Disease risk assessment method based on data analysis

Abstract

The invention discloses a disease risk assessment method based on data analysis, and relates to the field of disease assessment, and the method comprises the following steps: 1, collecting physiological indexes and preference data of a user, carrying out the clustering of physique types based on the physiological indexes, and obtaining the physique type of the current user; 2, editing a plurality of corresponding testable events according to the characteristics of each physique type, matching the corresponding testable events based on the physique type of the current user, and performing trigger definition on the importance of the current periodic events based on the historical standard reaching state of the user; when the health condition or behavior of the user changes, the evaluation standard and the test item can be adjusted in real time, the actual condition of the user can be adapted by automatically reducing the importance degree of similar test events and replacing the selection of the test events, and the user experience can be improved by collecting the physiological indexes and preference data of the user. Constitution type clustering and risk assessment can be carried out based on individual differences, and key organ nodes can be accurately marked.

Description

Technical Field

[0001] The present invention relates to the technical field of disease assessment, and in particular to a disease risk assessment method based on data analysis. Background Art

[0002] In recent years, the incidence of endocrine diseases has gradually increased. Unhealthy eating habits, lack of exercise and other lifestyle habits have led to an increase in many endocrine problems, and effective screening and prevention measures are urgently needed. With the improvement of public health awareness, more and more people hope to actively monitor their health status and actively participate in personal health management. Medicine is gradually shifting towards personalized medicine. Patients hope to get a tailored health management plan based on their own health status and physiological indicators. The modern medical system advocates a shift from traditional disease treatment to active prevention, which provides a lot of research support for the early identification and intervention of endocrine diseases. Existing endocrine diseases are difficult to detect in the early stages. If a precise indication is needed, highly professional detection methods are required, such as imaging and laboratory tests. Many people do not give priority to such detection methods because they do not pay attention to such diseases. Conventional single self-examination methods, such as blood sugar monitoring or weight monitoring, are difficult for non-professionals to identify abnormal information in the changing trends of such indicators; Many existing methods are unable to adjust evaluation criteria and test items in real time when the user's health status or behavior changes. They only focus on a single physiological indicator, have a narrow evaluation angle, and ignore the complexity of the endocrine system and the interaction of multiple factors. Summary of the invention

[0003] 1. Technical issues to be resolved In view of the above-mentioned shortcomings of the prior art, the present invention provides a disease risk assessment method based on data analysis, which can effectively solve the problems of the prior art.

[0004] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention discloses a disease risk assessment method based on data analysis, comprising the following steps: Step 1: Collect user physiological indicators and preference data, cluster physical types based on physiological indicators, and obtain the physical type of the current user; Step 2: Edit several corresponding testable events according to the characteristics of each physical type, match the corresponding testable events based on the physical type of the current user, and define the triggering importance of the current periodic event based on the user's historical compliance status; Step 3: Generate a list of test events based on the matched testable events and user preferences and event importance, and the user can select one or more test events. Step 4: When the user is testing, the application provides a recording strategy for the corresponding event type to record the test progress data and the test result data after the test is completed; Step 5: According to the user's test data, based on the action completion index, frequency completion index and time completion index, perform core and conventional test evaluation processing, and obtain the completion degree of the test event corresponding to the current test data as a reference weight; Step 6: Based on the test event completion and test result data, combined with user preference data, identify key features; Step 7: Based on key features and user physiological indicators, an endocrine model is constructed to simulate the performance of the endocrine system in the current and future cycles, mark the attention of several organ regions involved in the endocrine model, and identify key organ nodes; Step 8: Combine the test result data, event completion, key features and event reference weights, use the risk assessment algorithm to calculate the risk coefficient of endocrine diseases corresponding to the identified key organ nodes, and output the comprehensive assessment results.

[0005] Furthermore, the trigger definition process in step 2 is: Step 21: Based on the association matrix of the user's physical classification and endocrine indicators, a three-dimensional event vector including the test type, physiological target organ, and data collection cycle is generated, and each test event vector is accompanied by an initial importance parameter; Step 22: If the user continuously meets the monitoring standard for a certain event within a preset number of times within a limited period, the test frequency of the same type of test event will be automatically reduced; Step 23: When reducing the frequency of similar tests, automatically select alternative test events according to the preset organ association weights, giving priority to test events with the top 20% association with the current constitution type; Step 24: When the frequency of a specific test event is adjusted, the associated organ verification test is started synchronously, and the verification result is automatically fed back to the endocrine model in step 7 for parameter calibration.

[0006] Furthermore, the weight of the core test in step 5 is set to three times that of the regular test. The weight of the overdue core test or regular test is reduced according to the overdue status, using an exponential decay function of a preset scale. The weight of each test is dynamically adjusted according to the user's historical performance and current health status.

[0007] Furthermore, the process of identifying key organ nodes in step 7 is as follows: Endocrine organ nodes are defined, and organs related to the endocrine system are divided into different levels according to their functions and interaction relationships, including: The first layer is the core endocrine glands, including the pancreas, thyroid gland, adrenal gland, pituitary gland and gonads; the second layer is the secondary organs, including the liver and kidneys; the third layer is the related organs that affect the endocrine system, including the heart, muscle tissue and adipose tissue. The organ nodes at each level are dynamically scored through physiological indicators collected in real time; Based on the scores of organ nodes at each level and the standard risk of endocrine diseases, the initial focus of several organs is defined, the daily trends of physiological indicators are monitored, a baseline is established through historical data, and an organ status assessment is given for a specific time period.

[0008] Furthermore, the user's physiological indicators in step 1 include: blood sugar level, hormone content and metabolic level data, and the preference data is normalized data that is a comprehensive integration of eating habits and exercise frequency.

[0009] Furthermore, the types of events that can be tested in step 2 include: human contact test, instrument contact test, non-contact action test and behavior intervention test.

[0010] Furthermore, the recording strategy in step 4 is: recording the test start time, test end time, test results and the user's subjective feelings. When the user starts or ends the test, the application automatically records the timestamp, allowing the user to manually enter the test data. If the test requires a specific instrument, it can be connected to the specific instrument via Bluetooth or Wi-Fi to automatically obtain data. The test data is first stored locally on the device and regularly backed up to the cloud.

[0011] Furthermore, the risk assessment algorithm in step 8 generates a risk coefficient by integrating the test results, completion, key features and weights, combined with the organ concern, and the risk coefficient calculation formula is: ; In the formula, represents the standardized result value of the ith test event for the mth organ, Represents the total number of organs, represents the total number of test events for the mth organ, represents the impact coefficient of the i-th test event on the key characteristics of the m-th organ, represents the completion score of the i-th test event on the m-th organ, Represents the dynamic weight of the ith test event on the mth organ, including overdue decay and type weight, represents the sum of weights of all test events associated with the mth organ, Represents the organ attention, indicating the dynamic score of the mth organ, Represents the key feature factor, which indicates the key feature influence weight related to the mth organ.

[0012] Furthermore, the working logic of the risk coefficient calculation formula is: for each organ, calculate the weighted result mean of its associated test events, use the organ attention and key characteristic factors as amplification factors, and finally accumulate all organ risk values.

[0013] Furthermore, the comprehensive evaluation results in step 8 include: basic information of the user, physiological indicators, a list of test events and their completion, risk assessment results of key organ nodes, key organ status assessment, and personalized suggestions for the current status.

[0014] (III) Beneficial effects Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects: When the user's health status or behavior changes, the evaluation criteria and test items can be adjusted in real time. By automatically reducing the importance of similar test events and selecting alternative test events, it can adapt to the user's actual situation and improve the flexibility and effectiveness of the evaluation. By collecting the user's physiological indicators and preference data, it can cluster physical types and assess risks based on individual differences, provide personalized health management plans, and more comprehensively assess the user's health status, reflecting the complexity of the endocrine system.

[0015] By identifying key features and performing dynamic scoring, this method can accurately mark the key organ nodes that need attention in the user's endocrine system, so as to make timely intervention before potential risks occur. By using risk assessment algorithms, combined with test results, completion and dynamic weights, it can effectively quantify the risk factor of endocrine diseases, helping users and professionals better understand health risks and take corresponding measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of the process of the present invention; Figure 2 It is a flowchart of the trigger definition process in the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0019] The present invention will be further described below in conjunction with the embodiments.

[0020] ① Example 1: A disease risk assessment method based on data analysis in this example, such as Figure 1 As shown, the following steps are included: Step 1: Collect user physiological indicators and preference data, cluster the physical type based on the physiological indicators, and obtain the physical type of the current user; physiological indicators include: blood sugar level, hormone content and metabolic level data, and preference data is normalized data integrated with eating habits and exercise frequency; Step 2: According to the characteristics of each physical type, edit several corresponding testable events, match the corresponding testable events based on the physical type of the current user, and define the triggering importance of the current cycle event based on the user's historical compliance status; the types of testable events include: human contact test, instrument contact test, non-contact action test and behavioral intervention test; Step 3: Generate a list of test events based on the matched testable events and user preferences and event importance, and the user can select one or more test events. Allowing users to select test events by themselves enhances user participation and initiative, thereby improving compliance and the effectiveness of results. Step 4: When the user is conducting a test, the application provides a recording strategy for the corresponding event type to record the test data and the test result data after the test is completed; the recording strategy is: record the test start time, test end time, test results and the user's subjective feelings. When the user starts or ends the test, the application automatically records the timestamp, allowing the user to manually enter the test data. If the test requires a specific instrument, it can be connected to the specific instrument via Bluetooth or Wi-Fi to automatically obtain data. The test data is first stored locally on the device and regularly backed up to the cloud; Step 5: According to the user's test data, based on the action completion index, frequency completion index and time completion index, the core and regular test evaluation processing is carried out, and the completion degree of the test event corresponding to the current test data is obtained as the reference weight; the weight of the core test is set to three times that of the regular test. The weight of the overdue core test or regular test is reduced according to the overdue status according to the exponential decay function of the preset scale. The weight of each test is dynamically adjusted according to the user's historical performance and current health status; Step 6: Based on the test event completion and test result data, combined with user preference data, identify key features; Step 7: Based on key features and user physiological indicators, an endocrine model is constructed to simulate the performance of the endocrine system in the current and future cycles, mark the attention of several organ regions involved in the endocrine model, and identify key organ nodes; The process of building the endocrine model is as follows: based on key features and user physiological indicators, a hierarchical feedback network is constructed through the endocrine axis, positive or negative feedback loops are annotated, the dynamics of hormone concentration changes over time are described, the betweenness and proximity of organ nodes in the network are obtained, the designated hub organs are located, initial conditions are input, and the differential equations are iteratively solved; The process of identifying key organ nodes is: Endocrine organ nodes are defined, and organs related to the endocrine system are divided into different levels according to their functions and interaction relationships, including: The first layer is the core endocrine glands, including the pancreas, thyroid gland, adrenal gland, pituitary gland and gonads; the second layer is the secondary organs, including the liver and kidneys; the third layer is the related organs that affect the endocrine system, including the heart, muscle tissue and adipose tissue. The organ nodes at each level are dynamically scored through physiological indicators collected in real time; Based on the scores of each level of organ nodes and the standard risk of endocrine diseases, the initial focus of several organs is defined, the daily trend of physiological indicators is monitored, a baseline is established through historical data, and an organ status assessment is given for a specific time period; Step 8: Combine the test result data, event completion, key features and event reference weights, use the risk assessment algorithm to calculate the risk factor of endocrine diseases corresponding to the identified key organ nodes, and output the comprehensive assessment results. The comprehensive assessment results include: user basic information, physiological indicators, test event list and its completion, key organ node risk assessment results, key organ status assessment and personalized suggestions for the current status.

[0021] Compared with existing technologies, by collecting user physiological indicators and preference data, it can provide each user with personalized physical type analysis and test event matching, making risk assessment more targeted and improving the effectiveness of detection. It introduces a dynamic adjustment function that can flexibly adjust the importance and frequency of test events according to the user's test compliance and physiological indicator changes, effectively avoiding fatigue from frequent testing, while accurately controlling the focus of risk assessment; By combining multi-dimensional data such as physiological indicators, preference data and test results to build an endocrine model, it is possible to analyze the user's health status more comprehensively rather than relying on a single indicator, improve the accuracy of the assessment, focus on identifying key organ nodes, and more effectively locate possible health risk points through multi-level analysis of the functions of organs related to the endocrine system, which is of great significance for clinical prevention and early intervention; Real-time collection of physiological indicators and dynamic scoring provide a more timely health status assessment. Combined with baseline analysis of historical data, it can better monitor the user's health trends. By combining test results, completion, key characteristics and event weights, the risk factor of endocrine diseases is calculated, providing more comprehensive risk assessment results and personalized health recommendations to help users better understand their own health risks.

[0022] ② Example 2: In this example, the risk assessment algorithm generates a risk coefficient by integrating the test results, completion, key features and weights, combined with the organ attention. The specific formula for calculating the risk coefficient is: ; In the formula, represents the standardized result value of the ith test event for the mth organ, Represents the total number of organs, represents the total number of test events for the mth organ, represents the impact coefficient of the i-th test event on the key characteristics of the m-th organ, represents the completion score of the i-th test event on the m-th organ, Represents the dynamic weight of the ith test event on the mth organ, including overdue decay and type weight, represents the sum of weights of all test events associated with the mth organ, Represents the organ attention, indicating the dynamic score of the mth organ, Represents the key feature factor, which indicates the key feature influence weight related to the mth organ.

[0023] The working logic of the risk coefficient calculation formula is: for each organ, calculate the weighted average of its associated test events, use the organ's attention and key characteristic factors as amplification factors, and finally accumulate all organ risk values; By combining test results, completion, key features and organ attention, the formula achieves the integration of multi-dimensional data. This integrated path can more comprehensively assess risks and ensure that potential influencing factors are not missed. The hierarchical division of endocrine system organs emphasizes the relationship between different organs of the endocrine system, distinguishes core endocrine glands from other related organs, makes risk assessment more systematic, and helps identify key organs. Therefore, when an organ behaves abnormally, potential health risks can be quickly located; Through the risk assessment algorithm, combined with user habits and physiological indicators, users can know which tests are more important and how to adjust their daily health management methods, thereby enhancing users' self-management capabilities.

[0024] ③Example 3: Figure 2 As shown, in this embodiment, the trigger definition process in step 2 is specifically as follows: Step 21: Based on the association matrix of the user's physical classification and endocrine indicators, a three-dimensional event vector including the test type, physiological target organ, and data collection cycle is generated, and each test event vector is accompanied by an initial importance parameter; Step 22: If the user continuously meets the monitoring standard for a certain event within a preset number of times within a limited period, the test frequency of the same type of test event will be automatically reduced; Step 23: When reducing the frequency of similar tests, automatically select alternative test events according to the preset organ association weights, giving priority to test events with the top 20% association with the current constitution type; Step 24: When the frequency of a specific test event is adjusted, the verification test of the associated organ is started synchronously, and the verification result is automatically fed back to the endocrine model in step 7 for parameter calibration; Compared with the existing technology, through the association matrix established based on the user's physical classification and endocrine indicators, the process can generate personalized three-dimensional event vectors for each user, enhance the responsiveness to the user's physiological characteristics, and dynamically adapt to the user's actual situation; The automatic reduction of the importance of similar test events achieved in step 22 reduces unnecessary repeated tests, thereby effectively reducing the test burden of users, improving user experience, and making the test more targeted; In step 23, alternative test events are selected according to the preset organ correlation weights, which provides users with a more flexible test plan and gives priority to events with the top 20% correlation with the current constitution type, which helps to ensure the scientificity and effectiveness of the test; Step 24 implements the instant feedback mechanism of the test frequency adjustment and the endocrine model. When a test event adjusts the frequency, the associated organ verification test is automatically started, which helps to calibrate the model parameters in real time. The closed-loop feedback mechanism can improve the accuracy and adaptability of the model, making the risk assessment results more reliable. By adjusting the frequency of specific test events and combining them with verification testing of key organs, preventive intervention can be carried out in the early stages of the disease, rather than just post-analysis, which helps reduce the risk of endocrine diseases. By integrating information such as test type, physiological target organs, and data collection cycles into event vectors, a multi-dimensional evaluation system is formed, which can more comprehensively monitor and evaluate the user's health status, which is more comprehensive than traditional methods of single indicator monitoring.

[0025] In summary: the present invention can cluster physical types and conduct risk assessment based on individual differences by collecting physiological indicators and preference data of users, and provide personalized health management programs, avoiding one-size-fits-all evaluation criteria. Instead of focusing on a single physiological indicator (such as blood sugar or weight), the present invention integrates multiple physiological indicators (blood sugar level, hormone content, metabolic level) and user behavior data (eating habits, exercise frequency), and can more comprehensively evaluate the health status of users, reflecting the complexity of the endocrine system. When the user's health status or behavior changes, the evaluation criteria and test items can be adjusted in real time. By automatically reducing the importance of similar test events and selecting alternative test events, the method can adapt to the user's actual situation and improve the flexibility and effectiveness of the evaluation. By identifying key features and performing dynamic scoring, the method can accurately mark the key organ nodes that need attention in the user's endocrine system, so as to carry out timely intervention before potential risks occur. The risk assessment algorithm, combined with test results, completion and dynamic weights, can effectively quantify the risk factor of endocrine diseases, help users and professionals better understand health risks and take corresponding measures. The final comprehensive assessment results include basic user information, physiological indicators, test event lists, key organ risk assessment results, etc., and provide personalized health advice to enhance the user's self-management ability. When the user's health status or behavior changes, the evaluation criteria and test items can be adjusted in real time. By automatically reducing the importance of similar test events and selecting alternative test events, it can adapt to the user's actual situation and improve the flexibility and effectiveness of the evaluation. By collecting the user's physiological indicators and preference data, it can cluster physical types and conduct risk assessment based on individual differences, provide personalized health management plans, and more comprehensively evaluate the user's health status, reflecting the complexity of the endocrine system. By identifying key features and performing dynamic scoring, this method can accurately mark the key organ nodes that need attention in the user's endocrine system, so as to make timely intervention before potential risks occur. By using risk assessment algorithms, combined with test results, completion and dynamic weights, it can effectively quantify the risk factor of endocrine diseases, helping users and professionals better understand health risks and take corresponding measures.

[0026] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A disease risk assessment method based on data analysis, characterized in that: The following steps are involved: Step 1: Collect user physiological indicators and preference data, cluster physical types based on physiological indicators, and obtain the physical type of the current user; Step 2: Edit several corresponding testable events according to the characteristics of each physical type, match the corresponding testable events based on the physical type of the current user, and define the triggering importance of the current periodic event based on the user's historical compliance status; Step 3: Generate a list of test events based on the matched testable events and user preferences and event importance, and the user can select one or more test events. Step 4: When the user is testing, the application provides a recording strategy for the corresponding event type to record the test progress data and the test result data after the test is completed; Step 5: According to the user's test data, based on the action completion index, frequency completion index and time completion index, perform core and conventional test evaluation processing, and obtain the completion degree of the test event corresponding to the current test data as a reference weight; Step 6: Based on the test event completion and test result data, combined with user preference data, identify key features; Step 7: Based on key features and user physiological indicators, an endocrine model is constructed to simulate the performance of the endocrine system in the current and future cycles, mark the attention of several organ regions involved in the endocrine model, and identify key organ nodes; Step 8: Combine the test result data, event completion, key features and event reference weights, use the risk assessment algorithm to calculate the risk coefficient of endocrine diseases corresponding to the identified key organ nodes, and output the comprehensive assessment results.

2. A disease risk assessment method based on data analysis according to claim 1, characterized in that: The trigger definition process in step 2 is as follows: Step 21: Based on the association matrix of the user's physical classification and endocrine indicators, a three-dimensional event vector including the test type, physiological target organ, and data collection cycle is generated, and each test event vector is accompanied by an initial importance parameter; Step 22: If the user continuously meets the monitoring standard for a certain event within a preset number of times within a limited period, the test frequency of the same type of test event will be automatically reduced; Step 23: When reducing the frequency of similar tests, automatically select alternative test events according to the preset organ association weights, giving priority to test events with the top 20% association with the current constitution type; Step 24: When the frequency of a specific test event is adjusted, the associated organ verification test is started synchronously, and the verification result is automatically fed back to the endocrine model in step 7 for parameter calibration.

3. The disease risk assessment method based on data analysis according to claim 1, characterized in that: The weight of the core test in step 5 is set to three times that of the regular test. The weight of the overdue core test or regular test is reduced according to the overdue status and an exponential decay function of a preset scale. The weight of each test is dynamically adjusted according to the user's historical performance and current health status.

4. The disease risk assessment method based on data analysis according to claim 1, characterized in that: The process of identifying key organ nodes in step 7 is as follows: Endocrine organ nodes are defined, and organs related to the endocrine system are divided into different levels according to their functions and interaction relationships, including: The first layer is the core endocrine glands, including the pancreas, thyroid gland, adrenal gland, pituitary gland and gonads; the second layer is the secondary organs, including the liver and kidneys; the third layer is the related organs that affect the endocrine system, including the heart, muscle tissue and adipose tissue. The organ nodes at each level are dynamically scored through physiological indicators collected in real time; Based on the scores of organ nodes at each level and the standard risk of endocrine diseases, the initial focus of several organs is defined, the daily trends of physiological indicators are monitored, a baseline is established through historical data, and an organ status assessment is given for a specific time period.

5. The disease risk assessment method based on data analysis according to claim 1, characterized in that: The user's physiological indicators in step 1 include: blood sugar level, hormone content and metabolic level data, and the preference data is normalized data that is a comprehensive integration of eating habits and exercise frequency.

6. A disease risk assessment method based on data analysis according to claim 1, characterized in that: The types of events that can be tested in step 2 include: human contact test, instrument contact test, non-contact action test and behavior intervention test.

7. A disease risk assessment method based on data analysis according to claim 1, characterized in that: The recording strategy in step 4 is: record the test start time, test end time, test results and the user's subjective feelings. When the user starts or ends the test, the application automatically records the timestamp, allowing the user to manually enter the test data. If the test requires a specific instrument, it can be connected to the specific instrument via Bluetooth or Wi-Fi to automatically obtain data. The test data is first stored locally on the device and regularly backed up to the cloud.

8. The disease risk assessment method based on data analysis according to claim 1, characterized in that: The risk assessment algorithm in step 8 generates a risk coefficient by integrating the test results, completion, key features and weights, combined with the organ concern. The risk coefficient calculation formula is: ； In the formula, represents the standardized result value of the ith test event for the mth organ, Represents the total number of organs, represents the total number of test events for the mth organ, represents the impact coefficient of the i-th test event on the key characteristics of the m-th organ, represents the completion score of the i-th test event on the m-th organ, Represents the dynamic weight of the ith test event on the mth organ, including overdue decay and type weight, represents the sum of weights of all test events associated with the mth organ, Represents the organ attention, indicating the dynamic score of the mth organ, Represents the key feature factor, which indicates the key feature influence weight related to the mth organ.

9. A disease risk assessment method based on data analysis according to claim 8, characterized in that: The working logic of the risk coefficient calculation formula is: for each organ, calculate the weighted average of the associated test events, use the organ's attention and key characteristic factors as amplification factors, and finally accumulate all organ risk values.

10. A disease risk assessment method based on data analysis according to claim 1, characterized in that: The comprehensive evaluation results in step 8 include: basic user information, physiological indicators, a list of test events and their completion, key organ node risk assessment results, key organ status assessment, and personalized recommendations for the current status.

Images