Human health risk prediction value monitoring method and device and storage medium
By acquiring real-time data and predicting health risks using nonlinear machine learning models, combined with user interaction and data filtering, the problem of health risk monitoring and reduction has been solved, achieving real-time monitoring and reduction of health risks.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN NOEN MEDICAL EQUIP CO LTD
- Filing Date
- 2026-02-25
- Publication Date
- 2026-07-10
AI Technical Summary
People neglect their physical health, resulting in high predicted health risks and a lack of effective monitoring and mitigation methods.
By acquiring user data in real time through handheld or wearable devices, using nonlinear machine learning models to predict health risk values, recommending ways to change data to reduce risk, allowing users to exchange and filter health data, and providing travel advice and alerts.
It enables real-time monitoring and prediction of health risks, recommends ways to mitigate them, promotes communication among users, and helps users reduce health risks and maintain good health.
Smart Images
Figure CN122369904A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of health monitoring technology, and in particular to a method, device and storage medium for monitoring human health risk prediction values. Background Technology
[0002] With economic development and an increasingly fast-paced lifestyle, people are neglecting their health, receiving less rest and exercise, leading to severe physical exhaustion, prominent health problems, and a higher probability of death, significantly impacting lifespan. Therefore, there is an urgent need to develop a method for monitoring and reducing predictive values of health risks. Summary of the Invention
[0003] In view of this, embodiments of this application provide a method, device and storage medium for monitoring human health risk prediction values, in order to solve the problem that people are increasingly neglecting their physical health and that health risk prediction values are high.
[0004] In a first aspect, embodiments of this application provide a method for monitoring human health risk prediction values, comprising the following steps: Create a personal account and add user data to the personal account; obtain the latest user data in real time through handheld mobile devices or wearable devices and upload it to the account to update the data information; Predict the user's health risk based on the user's data information; Calculate which data changes can reduce a user's predicted health risk and recommend them to the user; Display the data and health risk prediction results of users who have been granted access, so that other users can browse them; Based on the filtering criteria entered by the user, the data and health risk prediction values of all users with granted permissions are filtered, statistically analyzed, and displayed as charts.
[0005] In some embodiments, the step of filtering and statistically analyzing the data and / or health risk prediction values of all users with granted permissions based on user-input filtering criteria and displaying them as charts includes: On the filtering interface, based on the filtering criteria entered by the user, users whose data information has a similarity to the current user's data information reaches a predetermined value, but whose predicted health risk value is lower are filtered out. The filtered users, their data information, and their predicted health risk values are then displayed to the current user in a chart.
[0006] In some embodiments, the step of filtering and statistically analyzing the data and / or health risk prediction values of all users with granted permissions based on user-input filtering criteria and displaying them as charts includes: On the filtering interface, all users are filtered based on the disease name entered by the user. Users with a history of the disease who have been cured are selected, and the filtering results are displayed to the current user in a chart.
[0007] In some embodiments, the method for monitoring human health risk prediction values further includes: Send a friend request to the specified user based on the user's input; and / or An alarm will be issued to the user when the predicted health risk value is higher than the predetermined value.
[0008] In some embodiments, the human health risk prediction monitoring method further includes the steps of: real-time collection of each user's location, combined with each user's disease information, to provide the current user with travel location suggestions to avoid areas with high incidence of disease; and / or The specific steps of calculating which data changes can reduce the user's predicted health risk value and recommending it to the user include: changing one of the data information, keeping the other data information unchanged, calculating the predicted health risk value, comparing the calculated predicted health risk value with the predicted health risk value before the data information was changed, and if the predicted health risk value is reduced and the reduction is greater than a certain threshold, then the changed data information is recommended to the user.
[0009] In some embodiments, the data information includes activity data information and baseline characteristic data information. The activity data information is collected by a handheld mobile device or wearable device over a continuous monitoring period. The baseline characteristic data information includes at least one of demographic characteristics, health characteristics, living environment characteristics, and lifestyle characteristics.
[0010] In some embodiments, the method for predicting the health risk prediction value based on the user's data information and updating it periodically includes: Feature construction: The activity data is processed to calculate the average activity data feature value representing the overall activity level of the target individual; Model prediction: The average activity data feature values and the baseline feature data are input into a trained nonlinear machine learning prediction model, and the prediction model outputs the predicted mortality risk value of the target individual within a preset time period.
[0011] In some embodiments, the average activity data characteristic value is the arithmetic mean of the activity data at all valid monitoring times within the continuous monitoring period; and / or The activity data includes at least one of heart rate, steps, distance traveled, cadence, acceleration, and speed; and / or The health characteristics include at least one of the following: body mass index, body fat percentage, systolic blood pressure, diastolic blood pressure, history of diabetes, history of cancer, history of heart disease, recent hospitalization, and long-term medication use; and / or The demographic characteristics include at least one of the following: age, sex, education level, income level, and marital status; and / or The lifestyle characteristics include at least one of the following: sleep duration, dietary habits, smoking status, and alcohol consumption status; and / or The living environment characteristics include at least one of the following: air quality, water quality, noise pollution level, climate conditions, and safety of the living environment.
[0012] A human health risk prediction value monitoring device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any human health risk prediction value monitoring method provided in this application.
[0013] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the human health risk prediction monitoring methods provided in this application.
[0014] The human health risk prediction monitoring method of this application can update the user's latest data information in real time and display the predicted health risk value in real time. It can also recommend ways to reduce the predicted health risk value, allowing the user to follow the recommended methods to lower the predicted health risk value and maintain good health. This method can also allow the user to browse and filter information from other users according to their needs, providing information and methods beneficial to the user's health and reducing the predicted health risk value. Furthermore, based on the user's input filtering conditions, it can filter and statistically analyze the data information and predicted health risk values of all users with granted permissions and display them in charts to help the user select users or information that are helpful to their health, thereby helping the user reduce the predicted health risk value. Attached Figure Description
[0015] Figure 1 This is a flowchart illustrating the human health risk prediction monitoring method in the embodiments of this application; Figure 2 for Figure 1 Detailed flowchart of step S200; Figure 3 This is a schematic diagram illustrating the importance of the Health Risk Prediction Factor (SHAP) derived from the Random Forest prediction model in this embodiment of the application. Figure 4 This is a schematic block diagram of the human health risk prediction value detection system in the embodiments of this application; Figure 5 This is a schematic block diagram of the human health risk prediction value detection device in the embodiments of this application. Detailed Implementation
[0016] To make the inventive objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0017] The system corresponding to the human health risk prediction value monitoring method of this application embodiment can be made into an APP, which can be downloaded and used on mobile devices. Alternatively, the system corresponding to the human health risk prediction value monitoring method of this application embodiment can be embedded in a specific health risk prediction value monitoring device, and health risk prediction value monitoring can be realized by purchasing the device.
[0018] Please see Figure 1 The method for monitoring human health risk prediction values in the embodiments of this application may include: Step S100: Create a personal account and add user data information to the personal account; obtain the latest user data information in real time through a handheld mobile device or wearable device and upload it to the account to update the data information.
[0019] Specifically, each user can create their own account and add personal data to it. Data can be added manually or automatically collected and uploaded to the account via handheld or wearable devices, allowing for real-time or scheduled updates. Data may include, for example, gender, age, heart rate, body mass index, acceleration, body fat percentage, systolic blood pressure, diastolic blood pressure, medical history, lifestyle habits, and living environment. Handheld mobile devices could be smartphones, and wearable devices could be smartwatches.
[0020] Please see Figure 1 The method for monitoring human health risk prediction values in the embodiments of this application may further include: Step S200: Predict the user's health risk prediction value based on the user's data information.
[0021] Specifically, health risk prediction can be achieved by training an existing algorithm model and then using that model to predict health risks. Once the algorithm model is trained, to calculate a user's health risk prediction, the user's data is input into the algorithm model to generate the predicted health risk. Specific algorithm model training and data processing methods are described in detail later. Suitable algorithm models include, for example, logistic regression, decision trees, random forests, gradient boosted machines, K-nearest neighbors, neural networks, and multilayer perceptrons.
[0022] Please see Figure 1 The method for monitoring human health risk prediction values in the embodiments of this application may further include: Step S300: Calculate which data changes can reduce the user's predicted health risk value and recommend them to the user.
[0023] Specifically, the human health risk prediction monitoring method of this application also includes recommending ways to reduce the predicted health risk to users, thereby ensuring the health and longevity of users.
[0024] Step S300 specifically includes: changing one piece of data information in the data information, keeping the other data information unchanged, calculating the health risk prediction value, comparing the calculated health risk prediction value with the health risk prediction value before the data information was changed, and if the health risk prediction value decreases and the decrease is greater than a certain threshold, then the changed data information is recommended to the user.
[0025] For example, if a user's current health risk prediction is calculated to be 8%, and the acceleration data is currently 10, to recommend ways to reduce this prediction, the system can temporarily change one item in the user's current data, for example, increasing the acceleration from 10 to 15 (acceleration can be understood as the user's level of activity). This change in acceleration is hypothetical; the actual stored acceleration data of 10 remains unchanged. It's merely a virtual change to 15 to calculate the impact of the acceleration change on the health risk prediction. Other data remains unchanged. The modified acceleration and other unchanged data are then input into the model, and the health risk prediction is recalculated. If the predicted health risk is 2%, a 6% reduction from the previous 8%, this is a significant decrease. Therefore, the recommendation that increasing the acceleration from 10 to 15 will reduce the predicted health risk by 6% can be sent to the user.
[0026] Please see Figure 1 The method for monitoring human health risk prediction values in the embodiments of this application may further include: Step S400: Display the data information and health risk prediction results of users who have been granted access, for other users to browse.
[0027] Specifically, users can grant permissions through privacy settings, deciding whether to display their data to other users. Displaying data to other users makes it easier for them to view and refer to the data, and also facilitates the system's data collection and statistical analysis. This data is then used to continuously train the algorithm model, improving the accuracy of health risk predictions.
[0028] At the same time, displaying data information to other users facilitates communication among them. If other users see information that interests them or that they want to know more about, such as seeing someone with the same medical history, or someone with the same medical history who has been cured, they can exchange and discuss treatment methods, which is conducive to creating a healthy environment.
[0029] Therefore, the human health risk prediction monitoring method in the embodiments of this application may further include: Step S10: Send a friend request to the specified user based on the user's input.
[0030] Specifically, this application allows users to add each other as friends and communicate. If a user finds an interesting user, they can send a friend request to exchange experiences on health preservation or disease treatment.
[0031] Please see Figure 1 The method for monitoring human health risk prediction values in the embodiments of this application may further include: Step S500: Based on the filtering conditions input by the user, filter and statistically analyze the data information and health risk prediction values of all users with granted permissions and display them as charts.
[0032] Specifically, users can filter the data of other users with granted permissions in the system as needed, thereby selecting users who meet their needs and viewing their data or adding them as friends to continue communication.
[0033] In one embodiment, step S500 specifically includes: Step S510: On the filtering interface, based on the filtering conditions entered by the user, filter users whose data information similarity to the current user reaches a predetermined value, but whose predicted health risk value is lower, and display the filtered users, their data information, and predicted health risk value in a chart to the current user.
[0034] Specific filtering methods can be implemented, for example, by setting the user information display interface to sort by similarity. Clicking "Sort by Similarity" will display the users whose data is most similar to the current user's data at the top for the user to view. When a user finds other users whose data is highly similar to their own, but whose health risk prediction value is much lower, they can compare the differences in their data to find ways to reduce mortality. For example, after a user clicks "Sort by Similarity," the system's sorting results are shown in Table 1 below. Table 1 shows that user Zhang San and the current user's data are basically the same except for a slight difference in acceleration. Zhang San's acceleration is 6, and his health risk prediction value is 7%; the current user's acceleration is 12, but his health risk prediction value is 15%. Therefore, the current user can learn from Table 1 that increasing acceleration can significantly reduce the health risk prediction value.
[0035] In one embodiment, step S500 specifically includes: Step S520: On the filtering interface, all users are filtered according to the disease name entered by the user, and users with a history of the disease and who have been cured are filtered out. The filtering results are then displayed to the current user in a chart.
[0036] Specifically, users can enter the name of a disease in the search box on the user information display interface to search for users with a history of that disease. They can then select cured users from among those with a history of the disease, add them as friends, and ask for advice on treatment methods or where to seek treatment. Simultaneously, if a user successfully cures their disease, they can search for users with the same disease who are not yet cured to share treatment methods with other uncured users. This contributes to the construction of a global health system, facilitates communication among patients, promotes human health and longevity, and reduces the predicted value of health risks. Specifically, data on disease history and whether a user has been cured or not can be manually uploaded by the user or automatically collected through handheld or wearable mobile devices. In one embodiment, for example, if a current user has heart disease, they can search for users with a history of heart disease who have been cured. Examples of search results are shown in Table 2 below. Table 2 clearly shows users with a history of heart disease who have been cured.
[0037] In one embodiment, the human health risk prediction value monitoring method in this application embodiment may further include: Step S20: Collect the location of each user in real time, and combine it with the disease information of each user to provide travel location suggestions for the current user to avoid areas with high incidence of disease.
[0038] Specifically, the system can detect each user's location in real time and upload it to their account. Simultaneously, it can combine this information with each user's individual health status to provide disease avoidance strategies for other users. For example, if it detects a high number of people with colds in location A, and a user plans to travel to A, the system can remind them not to go or to take precautions. Alternatively, users can search for the number of people with colds currently in location A, providing a reference for their travel plans, reducing the risk of illness, and thus lowering the predicted health risk.
[0039] In one embodiment, the human health risk prediction value monitoring method in this application embodiment may further include: Step S30: When the predicted health risk value is higher than the predetermined value, an alarm is issued to the user.
[0040] When the predicted health risk value is too high, the user can be alerted, for example, through an informational notification, and suggestions for reducing the predicted health risk value can be provided. These suggestions can be made using the method described in step 300.
[0041] In step S200, to predict the health risk prediction value, this application embodiment also provides a specific prediction method. This prediction method requires activity data information and baseline characteristic data information. That is, in step S200, the data information includes activity data information and baseline characteristic data information. Activity data information is collected by a handheld mobile device or wearable device over a continuous monitoring period. Baseline characteristic data information includes at least one of demographic characteristics, health characteristics, living environment characteristics, and lifestyle characteristics.
[0042] refer to Figure 2 The specific method for calculating the health risk prediction value in step S200 includes: S210, Feature Construction: Process the activity data to calculate the average activity data feature value representing the overall activity level of the target individual; S220, Model Prediction: The average activity data feature value and the baseline feature data are input into a trained nonlinear machine learning prediction model, and the prediction model outputs the predicted mortality risk value of the target individual within a preset time period.
[0043] The average activity data value is the arithmetic mean of activity data from all valid monitoring moments within a continuous monitoring period. This average reflects the average intensity of an individual's physical activity during the monitoring period, eliminating interference from instantaneous peaks or troughs. The average activity data can be collected from wearable devices (such as smartwatches, smart rings, etc.) worn by the user over a continuous monitoring period (e.g., 7 consecutive days). Before calculation, the collected activity data must be calibrated and its validity assessed, and invalid data segments (including those where the device was not worn, the signal was abnormal, or the monitoring duration was insufficient) must be removed to ensure that the analysis is based on data from valid monitoring moments.
[0044] In one embodiment, the activity data information includes at least one of heart rate, steps, distance traveled, cadence, acceleration, and speed.
[0045] In one embodiment, health characteristics include at least one of the following: body mass index, body fat percentage, systolic blood pressure, diastolic blood pressure, history of diabetes, history of cancer, history of heart disease, recent hospitalization history, and long-term medication use.
[0046] In one embodiment, demographic characteristics include at least one of the following: age, sex, education level, income level, and marital status.
[0047] In one embodiment, lifestyle characteristics include at least one of the following: sleep duration, dietary habits, smoking status, and alcohol consumption status. Dietary habits may specifically include vegetable intake, fruit intake, etc.
[0048] In one embodiment, the living environment characteristics include at least one of the following: air quality, water quality, noise pollution level, climate conditions, and living environment safety.
[0049] The nonlinear machine learning prediction model in step S220 is based on a random forest model or a gradient boosted machine model.
[0050] The random forest model and gradient boosting machine model were verified to have the highest accuracy in predicting health risk values. The specific verification methods are as follows: First, seven prediction models were selected: logistic regression, decision tree, random forest, gradient boosted machine, K-nearest neighbors, neural network, and multilayer perceptron. These models were trained and validated, and then the two models that most accurately predicted health risk values were selected.
[0051] All prediction models were trained, and the most accurate models were selected for testing. The data used for training and testing were divided into training and testing sets. 80% of the data was allocated to the training set, and 20% to the testing set. For example, with 10,000 data points, 8,000 were used for the training set and 2,000 for the testing set. The data was available from the UK Biobank.
[0052] Predictive model training and parameter tuning were performed on 80% of the training set. After selecting several more accurate predictive models, predictions were made on the remaining 20% of the test set, and the predicted values were compared with the actual values.
[0053] When training the prediction models, five-fold cross-validation was used to tune the parameters of each algorithm. This process splits the training set data into five parts, using four parts to build the prediction model and the fifth part to test the accuracy of the prediction model. This validation process was repeated for each combination of prediction model parameters to ensure the stability of the prediction model. After cross-validation, the accuracy of all prediction models was compared, and the accuracy of each prediction model was evaluated and compared using the area under the receiver operating characteristic (AUC), selecting the most accurate prediction model for testing. Validation showed that the random forest model provided the most accurate health risk predictions, followed by the gradient boosted machine model. The AUC values for each model are as follows: The AUC of the random forest model is 0.783; The AUC of the gradient boosted machine model is 0.773. The AUC of the K-nearest neighbors model is 0.758; The AUC of the logistic regression model is 0.745. The AUC of the decision tree model is 0.741. The AUC of the multilayer perceptron model is 0.731; The AUC of the neural network model is 0.722.
[0054] In one embodiment, the most important factor in the data information from which the predictive model derives its predicted health risk values is average acceleration. Average acceleration is measured by an accelerometer in a wearable device, and the average activity data information mentioned above includes average acceleration.
[0055] In this embodiment, the average acceleration is set with two thresholds: a first threshold and a second threshold. When the average acceleration is less than the first threshold or greater than the second threshold, the predicted health risk value of the prediction model is higher; when the average acceleration is greater than or equal to the first threshold and less than or equal to the second threshold, the predicted health risk value of the prediction model is lower. The first threshold can be 15 mg, and the second threshold can be 25 mg.
[0056] Specifically, to further understand the most important predictors of health risk prediction values, a diagram illustrating the importance of SHAP was derived from the most accurate prediction model (random forest prediction model), as shown below. Figure 3 As is well known, age is the most important predictor of health risk. Figure 3 The study showed that, after age, average acceleration was the second most important predictor of health risk. Average acceleration represents a user's average level of physical activity; a moderately high average acceleration can reduce the probability of death, for example, above 15mg. However, excessively high average acceleration can increase the predicted value of health risk. In other words, while moderate physical activity can significantly reduce the risk of death, very high levels of physical activity can also lead to an increased predicted value of health risk.
[0057] Furthermore, this invention also provides a system for predicting human health risk values. For example... Figure 4 As shown, the human health risk prediction system 800 includes: The data acquisition module 801 creates a personal account and adds user data information to the personal account; it acquires the latest user data information in real time through a handheld mobile device or wearable device and uploads it to the account to update the data information. The health risk prediction module 802 predicts the user's health risk based on the user's data information. The filtering and recommendation module 803 is used to calculate which changes in data information can reduce the user's predicted health risk value and recommend them to the user. It is also used to display the data information and predicted health risk values of users with granted permissions for other users to browse, and to filter and statistically analyze the data information and predicted health risk values of all users with granted permissions based on the filtering conditions input by the user and display them as charts.
[0058] The description of the system embodiments above is similar to that of the method embodiments above, and has similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.
[0059] It should be noted that the module division of the human health risk prediction monitoring system shown in the embodiments of this application is illustrative and only represents a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processing unit, exist as separate physical units, or be integrated into a group of two or more modules. The integrated modules can be implemented in hardware, as software functional units, or a combination of software and hardware.
[0060] It should be noted that, in the embodiments of this application, if the above-described methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM (Read Only Memory), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.
[0061] This application also discloses a device for monitoring human health risk prediction values. For example... Figure 5As shown. The human health risk prediction monitoring device 900 includes a processor 901 and a memory 902. In this embodiment, the processor 901 can be a general-purpose processor, such as an ARM architecture processor. The memory 902 stores a computer program and can be a high-speed random access memory or a non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 902 may also include a memory controller to provide the processor 901 with access to the memory 902. The processor 901 executes the computer program in the memory 902 to perform any of the above-mentioned human health risk prediction monitoring methods, such as: Create a personal account and add user data to the personal account; obtain the latest user data in real time through handheld mobile devices or wearable devices and upload it to the account to update the data information; Predict the user's health risk based on the user's data information; Calculate which data changes can reduce a user's predicted health risk and recommend them to the user; Display the data and health risk prediction results of users who have been granted access, so that other users can browse them; Based on the filtering criteria entered by the user, the data and health risk prediction values of all users with granted permissions are filtered, statistically analyzed, and displayed as charts.
[0062] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps in the human health risk prediction value monitoring method provided in the above embodiments.
[0063] When the computer program stored therein is executed on the processor of the physiotherapy device provided in this application embodiment, the processor of the physiotherapy device performs any of the steps in the human health risk prediction value monitoring method suitable for the physiotherapy device. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0064] The above provides a detailed description of a method, device, and storage medium for monitoring human health risk prediction values provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for monitoring predictive values of human health risks, characterized in that, Includes the following steps: Create a personal account and add user data to the personal account; obtain the latest user data in real time through handheld mobile devices or wearable devices and upload it to the account to update the data information; Predict the user's health risk based on the user's data information; Calculate which data changes can reduce a user's predicted health risk and recommend them to the user; Display the data and health risk prediction results of users who have been granted access, so that other users can browse them; Based on the filtering criteria entered by the user, the data and health risk prediction values of all users with granted permissions are filtered, statistically analyzed, and displayed as charts.
2. The method for monitoring human health risk prediction values according to claim 1, characterized in that, The step of filtering and statistically analyzing the data and / or health risk prediction values of all users with granted permissions based on user-input filtering criteria and displaying them as charts includes: On the filtering interface, based on the filtering criteria entered by the user, users whose data information has a similarity to the current user's data information reaches a predetermined value, but whose predicted health risk value is lower are filtered out. The filtered users, their data information, and their predicted health risk values are then displayed to the current user in a chart.
3. The method for monitoring human health risk prediction values according to claim 1, characterized in that, The step of filtering and statistically analyzing the data and / or health risk prediction values of all users with granted permissions based on user-input filtering criteria and displaying them as charts includes: On the filtering interface, all users are filtered based on the disease name entered by the user. Users with a history of the disease who have been cured are selected, and the filtering results are displayed to the current user in a chart.
4. The method for monitoring human health risk prediction values according to any one of claims 2 to 3, characterized in that, Also includes: Send a friend request to the specified user based on the user's input command to add a friend; and / or An alarm will be issued to the user when the predicted health risk value is higher than the predetermined value.
5. The method for monitoring human health risk prediction values according to claim 1, characterized in that, Also includes Steps: Collect the location of each user in real time, combine it with the user's disease information, and provide the current user with travel destination suggestions to avoid areas with high incidence of disease; and / or The specific steps of calculating which data changes can reduce the user's predicted health risk value and recommending it to the user include: changing one of the data information, keeping the other data information unchanged, calculating the predicted health risk value, comparing the calculated predicted health risk value with the predicted health risk value before the data information was changed, and if the predicted health risk value is reduced and the reduction is greater than a certain threshold, then the changed data information is recommended to the user.
6. The method for monitoring human health risk prediction values according to claim 1, characterized in that, The data information includes activity data information and baseline characteristic data information. The activity data information is collected by a handheld mobile device or wearable device within a continuous monitoring period. The baseline characteristic data information includes at least one of demographic characteristics, health characteristics, living environment characteristics, and lifestyle characteristics.
7. The method for monitoring human health risk prediction values according to claim 6, characterized in that, In the step of predicting the user's health risk prediction value based on the user's data information and updating it periodically, the prediction method for the health risk prediction value includes: Feature construction: The activity data is processed to calculate the average activity data feature value representing the overall activity level of the target individual; Model prediction: The average activity data feature values and the baseline feature data are input into a trained nonlinear machine learning prediction model, and the prediction model outputs the predicted mortality risk value of the target individual within a preset time period.
8. The method for monitoring human health risk prediction values according to claim 6, characterized in that, The average activity data characteristic value is the arithmetic mean of the activity data at all valid monitoring times within the continuous monitoring period; and / or The activity data includes at least one of heart rate, steps, distance traveled, cadence, acceleration, and speed; and / or The health characteristics include at least one of the following: body mass index, body fat percentage, systolic blood pressure, diastolic blood pressure, history of diabetes, history of cancer, history of heart disease, recent hospitalization, and long-term medication use; and / or The demographic characteristics include at least one of the following: age, sex, education level, income level, and marital status; and / or The lifestyle characteristics include at least one of the following: sleep duration, dietary habits, smoking status, and alcohol consumption status; and / or The living environment characteristics include at least one of the following: air quality, water quality, noise pollution level, climate conditions, and safety of the living environment.
9. A human health risk prediction monitoring device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the human health risk prediction value monitoring method according to any one of claims 1 to 8.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the human health risk prediction value monitoring method as described in any one of claims 1-8.