Dynamic health management method and system based on diabetic nephropathy and storage medium

Abstract

The invention relates to the technical field of health management, in particular to a dynamic health management method and system based on diabetic nephropathy and a storage medium, and the method comprises the following steps: in the dynamic health management system, dividing the dynamic health management system into a plurality of label sets according to influence factors of a personalized health management scheme, and matching each label set with a personalized label; acquiring real-time personalized tags of the type 2 diabetic nephropathy patient on each tag set, and matching to a real-time personalized health management scheme; matching a new personalized health management scheme by utilizing the adjusted new personalized label based on the fed-back health index and action data; and the dynamic health management system establishes a dynamic adaptive updating model of the personalized health management scheme by using a neural network. According to the invention, unified standard health management scheme matching is realized based on the combined personalized tag, the health management scheme can be updated in time along with the updating of the individual condition of the patient, and the timeliness of health management is ensured.

Description

Technical Field

[0001] The present invention relates to the field of health management technology, and in particular to a dynamic health management method, system and storage medium based on diabetic nephropathy. Background Art

[0002] Type 2 diabetic kidney disease (DKD) is one of the most common complications of patients with type 2 diabetic kidney disease and the main cause of end-stage renal disease (ESRD), accounting for 59% of new ESRD. With the increasing incidence of diabetes year by year, the high incidence of DKD has brought tremendous pressure and challenges to the medical system and social economy.

[0003] However, the current health management plans for patients with type 2 diabetes and nephropathy are mostly set up subjectively by doctors, so the benefits of patient health management depend entirely on the individual experience and skill level of the doctor. This will also lead to the inability of the existing subjective patient health management to achieve a unified standard for health management plan selection, and the inability to guarantee the benefits of patient health management. In addition, the health management plans formulated by doctors are either static or adjusted only after the patient becomes uncomfortable or the management is ineffective. It is also impossible to update the health management plan in a timely manner as the patient's individual situation is updated, and the timeliness of health management is insufficient. Summary of the invention

[0004] The purpose of the present invention is to provide a dynamic health management method, system and storage medium based on diabetic nephropathy, so as to solve the technical problems in the prior art that subjective patient health management cannot achieve unified standard health management plan selection, cannot timely update the health management plan as the patient's individual condition updates, and the timeliness of health management is insufficient.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions: A dynamic health management method based on diabetic nephropathy, comprising the following steps: In the dynamic health management system, the influencing factors of the personalized health management plan of patients with type 2 diabetic nephropathy are divided into multiple label sets, and each label set is matched with a personalized label that reflects the personalized characterization of the influencing factors of patients with type 2 diabetic nephropathy, wherein the influencing factors include the health information, self-management information, risk level information and expert consensus information of the patients with type 2 diabetic nephropathy, the health information, self-management information and expert consensus information are all directly collected by the system, and the risk level information is indirectly calculated by a pre-established risk prediction model for the onset of type 2 diabetic nephropathy; The dynamic health management system obtains the real-time personalized labels of type 2 diabetic nephropathy patients on various label sets, and matches the real-time personalized health management plan of type 2 diabetic nephropathy patients based on the real-time personalized labels of type 2 diabetic nephropathy patients on various label sets; The dynamic health management system monitors the action data of the type 2 diabetic nephropathy patient executing the real-time personalized health management program, and monitors the health indicators of the type 2 diabetic nephropathy patient after the real-time personalized health management program is executed; The dynamic health management system dynamically adjusts the real-time personalized label of the type 2 diabetic nephropathy patient based on the fed-back health index and the action data to obtain a new personalized label, and uses the adjusted new personalized label to match a new personalized health management plan for the type 2 diabetic nephropathy patient; The dynamic health management system uses neural networks to establish health indicators and action data of real-time personalized health management plans, as well as the mapping relationship between real-time personalized health management plans and new personalized health management plans, to obtain a dynamic adaptive update model of personalized health management plans; After the dynamic adaptive update model is established, the dynamic health management system inputs the monitored health indicators and motion data, as well as the real-time personalized health management plan into the dynamic adaptive update model to obtain a new personalized health management plan for patients with type 2 diabetic nephropathy.

[0006] As a preferred solution of the present invention, the label set includes: a patient label set corresponding to health information, a self-management label set corresponding to self-management information, a risk label set corresponding to risk level information, and a solution label set corresponding to expert consensus information, wherein: The personalized labels in the patient label set are composed of multiple health information elements with clear representativeness and discrimination; The personalized labels in the self-management label set consist of individual self-management behaviors on the ability and motivation dimensions of the Fogg health behavior model; The personalized labels in the risk label set are composed of various levels of the risk of type 2 diabetic nephropathy predicted by the type 2 diabetic nephropathy risk prediction model; The personalized labels in the protocol label set are composed of the core points of type 2 diabetic nephropathy management extracted from domestic and international literature, guidelines and expert consensus.

[0007] As a preferred embodiment of the present invention, a method for constructing a risk prediction model for type 2 diabetic nephropathy comprises: The multivariate Logistic regression model was used to analyze the influencing factors of type 2 diabetic nephropathy and screen out the characteristic factors that have a significant impact on the onset of type 2 diabetic nephropathy. Conduct principal component analysis on each characteristic factor to obtain the contribution of the characteristic factor; Based on the contribution of the characteristic factors, the characteristic weights used to centralize the characteristic factors are determined; Based on the contribution of the characteristic factors, determining the characteristic weights for decentralizing the characteristic factors; A game is played between the feature weights after decentralized processing and the feature weights after centralized processing to obtain the optimal feature weights; Based on the characteristic factors weighted by the optimal characteristic weights, a risk prediction model for type 2 diabetic nephropathy was constructed; The risk prediction model for type 2 diabetic nephropathy is: ; In the formula, Score is the risk score, are the optimal feature weights of the 1st, 2nd, and nth feature factors respectively, They are the 1st, 2nd, and nth feature factors respectively, and CNN is a convolutional neural network.

[0008] As a preferred solution of the present invention, a method for determining feature weights after centralization processing includes: The contribution of the characteristic factor is normalized and used as the characteristic weight after the characteristic factor is centralized. The normalization of feature weights after centralization is: ; In the formula, After centralized processing i The feature weight of each feature factor, For the i The contribution of the characteristic factors, is the contribution set of each characteristic factor, for The minimum value in The maximum value in ; Methods for determining feature weights after decentralized processing include: The contribution of the characteristic factor is processed inversely, and the contribution after the inverse processing is normalized as the characteristic weight of the characteristic factor after decentralized processing; The inverse and normalized processing of the feature weight after centralization is: ; In the formula, After decentralization i The feature weight of each feature factor, For the i The contribution of the characteristic factors, is the inverse set of contribution of each characteristic factor, The minimum value in The maximum value in , n is the total number of feature factors, min is the minimum operator, and max is the maximum operator. As a preferred solution of the present invention, the method for determining the optimal feature weight includes: The game theory centralized model is used to optimize the feature weights after decentralized processing and the feature weights after centralized processing. The decision model of the optimal feature weights is derived from the optimization goal of minimizing the weight deviation. The decision model of the optimal feature weights is: ; In the formula, F is the objective function value, min is the minimum operator, x is the identifier of w and v, for The linear coefficient of , T is the transposition operator; the decision model is transformed and solved using the optimal first-order derivative condition, and the solution equation for the optimal feature weight is obtained as follows: ; Solve the equation and normalize it to get the optimal feature weight, which is: ; ; In the formula, is the set of optimal feature weights of each feature factor, After normalization , is a set of linear coefficients, for The minimum value in The maximum value in .

[0009] As a preferred embodiment of the present invention, the method for determining each level of risk of developing type 2 diabetic nephropathy includes: The risk score output by the risk prediction model for type 2 diabetic nephropathy was compared with the threshold range of risk level, where: When the risk score output by the risk prediction model for type 2 diabetic nephropathy is within the threshold range of the high risk level, the risk score corresponds to the high risk level; When the risk score output by the risk prediction model for type 2 diabetic nephropathy is within the threshold range of the medium risk level, the risk score corresponds to the medium risk level; When the risk score output by the risk prediction model for the onset of type 2 diabetic nephropathy is within the threshold range of the low risk level, the risk score corresponds to the low risk level; The method for determining the threshold range includes: The risk score range of the top 25% of all cases in the case data of type 2 diabetic nephropathy used to construct the disease risk prediction model is classified as the threshold range of the high risk level, the risk score range of the middle 50% is classified as the threshold range of the medium risk level, and the risk score range of the bottom 25% is classified as the threshold range of the low risk level.

[0010] As a preferred embodiment of the present invention, a method for matching a new personalized health management plan for patients with type 2 diabetic nephropathy using the adjusted new personalized label includes: Dynamically update the personalized labels in the patient label set and the self-management label set corresponding to the health indicators and the action data of the real-time personalized health management method, and combine the personalized labels in the scheme label set and the risk label set to obtain new personalized labels for patients with type 2 diabetic nephropathy; New personalized labels of patients with type 2 diabetic nephropathy are newly matched with each label set of the personalized health management plan to obtain a new personalized health management plan.

[0011] As a preferred solution of the present invention, a method for constructing a dynamic adaptive update model of a personalized health management solution includes: The health indicators, motion data of the real-time personalized health management plan, and the real-time personalized health management plan are used as input items of the neural network, and the new personalized health management plan is used as the output of the neural network; Based on the loss function, the neural network is updated to obtain the dynamic adaptive update model: ; Where, Fnew is the new personalized health management plan, S and D are the health indicators and execution data of the current personalized health management plan, F is the current personalized health management plan, and CNN is the neural network; The loss function of the dynamic adaptive update model is: ; Where Loss is the loss function value, Snew and Dnew are the health indicators and execution data of the new personalized health management plan, max is the maximum operator, and min is the minimum operator. All are L2 norm forms.

[0012] As a preferred embodiment of the present invention, the present invention provides a dynamic health management system based on diabetic nephropathy, which is applied to a dynamic health management method based on diabetic nephropathy. The system includes: A data preprocessing unit, for dividing the influencing factors of the personalized health management plan of patients with type 2 diabetic nephropathy into multiple label sets, and matching each label set with a personalized label that reflects the personalized characterization of the patients with type 2 diabetic nephropathy in terms of the influencing factors, wherein the influencing factors include the health information, self-management information, risk level information and expert consensus information of the patients with type 2 diabetic nephropathy, the health information, self-management information and expert consensus information are all directly collected by the system, and the risk level information is indirectly calculated by a pre-established risk prediction model for the onset of type 2 diabetic nephropathy; A program initialization unit, used for obtaining real-time personalized tags of patients with type 2 diabetic nephropathy on various tag sets, and matching the real-time personalized health management program of patients with type 2 diabetic nephropathy based on the real-time personalized tags of patients with type 2 diabetic nephropathy on various tag sets; A dynamic monitoring unit, used to monitor the action data of the type 2 diabetic nephropathy patient executing the real-time personalized health management program, and to monitor the health indicators of the type 2 diabetic nephropathy patient after the real-time personalized health management program is executed; A program updating unit, configured to dynamically adjust the real-time personalized label of the patient with type 2 diabetic nephropathy based on the fed-back health index and the action data to obtain a new personalized label, and use the adjusted new personalized label to match a new personalized health management program for the patient with type 2 diabetic nephropathy; A deep learning unit, which is used to establish health indicators and action data of a real-time personalized health management plan using a neural network, as well as a mapping relationship between the real-time personalized health management plan and a new personalized health management plan, to obtain a dynamic adaptive update model of the personalized health management plan; The scheme adaptation unit is used to input the monitored health indicators and action data, as well as the real-time personalized health management scheme into the dynamic adaptive update model after the dynamic adaptive update model is established, so as to obtain a new personalized health management scheme for patients with type 2 diabetic nephropathy.

[0013] As a preferred embodiment of the present invention, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, a dynamic health management method based on diabetic nephropathy is implemented.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention determines a label set corresponding to influencing factors of a personalized health management program for patients with type 2 diabetic nephropathy, and accurately adapts to the personalized health management program of patients with type 2 diabetic nephropathy through the personalized labels of the patients with type 2 diabetic nephropathy in each label set, realizes unified standard health management program matching based on combined personalized labels, dynamically adjusts the personalized health management program of patients with type 2 diabetic nephropathy based on the health indicators and the execution data, realizes timely updating of the health management program as the individual conditions of the patients are updated, and ensures the timeliness of health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0016] Figure 1 A flow chart of a dynamic health management method based on diabetic nephropathy provided by an embodiment of the present invention; Figure 2 A block diagram of a dynamic health management system based on diabetic nephropathy provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the present invention provides a dynamic health management method based on diabetic nephropathy, comprising the following steps: In the dynamic health management system, the influencing factors of the personalized health management plan of patients with type 2 diabetic nephropathy are divided into multiple label sets, and each label set is matched with a personalized label that reflects the personalized representation of the influencing factors of patients with type 2 diabetic nephropathy. Among them, the influencing factors include the health information, self-management information, risk level information and expert consensus information of patients with type 2 diabetic nephropathy. The health information, self-management information and expert consensus information are all directly collected by the system, and the risk level information is indirectly calculated through the pre-established type 2 diabetic nephropathy risk prediction model. The dynamic health management system obtains the real-time personalized labels of type 2 diabetic nephropathy patients on various label sets, and matches the real-time personalized health management plan of type 2 diabetic nephropathy patients based on the real-time personalized labels of type 2 diabetic nephropathy patients on various label sets; The dynamic health management system monitors the action data of patients with type 2 diabetic nephropathy who implement the real-time personalized health management plan, and monitors the health indicators of patients with type 2 diabetic nephropathy after the implementation of the real-time personalized health management plan; The dynamic health management system dynamically adjusts the real-time personalized labels of patients with type 2 diabetic nephropathy based on the feedback health indicators and action data to obtain new personalized labels, and uses the adjusted new personalized labels to match new personalized health management plans for patients with type 2 diabetic nephropathy; The dynamic health management system uses neural networks to establish health indicators and action data of real-time personalized health management plans, as well as the mapping relationship between real-time personalized health management plans and new personalized health management plans, to obtain a dynamic adaptive update model of personalized health management plans; After the dynamic adaptive update model is established, the dynamic health management system will input the monitored health indicators and motion data, as well as the real-time personalized health management plan into the dynamic adaptive update model to obtain a new personalized health management plan for patients with type 2 diabetic nephropathy.

[0019] In the present invention, various influencing factors of the personalized health management plan for patients with type 2 diabetic nephropathy are divided into multiple label sets, and each label set is matched with a personalized label that reflects the personalized characterization of the influencing factors of patients with type 2 diabetic nephropathy, so as to achieve the matching of personalized labels in the label set, determine the health management plan suitable for patients with type 2 diabetic nephropathy, match management content plans of different degrees and different focuses for patients with different characteristics, and the personalized health management plan can ensure that patients with type 2 diabetic nephropathy reap health benefits.

[0020] As shown in the figure, the label set includes: a patient label set corresponding to health information, a self-management label set corresponding to self-management information, a risk label set corresponding to risk level information, and a scheme label set corresponding to expert consensus information, wherein: The personalized labels in the patient label set are composed of multiple health information elements with clear representativeness and differentiation. The personalized labels in the specific patient label set include gender, age, race, marital status, education level, current medical history, past medical history, family history, medication history, smoking habits, drinking habits, exercise habits, sleep conditions, height, weight, blood pressure, blood sugar, cholesterol, AIC, eGFR, urine biochemistry and other labels; The personalized labels in the self-management label set are composed of various self-management behaviors on the ability and motivation dimensions of Fogg's health behavior model. Specifically, the personalized labels in the self-management label set include high ability and low motivation for diet, high ability and low motivation for exercise, high ability and low motivation for taking medicine, high ability and low motivation for alcohol restriction, high ability and low motivation for smoking cessation, high ability and low motivation for emotion, high ability and high motivation for diet, high ability and high motivation for exercise, high ability and high motivation for taking medicine, high ability and high motivation for alcohol restriction, high ability and high motivation for smoking cessation, high ability and high motivation for emotion, low ability and low motivation for diet, low ability and low motivation for exercise, low ability and low motivation for taking medicine, low ability and low motivation for alcohol restriction, low ability and low motivation for smoking cessation, low ability and low motivation for emotion, low ability and high motivation for diet, low ability and high motivation for exercise, low ability and high motivation for taking medicine, low ability and high motivation for alcohol restriction, low ability and low motivation for smoking cessation, low ability and low motivation for emotion, low ability and high motivation for diet, low ability and high motivation for exercise, low ability and high motivation for taking medicine, low ability and high motivation for alcohol restriction, low ability and high motivation for smoking cessation, and low ability and high motivation for emotion; The personalized labels in the risk label set are composed of various levels of type 2 diabetic nephropathy risk predicted by the type 2 diabetic nephropathy risk prediction model, including: high risk level, medium risk level and low risk level; The personalized labels in the program label set are composed of the core points of type 2 diabetic nephropathy management extracted from domestic and foreign literature, guidelines and expert consensus. Specific personalized labels include blood sugar monitoring, low GI diet, prevention of complications, smoking cessation and alcohol restriction, emotion management, taking medication on time, blood pressure monitoring, low oil and salt, regular exercise, kidney function monitoring, moderate protein, and regular life.

[0021] The present invention labels various influencing factors of the personalized health management plan for patients with type 2 diabetic nephropathy, and divides them into a plan label set, a risk label set, a self-management label set and a patient label set, and utilizes the positioning matching of personalized labels in the label set to achieve the effect of matching a personalized health management plan for patients with type 2 diabetic nephropathy.

[0022] The personalized labels of patients with type 2 diabetic nephropathy in the present invention can display individual information of patients in multiple aspects. Matching health management plans with this label can achieve high adaptability between the plan and the individual patient. For example, the individual information of the patient who does not control his diet will be matched with a low-motivation, high-ability and low-risk plan for diet; the patient's irregular drug treatment will be matched with a low-motivation, low-ability and high-risk plan for drugs; the patient's failure to quit smoking effectively will be matched with a high-motivation, low-ability and medium-risk plan for smoking; the patient's lack of exercise will be matched with a low-motivation, low-ability and medium-risk plan for exercise, and so on.

[0023] The present invention achieves unified standard health management program matching based on combined personalized tags, eliminates the need for subjective health management that relies on experience, and ensures the objectivity of health management program formulation.

[0024] Furthermore, the present invention promotes self-management of research subjects from three dimensions of motivation, ability and triggering based on the Fogg health behavior model, through two modules: a monitoring module and an interactive module. Among them, the monitoring module: links multiple monitoring devices (combining wearable devices, home monitoring devices, and hospital follow-up medical records) to form a cloud data ecosystem, and collects patients' health indicators (such as blood sugar, blood pressure, and weight) and interactive data (such as frequency of use and feedback information) in real time.

[0025] Interaction module: Research subjects can view and record their health status at any time, and complete reminders, records, and clock-ins through the artificial intelligence question-and-answer system. The platform pushes personalized health education content and feedback based on monitoring and clock-in results, supporting patients to obtain comprehensive support for motivation, ability, and triggers in their daily lives. The status of the patient's personalized combination label can change dynamically over time and interaction. After each follow-up, the health management plan for the patient's health intervention is adjusted based on the updated status of the patient's personalized combination label, thereby dynamically adjusting the personalized health management plan for patients with type 2 diabetic nephropathy based on the patient's health indicators and health management clock-ins and interactive execution data, and timely updating of the health management plan as the patient's individual situation is updated to ensure the timeliness of health management.

[0026] The above can dynamically adjust the personalized health management plan for patients with type 2 diabetic nephropathy, and realize timely updating of the health management plan as the patient's individual condition is updated. However, processes such as patient label analysis and plan matching are still required. In order to further improve the efficiency of plan updates and further ensure timeliness, the present invention constructs a dynamic adaptive update model for health management plans, which predicts new personalized health management plans based on the health indicators and execution data of the current personalized health management plan, as well as the current personalized health management plan, realizes the automated model update of personalized health management plans, and simplifies the process of repeated label analysis and repeated plan matching.

[0027] Moreover, when constructing a dynamic adaptive update model for a health management program, the present invention The combination is taken as the loss, where The health indicators and execution data of the new personalized health management plan have changed greatly from those of the current personalized health management plan, indicating that the health indicators and execution data obtained after the personalized health management plan is adjusted have changed to the greatest extent, that is, it is most suitable for patient health management and the health management improvement effect is best. There are relatively small changes between the new personalized health management plan and the current personalized health management plan, which means that small-scale adjustments are made on the basis of the current personalized health management plan to ensure that patients can adapt to the new adjustments painlessly. The combination of the two parts can minimize the adjustments to the current personalized health management plan to obtain a new personalized health management plan that is most suitable for the current patient's condition.

[0028] The method for predicting the risk level of type 2 diabetic nephropathy is: Multivariate Logistic regression model was used to analyze the influencing factors of type 2 diabetic nephropathy, and the characteristic factors with significant influence on the incidence of type 2 diabetic nephropathy were screened out. The influencing factors included: demographic characteristics, clinical information, laboratory tests, renal puncture pathological results, physical examination, lifestyle, drug use, past medical history and family history, socioeconomic status, and emotional state. Conduct principal component analysis on each characteristic factor to obtain the contribution of the characteristic factor; Based on the contribution of the characteristic factors, the characteristic weights used to centralize the characteristic factors are determined; Based on the contribution of the characteristic factors, determining the characteristic weights for decentralizing the characteristic factors; A game is played between the feature weights after decentralized processing and the feature weights after centralized processing to obtain the optimal feature weights; Based on the characteristic factors weighted by the optimal characteristic weights, a risk prediction model for type 2 diabetic nephropathy was constructed.

[0029] The screening methods of characteristic factors include: SPSS26.0 and RStudio4.2.2 software were used to analyze the case data of type 2 diabetic nephropathy. The quantitative data that met the normal distribution were expressed as mean ± standard deviation. The qualitative data that did not conform to the normal distribution were expressed as frequency and percentage (%); the differences in the influencing factors between patients with non-type 2 diabetic nephropathy and patients with type 2 diabetic nephropathy were compared. The quantitative data with normal distribution were compared between the groups using t-test, and the qualitative data that did not conform to the normal distribution were compared between the groups using χ2 test and rank sum test. The difference was statistically significant; Logistic regression analysis was used to screen the influencing factors, with the test level α=0.05, and the screened influencing factors were used as characteristic factors.

[0030] Methods for determining feature weights after centralization include: The contribution of the characteristic factor is normalized and used as the characteristic weight after the characteristic factor is centralized. The normalization of feature weights after centralization is: ; In the formula, After centralized processing i The feature weight of each feature factor, For the i The contribution of the characteristic factors, is the contribution set of each characteristic factor, for The minimum value in The maximum value in .

[0031] Methods for determining feature weights after decentralized processing include: The contribution of the characteristic factor is processed inversely, and the contribution after the inverse processing is normalized as the characteristic weight of the characteristic factor after decentralized processing; The inverse and normalized processing of the feature weight after centralization is: ; In the formula, After decentralization i The feature weight of each feature factor, For the i The contribution of the characteristic factors, is the inverse set of contribution of each characteristic factor, The minimum value in The maximum value in , n is the total number of feature factors, min is the minimum operator, and max is the maximum operator. The method for determining the optimal feature weight includes: The game theory centralized model is used to optimize the feature weights after decentralized processing and the feature weights after centralized processing. The decision model of the optimal feature weights is derived from the optimization goal of minimizing the weight deviation. The decision model of the optimal feature weights is: ; In the formula, F is the objective function value, min is the minimum operator, x is the identifier of w and v, for The linear coefficient of , T is the transposition operator; The decision model is transformed and solved using the optimal first-order derivative condition, and the solution equation for the optimal feature weight is obtained as follows: ; Solve the equation and normalize it to get the optimal feature weight, which is: ; ; In the formula, is the set of optimal feature weights of each feature factor, After normalization is a set of linear coefficients, for The minimum value in The maximum value in .

[0032] The risk prediction model for type 2 diabetic nephropathy was constructed as follows: ; In the formula, Score is the risk score, are the optimal feature weights of the 1st, 2nd, and nth feature factors respectively, are the 1st, 2nd, and nth characteristic factors respectively, and CNN is a convolutional neural network; the methods for determining the various levels of the risk of type 2 diabetic nephropathy include: The risk score output by the risk prediction model for type 2 diabetic nephropathy was compared with the threshold range of risk level, where: When the risk score output by the risk prediction model for type 2 diabetic nephropathy is within the threshold range of the high risk level, the risk score corresponds to the high risk level; When the risk score output by the risk prediction model for type 2 diabetic nephropathy is within the threshold range of the medium risk level, the risk score corresponds to the medium risk level; When the risk score output by the risk prediction model for the onset of type 2 diabetic nephropathy is within the threshold range of the low risk level, the risk score corresponds to the low risk level; The method for determining the threshold range includes: The top 25% of the risk score range of all cases in the case data of type 2 diabetic nephropathy used to construct the risk prediction model for the onset of disease was designated as the threshold range for high risk, the middle 50% of the risk score range was designated as the threshold range for medium risk, and the bottom 25% of the risk score range was designated as the threshold range for low risk.

[0033] Methods for using the adjusted new personalized signature to match new personalized health management programs for patients with type 2 diabetic nephropathy include: The health indicators and action data of the real-time personalized health management method are dynamically updated in the patient label set and the self-management label set, and the personalized labels in the program label set and the risk label set are combined to obtain new personalized labels for patients with type 2 diabetic nephropathy; The new personalized labels of patients with type 2 diabetic nephropathy are newly matched with each label set of the personalized health management plan to obtain a new personalized health management plan.

[0034] The present invention constructs a dynamic adaptive update model for health management plans, predicts new personalized health management plans based on the health indicators and execution data of the current personalized health management plan, and the current personalized health management plan, realizes the automated model update of personalized health management plans, and summarizes the process of repeated label analysis and repeated matching of plans, as follows: The method for constructing a dynamic adaptive updating model of a personalized health management program of the present invention includes: The health indicators, motion data of the real-time personalized health management plan, and the real-time personalized health management plan are used as input items of the neural network, and the new personalized health management plan is used as the output of the neural network; Based on the loss function, the neural network is updated dynamically and adaptively, and the model is: Fnew=CNN(S,D,F); Where, Fnew is the new personalized health management plan, S and D are the health indicators and execution data of the current personalized health management plan, F is the current personalized health management plan, and CNN is the neural network; The loss function for training the dynamic adaptive update model of the health management solution is: ; In the formula, Loss is the loss function value, Snew and Dnew are the health indicators and execution data of the new personalized health management plan, max is the maximum operator, and min is the minimum operator. All are L2 norm forms.

[0035] When constructing a dynamic adaptive update model for a health management program, the present invention and The combination is taken as the loss, where There are large changes between the health indicators and execution data of the new personalized health management plan and the health indicators and execution data of the current personalized health management plan, which means that the health indicators and execution data obtained after the adjustment of the personalized health management plan have changed to the greatest extent, that is, it is most suitable for the patient's health management and the health management improvement effect is best. Min is that there is a small change between the new personalized health management plan and the current personalized health management plan, which means that small-scale adjustments are made on the basis of the current personalized health management plan to ensure that patients can adapt to the new adjustments painlessly. The combination of the two parts can achieve the minimum adjustment of the current personalized health management plan to obtain a new personalized health management plan that is most suitable for the current patient's situation.

[0036] The present invention provides a research method for dynamic health management, comprising: Research design and subjects: A randomized controlled trial design was adopted. Relying on the hospital platform, 600 patients diagnosed with type 2 diabetes were randomly selected. Based on the pre-constructed risk prediction model for type 2 diabetic nephropathy, the risk of disease in the research subjects was predicted and graded. The subjects were matched 1:1 according to gender, age and risk of disease and randomly divided into personalized dynamic management group (n=200), conventional management group (n=200) and control group (n=200).

[0037] Baseline data collection: Five categories of baseline data were collected, including basic information (age, gender, occupation, etc.), clinical data (diabetes course, medication use, etc.), lifestyle habits (diet, smoking, drinking, physical activity, etc.), physiological indicators (blood sugar, blood pressure, renal function, etc.), and health behavior triggers (using questionnaires to assess behavioral stages, decision-making balance, and self-efficacy).

[0038] Follow-up survey: Each group of patients was followed up every 6 months for 24 months, a total of 4 times. The survey content was the same as the baseline.

[0039] Research outcomes: Health behavior triggers: health behavior stage, decision-making balance, and self-efficacy; blood sugar control and renal function: urine albumin-creatinine ratio, glomerular filtration rate, glycated hemoglobin, and fasting blood sugar.

[0040] Routine management group: The routine management group regularly pushes health education content through the health app, distributes standardized health education manuals, covers the basic knowledge of diabetes and type 2 diabetic nephropathy, and provides general health guidance. Patients are encouraged to record their health behaviors and check in, but no personalized support or continuous feedback is provided.

[0041] Control group: The control group received only minimal intervention. The subjects received diagnosis and follow-up according to the hospital's routine procedures, and only basic health information and health guidance were provided during diagnosis and treatment, without special monitoring tools or self-management support. Follow-up data of patients in the control group were limited to the routine medical record system.

[0042] Data analysis: Compare the changes in various outcome indicators among the three groups during the follow-up period to evaluate the effect of dynamic management mode or program on diabetic nephropathy intervention. The main analysis methods include repeated measures analysis of variance and mixed effects model, which are used to detect the significance of differences between the groups and to compare the effectiveness of health management programs on patients.

[0043] like Figure 2 As shown, the present invention provides a dynamic health management system based on diabetic nephropathy, which is applied to a dynamic health management method based on diabetic nephropathy. The system includes: A data preprocessing unit is used to divide the influencing factors of the personalized health management plan of patients with type 2 diabetic nephropathy into multiple label sets, and match each label set with a personalized label that reflects the personalized representation of the influencing factors of patients with type 2 diabetic nephropathy, wherein the influencing factors include the health information, self-management information, risk level information and expert consensus information of patients with type 2 diabetic nephropathy, the health information, self-management information and expert consensus information are all directly collected by the system, and the risk level information is indirectly calculated through a pre-established risk prediction model for the onset of type 2 diabetic nephropathy; A program initialization unit, used for obtaining real-time personalized tags of patients with type 2 diabetic nephropathy on various tag sets, and matching the real-time personalized health management program of patients with type 2 diabetic nephropathy based on the real-time personalized tags of patients with type 2 diabetic nephropathy on various tag sets; A dynamic monitoring unit, used to monitor the action data of patients with type 2 diabetic nephropathy who implement a real-time personalized health management program, and to monitor the health indicators of patients with type 2 diabetic nephropathy after the implementation of the real-time personalized health management program; A program updating unit, which is used to dynamically adjust the real-time personalized labels of patients with type 2 diabetic nephropathy based on the feedback health indicators and action data to obtain new personalized labels, and use the adjusted new personalized labels to match new personalized health management programs for patients with type 2 diabetic nephropathy; A deep learning unit, which is used to establish health indicators and action data of a real-time personalized health management plan using a neural network, as well as a mapping relationship between the real-time personalized health management plan and a new personalized health management plan, to obtain a dynamic adaptive update model of the personalized health management plan; The solution adaptation unit is used to input the monitored health indicators and action data, as well as the real-time personalized health management plan into the dynamic adaptive update model after the dynamic adaptive update model is established, so as to obtain a new personalized health management plan for patients with type 2 diabetic nephropathy.

[0044] The present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, a dynamic health management method based on diabetic nephropathy is implemented.

[0045] The present invention determines a label set corresponding to influencing factors of a personalized health management program for patients with type 2 diabetic nephropathy, and accurately adapts to the personalized health management program for patients with type 2 diabetic nephropathy through the personalized labels of the patients with type 2 diabetic nephropathy in each label set, realizes unified standard health management program matching based on combined personalized labels, dynamically adjusts the personalized health management program for patients with type 2 diabetic nephropathy based on health indicators and execution data, realizes timely updating of the health management program as the individual conditions of the patients are updated, and ensures the timeliness of health management.

[0046] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A dynamic health management method based on diabetic nephropathy, characterized in that: The following steps are involved: In the dynamic health management system, the influencing factors of the personalized health management plan of patients with type 2 diabetic nephropathy are divided into multiple label sets, and each label set is matched with a personalized label that reflects the personalized characterization of the influencing factors of patients with type 2 diabetic nephropathy, wherein the influencing factors include the health information, self-management information, risk level information and expert consensus information of the patients with type 2 diabetic nephropathy, the health information, self-management information and expert consensus information are all directly collected by the system, and the risk level information is indirectly calculated by a pre-established risk prediction model for the onset of type 2 diabetic nephropathy; The dynamic health management system obtains the real-time personalized labels of type 2 diabetic nephropathy patients on various label sets, and matches the real-time personalized health management plan of type 2 diabetic nephropathy patients based on the real-time personalized labels of type 2 diabetic nephropathy patients on various label sets; The dynamic health management system monitors the action data of the type 2 diabetic nephropathy patient executing the real-time personalized health management program, and monitors the health indicators of the type 2 diabetic nephropathy patient after the real-time personalized health management program is executed; The dynamic health management system dynamically adjusts the real-time personalized label of the type 2 diabetic nephropathy patient based on the fed-back health index and the action data to obtain a new personalized label, and uses the adjusted new personalized label to match a new personalized health management plan for the type 2 diabetic nephropathy patient; The dynamic health management system uses neural networks to establish health indicators and action data of real-time personalized health management plans, as well as the mapping relationship between real-time personalized health management plans and new personalized health management plans, to obtain a dynamic adaptive update model of personalized health management plans; After the dynamic adaptive update model is established, the dynamic health management system inputs the monitored health indicators and motion data, as well as the real-time personalized health management plan into the dynamic adaptive update model to obtain a new personalized health management plan for patients with type 2 diabetic nephropathy.

2. A dynamic health management method based on diabetic nephropathy according to claim 1, characterized in that: The label set includes: a patient label set corresponding to health information, a self-management label set corresponding to self-management information, a risk label set corresponding to risk level information, and a scheme label set corresponding to expert consensus information, wherein: The personalized labels in the patient label set are composed of multiple health information elements with clear representativeness and discrimination; The personalized labels in the self-management label set consist of individual self-management behaviors on the ability and motivation dimensions of the Fogg health behavior model; The personalized labels in the risk label set are composed of various levels of the risk of type 2 diabetic nephropathy predicted by the type 2 diabetic nephropathy risk prediction model; The personalized labels in the protocol label set are composed of the core points of type 2 diabetic nephropathy management extracted from domestic and international literature, guidelines and expert consensus.

3. A dynamic health management method based on diabetic nephropathy according to claim 2, characterized in that: The method for constructing a risk prediction model for type 2 diabetic nephropathy includes: The multivariate Logistic regression model was used to analyze the influencing factors of type 2 diabetic nephropathy and screen out the characteristic factors that have a significant impact on the onset of type 2 diabetic nephropathy. Conduct principal component analysis on each characteristic factor to obtain the contribution of the characteristic factor; Based on the contribution of the characteristic factors, the characteristic weights used to centralize the characteristic factors are determined; Based on the contribution of the characteristic factors, determining the characteristic weights for decentralizing the characteristic factors; A game is played between the feature weights after decentralized processing and the feature weights after centralized processing to obtain the optimal feature weights; Based on the characteristic factors weighted by the optimal characteristic weights, a risk prediction model for type 2 diabetic nephropathy was constructed; The risk prediction model for type 2 diabetic nephropathy is: ; In the formula, Score is the risk score, are the optimal feature weights of the 1st, 2nd, and nth feature factors respectively, They are the 1st, 2nd, and nth feature factors respectively, and CNN is a convolutional neural network.

4. A dynamic health management method based on diabetic nephropathy according to claim 3, characterized in that: Methods for determining feature weights after centralization include: The contribution of the characteristic factor is normalized and used as the characteristic weight after the characteristic factor is centralized. The normalization of feature weights after centralization is: ; In the formula, After centralized processing i The feature weight of each feature factor, For the i The contribution of the characteristic factors, is the contribution set of each characteristic factor, for The minimum value in The maximum value in ; Methods for determining feature weights after decentralized processing include: The contribution of the characteristic factor is processed inversely, and the contribution after the inverse processing is normalized as the characteristic weight of the characteristic factor after decentralized processing; The inverse and normalized processing of the feature weight after centralization is: ; In the formula, After decentralization i The feature weight of each feature factor, For the i The contribution of the characteristic factors, is the inverse set of contribution of each characteristic factor, for The minimum value in The maximum value in , n is the total number of characteristic factors, min is the minimum operator, and max is the maximum operator.

5. A dynamic health management method based on diabetic nephropathy according to claim 4, characterized in that: Methods for determining the optimal feature weights include: The game theory centralized model is used to optimize the feature weights after decentralized processing and the feature weights after centralized processing. The decision model of the optimal feature weights is derived from the optimization goal of minimizing the weight deviation. The decision model of the optimal feature weights is: ; In the formula, F is the objective function value, min is the minimum operator, x is the identifier of w and v, for The linear coefficient of , T is the transposition operator; the decision model is transformed and solved using the optimal first-order derivative condition, and the solution equation for the optimal feature weight is obtained as follows: ； Solve the equation and normalize it to get the optimal feature weight, which is: ; ; In the formula, is the set of optimal feature weights of each feature factor, After normalization , is a set of linear coefficients, for The minimum value in The maximum value in .

6. A dynamic health management method based on diabetic nephropathy according to claim 5, characterized in that: The various levels of risk for developing type 2 diabetic kidney disease are determined by: The risk score output by the risk prediction model for type 2 diabetic nephropathy was compared with the threshold range of risk level, where: When the risk score output by the risk prediction model for type 2 diabetic nephropathy is within the threshold range of the high risk level, the risk score corresponds to the high risk level; When the risk score output by the risk prediction model for type 2 diabetic nephropathy is within the threshold range of the medium risk level, the risk score corresponds to the medium risk level; When the risk score output by the risk prediction model for the onset of type 2 diabetic nephropathy is within the threshold range of the low risk level, the risk score corresponds to the low risk level; The method for determining the threshold range includes: The risk score range of the top 25% of all cases in the case data of type 2 diabetic nephropathy used to construct the disease risk prediction model is classified as the threshold range of the high risk level, the risk score range of the middle 50% is classified as the threshold range of the medium risk level, and the risk score range of the bottom 25% is classified as the threshold range of the low risk level.

7. A dynamic health management method based on diabetic nephropathy according to claim 6, characterized in that: Methods for using the adjusted new personalized signature to match new personalized health management programs for patients with type 2 diabetic nephropathy include: Dynamically update the personalized labels in the patient label set and the self-management label set corresponding to the health indicators and the action data of the real-time personalized health management method, and combine the personalized labels in the scheme label set and the risk label set to obtain new personalized labels for patients with type 2 diabetic nephropathy; New personalized labels of patients with type 2 diabetic nephropathy are newly matched with each label set of the personalized health management plan to obtain a new personalized health management plan.

8. A dynamic health management method based on diabetic nephropathy according to claim 7, characterized in that: The method for constructing a dynamic adaptive update model for a personalized health management solution includes: The health indicators, motion data of the real-time personalized health management plan, and the real-time personalized health management plan are used as input items of the neural network, and the new personalized health management plan is used as the output of the neural network; Based on the loss function, the neural network is updated to obtain the dynamic adaptive update model: ; In the formula, Fnew is the new personalized health management plan, S and D are the health indicators and execution data of the current personalized health management plan, F is the current personalized health management plan, and CNN is the neural network; The loss function of the dynamic adaptive update model is: ; In the formula, Loss is the loss function value, Snew and Dnew are the health indicators and execution data of the new personalized health management plan, max is the maximum operator, and min is the minimum operator. All are L2 norm forms.

9. A dynamic health management system based on diabetic nephropathy, characterized in that: A dynamic health management method based on diabetic nephropathy as described in any one of claims 1 to 8, the system comprising: A data preprocessing unit, for dividing the influencing factors of the personalized health management plan of patients with type 2 diabetic nephropathy into multiple label sets, and matching each label set with a personalized label that reflects the personalized characterization of the patients with type 2 diabetic nephropathy in terms of the influencing factors, wherein the influencing factors include the health information, self-management information, risk level information and expert consensus information of the patients with type 2 diabetic nephropathy, the health information, self-management information and expert consensus information are all directly collected by the system, and the risk level information is indirectly calculated by a pre-established risk prediction model for the onset of type 2 diabetic nephropathy; A program initialization unit, used for obtaining real-time personalized tags of patients with type 2 diabetic nephropathy on various tag sets, and matching the real-time personalized health management program of patients with type 2 diabetic nephropathy based on the real-time personalized tags of patients with type 2 diabetic nephropathy on various tag sets; A dynamic monitoring unit, used to monitor the action data of the type 2 diabetic nephropathy patient executing the real-time personalized health management program, and to monitor the health indicators of the type 2 diabetic nephropathy patient after the real-time personalized health management program is executed; A program updating unit, configured to dynamically adjust the real-time personalized label of the patient with type 2 diabetic nephropathy based on the fed-back health index and the action data to obtain a new personalized label, and use the adjusted new personalized label to match a new personalized health management program for the patient with type 2 diabetic nephropathy; A deep learning unit, which is used to establish health indicators and action data of a real-time personalized health management plan using a neural network, as well as a mapping relationship between the real-time personalized health management plan and a new personalized health management plan, to obtain a dynamic adaptive update model of the personalized health management plan; The scheme adaptation unit is used to input the monitored health indicators and action data, as well as the real-time personalized health management scheme into the dynamic adaptive update model after the dynamic adaptive update model is established, so as to obtain a new personalized health management scheme for patients with type 2 diabetic nephropathy.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the method according to any one of claims 1 to 8 is implemented.

Images