize model performance.

[0016] (4) Apply the trained model to an independent test data set to evaluate the model’s predictive performance. Common evaluation metrics include accuracy, precision, recall, and F1 score. In addition, cross-validation can be performed to avoid overfitting and underfitting problems.

[0017] (5) Based on the model prediction results, the system outputs possible health risks to users, such as cardiovascular disease, diabetes, and hypertension, and provides corresponding suggestions and measures to help users reduce health risks;

[0018] (6) Continuously adjust and optimize the model based on the health management plan and tracking data implemented by the user to improve the accuracy and personalization of health risk assessment.

[0019] As a further solution of the present invention, the machine learning model and the deep learning model also include the following:

[0020] (1) Data cleaning, i.e. detecting and deleting duplicate and incomplete data, and then filling missing values. The methods include mean filling, median filling and mode filling;

[0021] (2) Outlier processing: detect and remove outliers through box plots, and then perform data standardization to map features of different scales to the same scale;

[0022] (3) Extract features related to health risks from the preprocessed data, such as age, gender, weight, heart rate, blood pressure, blood sugar and blood lipid physiological indicators, as well as information on diet, exercise and daily routine. In addition, time series analysis methods can be used to convert users' historical health data into useful features.

[0023] As a further solution of the present invention, the logistic regression calculation formula in the machine learning model is as follows:

[0024] P(Y=1|X)=\frac{1}{1+e^{-(\beta_0+\beta_1X_1+\beta_2X_2+\dots+\beta_n X_n)}}

[0025] Where: P(Y=1|X) is the probability that the target variable YY is 1 given the feature vector XX;

[0026] \beta_0, \beta_1, \dots, \beta_n are model parameters;

[0027] X_1, X_2, \dots, X_n are the features in the feature vector.

[0028] As a further solution of the present invention, the neural network formula in the deep learning model is as follows:

[0029]

[0030] Among them, O i，j，k，l is the value of position (i, j, k, l) in the output feature map;

[0031] I i+m，j+n，k+o，l+p is the value of position (i+m, j+n, k+o, l+p) in the input feature map;

[0032] W m，n，o，p are the parameters of the convolution kernel;

[0033] b is the bias term;

[0034] is an activation function, such as ReLU, Sigmoid.

[0035] As a further solution of the present invention, the method steps for recommending a personalized health management plan to a user based on the health risk assessment result of the user are as follows:

[0036] (1) Conduct a detailed analysis of the assessment results to identify the user's health risks, such as high blood lipids, high blood pressure and diabetes, and understand the user's personal situation, such as living habits, eating habits and exercise habits;

[0037] (2) Based on the assessment results and the user’s personal situation, formulate overall health management goals, such as lowering blood pressure, reducing weight and improving immunity.

[0038] As a further solution of the present invention, the health management solution includes the following solutions:

[0039] (1) Dietary recommendations: Develop a reasonable diet plan based on the user's eating habits and health conditions. For example, for patients with hyperlipidemia, it is recommended to reduce the intake of saturated fat and trans fat and increase the intake of vegetables and fruits. For patients with diabetes, it is recommended to control the total calorie intake and choose foods with a low glycemic index;

[0040] (2) Exercise plan: Develop a suitable exercise plan based on the user's exercise habits and health conditions. For example, for obese people, it is recommended to increase aerobic exercise and strength training to achieve the goal of weight loss; for patients with hypertension, it is recommended to do moderate aerobic exercise, such as walking and jogging, to lower blood pressure;

[0041] (3) Lifestyle adjustment: It is recommended that users adjust their work and rest schedules, ensure adequate sleep, learn to reduce stress and relax, avoid excessive stress and anxiety, and quit smoking and limit alcohol consumption.

[0042] As a further solution of the present invention, the health management program also includes providing continuous motivation and support to users, such as encouragement, rewards, and health education, to help users adhere to the health management program and gradually achieve health goals.

[0043] As a further solution of the present invention, the health management plan also includes using health monitoring devices (such as smart bracelets, blood pressure monitors) and user self-reporting methods to track the user's health data, evaluate the implementation of the health management plan, and adjust the plan in a timely manner based on the tracking results to make it more in line with the user's actual situation.

[0044] Compared with the related art, the health management method with health data analysis function provided by the present invention has the following beneficial effects:

[0045] 1. The present invention recommends personalized health management plans to users based on their health data to meet the needs of different users;

[0046] 2. The present invention uses machine learning models, deep learning models and other algorithms to perform health risk assessment, thereby improving the accuracy of health management;

[0047] 3. The present invention records the user's health data in real time through tools such as wearable devices and mobile applications, making it easy to adjust and optimize the health management plan in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0049] Figure 1 It is a schematic diagram of the process of the present invention;

[0050] Figure 2 It is a functional schematic diagram of some machine learning models and deep learning models in the present invention;

[0051] Figure 3 It is a schematic diagram of some health management solutions in the present invention;

[0052] Figure 4 This is a flow chart of recommending a personalized health management plan to a user based on the user's health risk assessment results in the present invention. DETAILED DESCRIPTION

[0053] Please refer to Figures 1 to 4 ,in, Figure 1 It is a schematic diagram of the process of the present invention; Figure 2 It is a functional schematic diagram of some machine learning models and deep learning models in the present invention; Figure 3 It is a schematic diagram of some health management solutions in the present invention; Figure 4 The present invention is a flowchart of recommending a personalized health management plan for a user based on the user's health risk assessment results. The health management method with health data analysis function includes the following steps:

[0054] S1. Collect the user's health data information through existing equipment and establish a personal health profile based on this data information. The health data information is not limited to blood pressure, heart rate and blood sugar;

[0055] S2. The collected health data needs to be cleaned, sorted and pre-processed before establishing personal health records to facilitate subsequent data analysis;

[0056] S3. Based on the user's health data, use machine learning models and deep learning model algorithms to conduct health risk assessment and predict the user's possible health risks, including but not limited to cardiovascular disease and diabetes;

[0057] S4. Recommend personalized health management plans to users based on their health risk assessment results, including advice on diet, exercise, and daily routines;

[0058] S5. The user implements the recommended health management plan and tracks the implementation status through wearable devices and mobile application tools to record the user's health data in real time;

[0059] S6. Based on the health management plan and tracking data implemented by the user, continuously adjust and optimize the user's health management plan to improve the effect of health management.

[0060] Traditional health management plans tend to remain static, but plans that are constantly adjusted based on tracking data can be adjusted in real time based on the user's physical reactions and changes in health conditions. This dynamic adjustment ensures that the health management plan always remains consistent with the user's actual needs.

[0061] Everyone's physical condition, living habits and health needs are unique. By continuously tracking user data, we can more accurately understand the user's physical condition and health needs, and thus provide them with more personalized health management plans.

[0062] By continuously analyzing the user's health data and the effectiveness of the implementation plan, we can find out which measures are effective and which measures need to be improved. In this way, we can ensure that every measure in the health management plan can maximize the user's health.

[0063] Tracking data can not only reflect current health status, but also predict potential health risks. By analyzing this data, preventive measures can be formulated for users in advance to avoid or reduce potential health problems.

[0064] Continuously adjusted and optimized health management plans can make users feel cared for and valued, thereby enhancing their confidence and compliance with the health management plan. This positive feedback will further encourage users to actively implement the health management plan.

[0065] Before the personal health records are stored, data conversion must be carried out in accordance with relevant specifications, the format must be unified, and corresponding fields must be added to facilitate classified inquiries.

[0066] The specific steps of using machine learning models and deep learning model algorithms to perform health risk assessment based on the user's health data and predict the user's possible health risks are as follows:

[0067] (1) The collected user health data needs to be preprocessed, including data cleaning, missing value filling, outlier processing, and data standardization steps, in order to facilitate subsequent feature engineering and model training;

[0068] (2) Extract features related to health risks from the preprocessed data, such as age, gender, weight, heart rate, blood pressure, blood sugar, blood lipid physiological indicators, as well as information on diet, exercise, and daily routine. In addition, you can also consider using time series analysis methods to convert users' historical health data into useful features;

[0069] (3) Select appropriate machine learning models or deep learning models, such as logistic regression and neural networks, based on the problem context and data characteristics. Next, use the preprocessed data and extracted features to train the model and adjust the model parameters to optimize model performance.

[0070] (4) Apply the trained model to an independent test data set to evaluate the model’s predictive performance. Common evaluation metrics include accuracy, precision, recall, and F1 score. In addition, cross-validation can be performed to avoid overfitting and underfitting problems.

[0071] (5) Based on the model prediction results, the system outputs possible health risks to users, such as cardiovascular disease, diabetes, and hypertension, and provides corresponding suggestions and measures to help users reduce health risks;

[0072] (6) Continuously adjust and optimize the model based on the health management plan and tracking data implemented by the user to improve the accuracy and personalization of health risk assessment.

[0073] Based on the user's health data, machine learning models and deep learning model algorithms can be used to conduct health risk assessments, predict the user's possible health risks, and provide corresponding suggestions and measures to help the user achieve better health management.

[0074] The machine learning model and deep learning model also include the following:

[0075] (1) Data cleaning, i.e. detecting and deleting duplicate and incomplete data, and then filling missing values. The methods include mean filling, median filling and mode filling;

[0076] (2) Outlier processing: detect and remove outliers through box plots, and then perform data standardization to map features of different scales to the same scale;

[0077] (3) Extract features related to health risks from the preprocessed data, such as age, gender, weight, heart rate, blood pressure, blood sugar and blood lipid physiological indicators, as well as information on diet, exercise and daily routine. In addition, time series analysis methods can be used to convert users' historical health data into useful features.

[0078] The logistic regression calculation formula in the machine learning model is as follows:

[0079] P(Y=1|X)=\frac{1}{1+e^{-(\beta_0+\beta_1X_1+\beta_2X_2+\dots+\beta_n X_n)}}

[0080] Where: P(Y=1|X) is the probability that the target variable YY is 1 given the feature vector XX;

[0081] \beta_0, \beta_1, \dots, \beta_n are model parameters;

[0082] X_1, X_2, \dots, X_n are the features in the feature vector.

[0083] The neural network formula in the deep learning model is as follows:

[0084]

[0085] Among them, 0 i，j，k，l is the value of position (i, j, k, l) in the output feature map;

[0086] I i+m，j+n，k+o，l+p is the value of position (i+m, j+n, k+o, l+p) in the input feature map;

[0087] W m，n，o，p are the parameters of the convolution kernel;

[0088] b is the bias term;

[0089] φ is the activation function, such as ReLU, Sigmoid.

[0090] Use the training data set to train the model and adjust the model parameters to optimize the model performance. After the training is completed, use an independent test data set to verify the model and evaluate the model's predictive performance. Common evaluation indicators include but are not limited to accuracy, precision, recall rate and F1 score. Based on the trained model, the possible health risks such as cardiovascular disease, diabetes and hypertension are output to the user. At the same time, corresponding suggestions and measures are provided to help users reduce health risks.

[0091] The method steps for recommending a personalized health management plan to a user based on the user's health risk assessment results are as follows:

[0092] (1) Conduct a detailed analysis of the assessment results to identify the user's health risks, such as high blood lipids, high blood pressure and diabetes, and understand the user's personal situation, such as living habits, eating habits and exercise habits;

[0093] (2) Based on the assessment results and the user’s personal situation, formulate overall health management goals, such as lowering blood pressure, reducing weight and improving immunity.

[0094] The health management program includes the following programs:

[0095] (1) Dietary recommendations: Develop a reasonable diet plan based on the user's eating habits and health conditions. For example, for patients with hyperlipidemia, it is recommended to reduce the intake of saturated fat and trans fat and increase the intake of vegetables and fruits. For patients with diabetes, it is recommended to control the total calorie intake and choose foods with a low glycemic index;

[0096] (2) Exercise plan: Develop a suitable exercise plan based on the user's exercise habits and health conditions. For example, for obese people, it is recommended to increase aerobic exercise and strength training to achieve the goal of weight loss; for patients with hypertension, it is recommended to do moderate aerobic exercise, such as walking and jogging, to lower blood pressure;

[0097] (3) Lifestyle adjustment: It is recommended that users adjust their work and rest schedules, ensure adequate sleep, learn to reduce stress and relax, avoid excessive stress and anxiety, and quit smoking and limit alcohol consumption.

[0098] The health management program also includes providing users with continuous motivation and support, such as encouragement, rewards, and health education, to help users adhere to the health management program and gradually achieve their health goals.

[0099] The health management plan also includes using health monitoring devices (such as smart bracelets, blood pressure monitors) and user self-reporting methods to track the user's health data, evaluate the implementation of the health management plan, and adjust the plan in a timely manner based on the tracking results to make it more in line with the user's actual situation.

[0100] Recommend personalized health management plans to users based on their health data to meet the needs of different users;

[0101] Using machine learning models, deep learning models and other algorithms to assess health risks improves the accuracy of health management;

[0102] Record users' health data in real time through wearable devices, mobile applications and other tools, so as to adjust and optimize health management plans in a timely manner;

[0103] Users can manage their health anytime and anywhere through tools such as mobile applications, without having to go to hospitals or clinics frequently.

[0104] The health management method with health data analysis function provided by the present invention can improve the accuracy and personalization level of health management, meet people's needs for health, and has broad application prospects.

[0105] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A health management method with health data analysis function, characterized in that: The following steps are involved: S1. Collect the user's health data information through existing equipment and establish a personal health profile based on this data information. The health data information is not limited to blood pressure, heart rate and blood sugar; S2. The collected health data needs to be cleaned, sorted and pre-processed before establishing personal health records to facilitate subsequent data analysis; S3. Based on the user's health data, use machine learning models and deep learning model algorithms to conduct health risk assessment and predict the user's possible health risks, including but not limited to cardiovascular disease and diabetes; S4. Recommend personalized health management plans to users based on their health risk assessment results, including advice on diet, exercise, and daily routines; S5. The user implements the recommended health management plan and tracks the implementation status through wearable devices and mobile application tools to record the user's health data in real time; S6. Based on the health management plan and tracking data implemented by the user, continuously adjust and optimize the user's health management plan to improve the effect of health management.

2. The health management method with health data analysis function according to claim 1, characterized in that: Before the personal health records are stored, data conversion must be carried out in accordance with relevant specifications, the format must be unified, and corresponding fields must be added to facilitate classified inquiries.

3. The health management method with health data analysis function according to claim 1, characterized in that: The specific steps of using machine learning models and deep learning model algorithms to perform health risk assessment based on the user's health data and predict the user's possible health risks are as follows: (1) The collected user health data needs to be preprocessed, including data cleaning, missing value filling, outlier processing, and data standardization steps, in order to facilitate subsequent feature engineering and model training; (2) Extract features related to health risks from the preprocessed data, such as age, gender, weight, heart rate, blood pressure, blood sugar, blood lipid physiological indicators, as well as information on diet, exercise, and daily routine. In addition, you can also consider using time series analysis methods to convert users' historical health data into useful features; (3) Select appropriate machine learning models or deep learning models, such as logistic regression and neural networks, based on the problem context and data characteristics. Next, use the preprocessed data and extracted features to train the model and adjust the model parameters to optimize model performance. (4) Apply the trained model to an independent test data set to evaluate the model’s predictive performance. Common evaluation metrics include accuracy, precision, recall, and F1 score. In addition, cross-validation can be performed to avoid overfitting and underfitting problems. (5) Based on the model prediction results, the system outputs possible health risks to users, such as cardiovascular disease, diabetes, and hypertension, and provides corresponding suggestions and measures to help users reduce health risks; (6) Continuously adjust and optimize the model based on the health management plan and tracking data implemented by the user to improve the accuracy and personalization of health risk assessment.

4. The health management method with health data analysis function according to claim 1, characterized in that: The machine learning model and deep learning model also include the following: (1) Data cleaning, i.e. detecting and deleting duplicate and incomplete data, and then filling missing values. The methods include mean filling, median filling and mode filling; (2) Outlier processing: detect and remove outliers through box plots, and then perform data standardization to map features of different scales to the same scale; (3) Extract features related to health risks from the preprocessed data, such as age, gender, weight, heart rate, blood pressure, blood sugar and blood lipid physiological indicators, as well as information on diet, exercise and daily routine. In addition, time series analysis methods can be used to convert users' historical health data into useful features.

5. The health management method with health data analysis function according to claim 1, characterized in that: The logistic regression calculation formula in the machine learning model is as follows: P(Y=1|X)=\frac{1}{1+e^{-(\beta_0+\beta_1X_1+\beta_2X_2+\dots+\beta_n X_n)}} Where: P(Y=1|X) is the probability that the target variable YY is 1 given the feature vector XX; \beta_0,\beta_1,\dots,\beta_n are model parameters; X_1,X_2,\dots,X_n are the features in the feature vector.

6. The health management method with health data analysis function according to claim 1, characterized in that: The neural network formula in the deep learning model is as follows: Among them, O i，j，k，l is the value of position (i, j, k, l) in the output feature map; I i+m，j+n，k+o，l+p is the value of position (i+m, j+n, k+o, l+p) in the input feature map; W m，n，o，p are the parameters of the convolution kernel; b is the bias term; is an activation function, such as ReLU, Sigmoid.

7. The health management method with health data analysis function according to claim 1, characterized in that: The method steps for recommending a personalized health management plan to a user based on the user's health risk assessment results are as follows: (1) Conduct a detailed analysis of the assessment results to identify the user's health risks, such as high blood lipids, high blood pressure and diabetes, and understand the user's personal situation, such as living habits, eating habits and exercise habits; (2) Based on the assessment results and the user’s personal situation, formulate overall health management goals, such as lowering blood pressure, reducing weight and improving immunity.

8. The health management method with health data analysis function according to claim 1, characterized in that: The health management program includes the following programs: (1) Dietary recommendations: Develop a reasonable diet plan based on the user's eating habits and health conditions. For example, for patients with hyperlipidemia, it is recommended to reduce the intake of saturated fat and trans fat and increase the intake of vegetables and fruits. For patients with diabetes, it is recommended to control the total calorie intake and choose foods with a low glycemic index; (2) Exercise plan: Develop a suitable exercise plan based on the user's exercise habits and health conditions. For example, for obese people, it is recommended to increase aerobic exercise and strength training to achieve the goal of weight loss; for patients with hypertension, it is recommended to do moderate aerobic exercise, such as walking and jogging, to lower blood pressure; (3) Lifestyle adjustment: It is recommended that users adjust their work and rest schedules, ensure adequate sleep, learn to reduce stress and relax, avoid excessive stress and anxiety, and quit smoking and limit alcohol consumption.

9. The health management method with health data analysis function according to claim 1, characterized in that: The health management program also includes providing users with continuous motivation and support, such as encouragement, rewards, and health education, to help users adhere to the health management program and gradually achieve their health goals.

10. The health management method with health data analysis function according to claim 1, characterized in that: The health management plan also includes using health monitoring devices (such as smart bracelets, blood pressure monitors) and user self-reporting methods to track the user's health data, evaluate the implementation of the health management plan, and adjust the plan in a timely manner based on the tracking results to make it more in line with the user's actual situation.

Images