Chronic disease management system

Abstract

The invention belongs to the technical field of medical systems, and provides a chronic disease management system which comprises a data acquisition module which monitors physiological indexes of a patient in real time through intelligent wearable equipment and automatically uploads measurement data; the data processing and analysis module automatically uploads the collected data to a cloud server, and establishes a disease prediction and risk assessment model; the health management module formulates a personalized health management plan for the patient according to the analysis result; the remote medical module provides remote communication and consultation between a patient and a doctor; the data sharing module is used for sharing and exchanging data among different medical institutions; the interaction module provides a patient operation interaction interface and registers and records basic information and illness state records of the patient; according to the invention, by establishing the disease prediction and risk assessment model, the patient is helped to know the health condition of the patient in advance and prevent the occurrence of diseases, and according to the analysis result of the disease prediction and risk assessment model, a personalized health management plan is made for the patient to realize accurate health management.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical systems, and in particular to a chronic disease management system. Background Art

[0002] In the current medical context, chronic diseases have become a major challenge to global health, forcing the medical system to constantly seek more effective management and treatment methods. However, the existing chronic disease management system generally has some shortcomings, which restricts patients' health management capabilities and the quality of medical services;

[0003] Traditional chronic disease management systems lack the ability to deeply analyze patient health data. Although these systems are usually able to record basic physiological indicators and changes in the condition, they often lack effective algorithms and models to prospectively predict disease development and risk assessment. This causes patients and doctors to rely on experience when formulating health management plans, lacking data support, and thus failing to identify potential health risks in a timely manner, missing the best time for prevention. In addition, traditional health management programs are often "one-size-fits-all" and cannot provide precise health guidance based on the individual needs of each patient, which reduces the effectiveness of health management;

[0004] The current chronic disease management system has significant obstacles in data sharing and exchange between different medical institutions. Many systems adopt a closed data management model, which prevents information from flowing between different medical service providers, thus creating the phenomenon of "information islands". This not only hinders the continuity of medical services for patients, but also increases the possibility of repeated examinations and treatments, further wasting medical resources and reducing the quality and efficiency of medical services.

[0005] To this end, technicians in this field have proposed a chronic disease management system, which aims to enhance patients' participation and health management awareness through in-depth data analysis, real-time monitoring and effective data sharing, and achieve personalized and precise health management. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a chronic disease management system to solve the problems raised in the background technology.

[0007] A chronic disease management system, comprising:

[0008] The data acquisition module monitors the patient's physiological indicators in real time through smart wearable devices, connects them to home medical devices, and automatically uploads measurement data;

[0009] The data processing and analysis module automatically uploads the collected data to the cloud server, uses big data analysis technology to analyze the collected data, and establishes disease prediction and risk assessment models;

[0010] Health management module, which develops personalized health management plans for patients based on analysis results;

[0011] Telemedicine module, which is used to provide remote communication and consultation between patients and doctors. Doctors can check patient data and adjust management plans at any time, and patients can also consult doctors about health problems at any time.

[0012] Data sharing module, which is used to share and exchange data between different medical institutions to provide continuous medical services for patients;

[0013] The interactive module is used to provide patients with an interactive interface for operation and to register and record basic patient information and medical records.

[0014] Preferably, the smart wearable devices in the data acquisition module include smart bracelets and smart watches, the home medical devices include home blood pressure monitors and blood glucose meters, and the physiological indicators include heart rate, blood pressure, and blood glucose.

[0015] Preferably, the data processing and analysis module pre-processes the collected data and selects physiological indicators, lifestyle, and family history as features to establish a disease prediction model by constructing a training set. where x i ∈R d is the feature vector, y i ∈{-1,+1} is the category label, by finding an optimal hyperplane ω T x+b=0, and the optimization problem is expressed as:

[0016]

[0017] Among them, w represents the normal vector of the hyperplane, b represents the intercept, and x i Represents the feature vector of the i-th sample, including physiological indicators, lifestyle, family history, y i Represents the category label of the i-th sample, with a value of +1 or -1, maximizing the interval while minimizing the loss function and satisfying its constraints so that each data point is correctly classified and the distance from the decision boundary is at least 1;

[0018] Introducing the kernel function K(x i ,x j ), the original feature space is mapped to a high-dimensional space, and the optimization problem becomes:

[0019]

[0020] Among them, ξ i represents the slack variable used to deal with the inseparable situation, C represents the penalty parameter used to control the trade-off between interval maximization and classification error, φ(xi ) represents the feature mapping function, which is used to transform the input sample x i Mapping to a higher dimensional space;

[0021] The model output is: f(x) = sign(w T φ(x)+b), where f(x) represents the output function of the model, which is used to predict the category of the new sample x, and sign(·) represents the sign function, which is used to map real numbers to category labels.

[0022] Preferably, the risk assessment model is obtained by calculating the decision value f(x) and using logistic regression to fit the relationship between the decision function value and the true label: Where A and B are the parameters obtained in logistic regression;

[0023] After obtaining the predicted probability of each sample, a risk threshold is set to distinguish the risk level. If P(y=1|x)≤0.3, the sample is marked as low risk; if 0.3<P(y=1|x)≤0.7, the sample is marked as medium risk; if P(y=1|x)>0.7, the sample is marked as high risk.

[0024] Preferably, the health management module customizes a health management plan according to the risk assessment level of the sample patient:

[0025] Closely monitor high-risk patients, conduct regular health checks and monitoring, and provide personalized interventions on diet and exercise, adjust medications based on the patient's condition, and regularly evaluate the effects and side effects of medications;

[0026] For medium-risk patients, educational materials and lectures are used to enhance patients’ health awareness, allowing them to self-monitor, set regular follow-up time points, evaluate changes in health status and the effectiveness of management plans, and make adjustments;

[0027] Provide preventive advice to low-risk patients, maintain healthy eating and exercise habits, and have regular physical examinations;

[0028] Regularly collect patients' health data, monitor changes in their health status, evaluate the effectiveness of health management plans based on patients' feedback and changes in health indicators, and collect patients' feedback through interactive modules.

[0029] Preferably, the telemedicine module provides a video call function, allowing patients to communicate with doctors face to face to discuss health problems and treatment plans, and a chat function is set up to allow patients to communicate with doctors in text, handle health consultations or discomfort feedback, and build communication files, in which all consultation records and feedback are recorded.

[0030] Preferably, the data sharing module uniformly formats the patient's medical records, laboratory results, and imaging data, exchanges and integrates data in real time through a middleware platform, and builds a centralized cloud database to store the patient's health records and data, and conducts data sharing and exchange between different medical institutions.

[0031] Preferably, the interactive module records basic personal information through active registration by the patient, establishes a unique identity for the patient, and records and collects the patient's family medical history information, patient diagnosis information and medication status, adds a real-time information verification mechanism to ensure that the input data format is correct, and provides instant feedback.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The present invention establishes a disease prediction and risk assessment model by conducting in-depth analysis of the collected data to help patients understand their health status in advance and prevent the occurrence of diseases; and based on the analysis results of the disease prediction and risk assessment model, formulates a personalized health management plan for the patient, including suggestions on diet, exercise, drug adjustment, etc., to achieve precise health management.

[0034] 2. The present invention monitors the patient's physiological indicators in real time through smart wearable devices and home medical devices, and automatically uploads the measurement data to ensure the timeliness and accuracy of the data; and provides remote communication and consultation functions between patients and doctors, so that patients can consult doctors about health problems at any time, and doctors can also view patient data and adjust management plans at any time.

[0035] 3. The present invention realizes data sharing and exchange between different medical institutions, provides patients with continuous medical services, avoids information islands, and improves the quality of medical services; and through the interactive module, patients can actively register and record their personal basic information and medical records, thereby improving patients' participation and health management awareness. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a block diagram of the chronic disease management system of the present invention. DETAILED DESCRIPTION

[0037] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0038] As attached Figure 1 As shown:

[0039] Embodiment 1: The present invention provides a chronic disease management system, comprising: a data acquisition module, which monitors the patient's physiological indicators in real time through smart wearable devices, connects them to home medical devices, and automatically uploads measurement data; a data processing and analysis module, which automatically uploads the collected data to a cloud server, uses big data analysis technology to analyze the collected data, and establishes a disease prediction and risk assessment model; a health management module, which formulates a personalized health management plan for the patient based on the analysis results; a telemedicine module, which is used to provide remote communication and consultation between patients and doctors, and doctors can view patient data and adjust management plans at any time, and patients can also consult doctors about health problems at any time; a sharing module, which shares and exchanges data between different medical institutions, and is used to provide patients with continuous medical services; an interactive module, which is used to provide a patient operation interactive interface, and register and record patient basic information and medical records.

[0040] In the data acquisition module, smart wearable devices include smart bracelets and smart watches, home medical devices include home blood pressure monitors and blood glucose meters, and physiological indicators include heart rate, blood pressure, and blood glucose. Through smart wearable devices such as smart watches and health bracelets, the patient's heart rate, blood pressure, blood glucose, number of steps and other physiological indicators are monitored in real time, connected to home blood pressure monitors, blood glucose meters and other devices, and the patient's measurement results are automatically uploaded to reduce the errors and inconveniences of manual input, ensuring that the real-time collected data can be quickly and accurately transmitted to the system background, providing a basis for subsequent analysis and processing.

[0041] The data processing and analysis module pre-processes the collected data and selects physiological indicators, lifestyle, and family medical history as features. It builds a disease prediction model based on historical data and real-time monitoring results. where x i ∈R d is the feature vector, y i ∈{-1,+1} is the category label, by finding an optimal hyperplane ω T x+b=0, and the optimization problem is expressed as:

[0042]

[0043] Among them, w represents the normal vector of the hyperplane, b represents the intercept, and x i Represents the feature vector of the i-th sample, including physiological indicators, lifestyle, family history, y i Represents the category label of the i-th sample, with a value of +1 or -1, maximizing the interval while minimizing the loss function and satisfying its constraints so that each data point is correctly classified and the distance from the decision boundary is at least 1;

[0044] Introducing the kernel function K(x i ,x j), the original feature space is mapped to a high-dimensional space, and the optimization problem becomes:

[0045]

[0046] Among them, ξ i represents the slack variable used to deal with the inseparable situation, C represents the penalty parameter used to control the trade-off between interval maximization and classification error, φ(x i ) represents the feature mapping function, which is used to transform the input sample x i Mapping to a higher dimensional space;

[0047] The model output is: f(x) = sign(w T φ(x)+b), where f(x) represents the output function of the model, which is used to predict the category of the new sample x, and sign(·) represents the sign function, which is used to map real numbers to category labels. The selected model is trained using the training set, and the model parameters (hyperparameters) are adjusted to improve the prediction accuracy; the model performance is evaluated using the test set, using appropriate indicators such as accuracy, recall, precision, F1-score, ROC curve, and AUC value; based on the evaluation results, the model parameters are adjusted, the model is optimized, and the trained model is deployed to the cloud server for real-time prediction; by building a disease prediction model, it helps chronic disease patients to conduct risk assessment and health management, and improves the quality of medical services.

[0048] Based on the constructed disease prediction model, a risk assessment model is further constructed. The goal of the risk assessment model is to assess the risk of individuals developing specific diseases based on their characteristics and health status. By calculating the decision value f(x), the relationship between the decision function value and the true label is fitted using logistic regression to obtain: A and B are the parameters obtained in logistic regression. The decision value of each new sample is calculated and then converted into a predicted probability through a probability model. Each sample is then labeled with a risk level based on the set threshold.

[0049] After obtaining the predicted probability of each sample, a risk threshold is set to distinguish the risk level. If P(y=1|x)≤0.3, the sample is marked as low risk; if 0.3<P(y=1|x)≤0.7, the sample is marked as medium risk; if P(y=1|x)>0.7, the sample is marked as high risk.

[0050] The health management module customizes health management plans based on the risk assessment level of sample patients: using the trained disease prediction model to conduct risk assessment on new patients to determine their disease probability and risk level; based on the model output, the patients are divided into low-risk, medium-risk and high-risk groups;

[0051] Closely monitor high-risk patients, conduct regular health checks and monitoring, and provide personalized interventions on diet and exercise, adjust medications based on the patient's condition, and regularly evaluate the effects and side effects of medications;

[0052] For medium-risk patients, educational materials and lectures are used to enhance patients’ health awareness, allowing them to self-monitor, set regular follow-up time points, evaluate changes in health status and the effectiveness of management plans, and make adjustments;

[0053] Provide preventive advice to low-risk patients, maintain healthy eating and exercise habits, and have regular physical examinations;

[0054] Regularly collect patients' health data, monitor changes in their health status, evaluate the effectiveness of health management plans based on patients' feedback and changes in health indicators, and collect patients' feedback through interactive modules. By comprehensively utilizing the analysis results of disease prediction and risk assessment models, the health management module can provide patients with personalized health management plans. This not only helps to effectively control the occurrence and development of chronic diseases, but also improves patients' health literacy and self-management capabilities, and achieves more accurate health management.

[0055] The telemedicine module provides a video call function, allowing patients to communicate with doctors face to face to discuss health problems and treatment plans, and set up a chat function, allowing patients to communicate with doctors in text, handle health consultations or discomfort feedback, build communication files, and all consultation records and feedback are recorded. With the patient's permission, the doctor can access the patient's electronic health records, including historical medical records, treatment records, test results, medication status, etc., and by linking with wearable devices or smartphone applications, the patient's physiological data can be collected and monitored in real time, and the doctor can view these real-time data at any time.

[0056] The data sharing module formats the patient's medical records, laboratory results, and imaging data in a unified manner, exchanges and integrates data in real time through the middleware platform, and builds a centralized cloud database to store the patient's health records and data. According to the needs of different regions or institutions, a distributed storage solution is adopted to ensure the reliability and high availability of data, and to share and exchange data between different medical institutions. When receiving treatment, patients need to actively authorize medical institutions to access their health data to ensure that data sharing obtains the patient's consent; patients have the right to view and manage their own data, including choosing which data can be shared and which data cannot be shared. The effect of data sharing is regularly evaluated to ensure that it can continue to meet the needs of patients and medical quality standards. The data sharing module in the chronic disease management system can effectively promote data sharing and exchange between different medical institutions. This will provide patients with continuous and consistent medical services and improve their health management experience.

[0057] The interactive module records basic personal information through active registration by patients, establishes a unique identity for patients, and records and collects family medical history information, patient diagnosis information, and medication status of patients. It adds a real-time information verification mechanism to ensure that the input data format is correct and provide instant feedback. The interactive module of the chronic disease management system can effectively help patients record basic information and medical records. It helps to improve patient participation, enhance initiative and awareness of health management, and thus promote the overall effect of health management.

[0058] Embodiment 2: This embodiment is basically the same as the previous embodiment, except that, in the data processing and analysis module, features closely related to disease prediction are selected, and irrelevant or redundant features are excluded. The principal components in the data, i.e., the directions with the largest variance, are found through data dimensionality reduction, and the data are projected onto these principal components, thereby achieving dimensionality reduction; it is expressed as: Y=PX, where Y represents the data after dimensionality reduction, P represents the mapping matrix, which is composed of principal components, and X represents the original data;

[0059] By introducing the kernel function, the data is mapped to a high-dimensional space, and the above method is performed in the high-dimensional space, which is expressed as: K(x i ,x j )=φ(x i ) T φ(x j ), where K(x i ,x j ) represents the kernel function, φ(x i ) is the data point x i Functions that map to higher-dimensional spaces.

[0060] Then, by calculating the correlation coefficient between the feature and the target variable, the feature with stronger correlation is selected, which is expressed as: where r XY represents the correlation coefficient between feature X and target variable Y, x i and i are the values ​​of feature X and target variable Y on the i-th sample, and are the means of feature X and target variable Y, respectively, and N represents the number of samples.

[0061] From the above, we can see that performing correlation analysis first and then using data dimensionality reduction and feature selection methods can extract meaningful features, reduce model complexity, and improve prediction accuracy.

[0062] Embodiment 3: This embodiment is basically the same as the previous embodiment, except that, in the telemedicine module, a threshold is set, and when the patient's health data exceeds the normal range, an alarm is automatically issued to notify the doctor to intervene in time; and data visualization tools are provided to doctors to quickly obtain the overall trend of the patient's health status, such as charts and reports, to help make faster judgments. Doctors can adjust personalized health management plans at any time based on the patient's latest physical data and feedback, including diet plans, exercise recommendations and drug prescriptions; combined with the self-monitoring records in the mobile phone application, doctors can conduct regular evaluations and optimize plans based on the patient's progress. At the same time, a patient feedback mechanism is established, so that patients can evaluate the effectiveness of consulting services and management plans, helping doctors and system administrators to continuously optimize services. All consulting records and feedback are recorded to form a complete communication file for subsequent tracking and reference.

[0063] Through the telemedicine module, the chronic disease management system can effectively promote real-time communication between patients and doctors, and enable doctors to view patients' data and adjust plans at any time. It not only improves the flexibility and efficiency of medical services, but also enhances patients' compliance and sense of participation, achieving a higher level of health management and disease control.

[0064] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible without substantially departing from the novel teachings and advantages of the subject matter described in this application. Without departing from the scope of the present invention, other replacements, improvements, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the present invention is not limited to specific embodiments, but extends to a variety of modifications still falling within the scope of the appended claims.

[0065] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0066] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, without undue experimentation, the development effort will be a routine task of design, fabrication, and production.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A chronic disease management system, characterized in that: include: The data acquisition module monitors the patient's physiological indicators in real time through smart wearable devices, connects them to home medical devices, and automatically uploads measurement data; The data processing and analysis module automatically uploads the collected data to the cloud server, uses big data analysis technology to analyze the collected data, and establishes disease prediction and risk assessment models; Health management module, which develops personalized health management plans for patients based on analysis results; Telemedicine module, which is used to provide remote communication and consultation between patients and doctors. Doctors can check patient data and adjust management plans at any time, and patients can also consult doctors about health problems at any time. Data sharing module, which is used to share and exchange data between different medical institutions to provide continuous medical services for patients; The interactive module is used to provide patients with an interactive interface for operation and to register and record basic patient information and medical records.

2. A chronic disease management system as claimed in claim 1, characterized in that: The smart wearable devices in the data acquisition module include smart bracelets and smart watches, the home medical devices include home blood pressure monitors and blood glucose meters, and the physiological indicators include heart rate, blood pressure, and blood glucose.

3. A chronic disease management system as claimed in claim 1, characterized in that: The data processing and analysis module pre-processes the collected data and selects physiological indicators, lifestyle, and family history as features to establish a disease prediction model by constructing a training set. where x i ∈R d is the feature vector, y i ∈{-1,+1} is the category label, by finding an optimal hyperplane ω T x+b=0, and the optimization problem is expressed as: Among them, w represents the normal vector of the hyperplane, b represents the intercept, and x i Represents the feature vector of the i-th sample, including physiological indicators, lifestyle, family history, y i Represents the category label of the i-th sample, with a value of +1 or -1, maximizing the interval while minimizing the loss function and satisfying its constraints so that each data point is correctly classified and the distance from the decision boundary is at least 1; Introducing the kernel function K(x i ,x j ), the original feature space is mapped to a high-dimensional space, and the optimization problem becomes: Among them, ξ i represents the slack variable used to deal with the inseparable situation, C represents the penalty parameter used to control the trade-off between interval maximization and classification error, φ(x i ) represents the feature mapping function, which is used to transform the input sample x i Mapping to a higher dimensional space; The model output is: f(x) = sign(w T φ(x)+b), where f(x) represents the output function of the model, which is used to predict the category of the new sample x, and sign(·) represents the sign function, which is used to map real numbers to category labels.

4. A chronic disease management system as claimed in claim 3, characterized in that: The risk assessment model is obtained by calculating the decision value f(x) and using logistic regression to fit the relationship between the decision function value and the true label: Where A and B are the parameters obtained in logistic regression; After obtaining the predicted probability of each sample, a risk threshold is set to distinguish the risk level. If P(y=1|x)≤0.3, the sample is marked as low risk. If 0.3<P(y=1|x)≤0.7, the sample is marked as medium risk; if P(y=1|x)>0.7, the sample is marked as high risk.

5. A chronic disease management system as claimed in claim 4, characterized in that: The health management module customizes the health management plan according to the risk assessment level of the sample patients: Closely monitor high-risk patients, conduct regular health checks and monitoring, and provide personalized interventions on diet and exercise, adjust medications based on the patient's condition, and regularly evaluate the effects and side effects of medications; For medium-risk patients, educational materials and lectures are used to enhance patients’ health awareness, allowing them to self-monitor, set regular follow-up time points, evaluate changes in health status and the effectiveness of management plans, and make adjustments; Provide preventive advice to low-risk patients, maintain healthy eating and exercise habits, and have regular physical examinations; Regularly collect patients' health data, monitor changes in their health status, evaluate the effectiveness of health management plans based on patients' feedback and changes in health indicators, and collect patients' feedback through interactive modules.

6. A chronic disease management system as claimed in claim 1, characterized in that: The telemedicine module provides a video call function, allowing patients to communicate with doctors face to face to discuss health problems and treatment plans, and sets up a chat function, allowing patients to communicate with doctors in text, handle health consultations or discomfort feedback, and build communication files. All consultation records and feedback are recorded.

7. A chronic disease management system as claimed in claim 1, characterized in that: The data sharing module uniformly formats the patient's medical records, laboratory results, and imaging data, exchanges and integrates data in real time through a middleware platform, and builds a centralized cloud database to store the patient's health records and data, allowing data sharing and exchange between different medical institutions.

8. A chronic disease management system as claimed in claim 1, characterized in that: The interactive module records basic personal information through active registration by the patient, establishes a unique identity for the patient, and records and collects the patient's family medical history information, patient diagnosis information and medication status, adds a real-time information verification mechanism to ensure that the input data format is correct, and provides instant feedback.

Images