Chronic disease patient information management system and method based on intelligent AI

Abstract

The invention discloses a chronic disease patient information management system and method based on intelligent AI, and relates to the technical field of information management. The information management system comprises a patient information management module, a data acquisition module, a data management module, a data analysis and evaluation module, a risk early warning module, a health management module and a remote medical service module. According to the chronic disease patient information management system and method based on the intelligent AI, learning and analysis are carried out based on comprehensive health data of the patient, so that accurate assessment of the health risk of the patient is realized, the current health data of the patient is integrated, and multi-dimensional information of medical history and living habits of the patient is combined, so that the assessment result is more comprehensive and accurate, and meanwhile, the assessment efficiency is improved. The health risk possibly faced by the patient in the future is predicted, early warning is given out in advance, sufficient time is provided for medical institutions to formulate intervention measures, potential health problems can be found and handled in time, and disease deterioration is prevented.

Description

Technical Field

[0001] The present invention relates to the field of information management technology, and specifically to an intelligent AI-based chronic disease patient information management system and method. Background Art

[0002] Chronic diseases, such as cardiovascular disease, diabetes, chronic respiratory diseases, etc., have always been a major challenge to global public health due to their long-term nature, complexity and high incidence. With the aging of the population and changes in lifestyle, the number of patients with chronic diseases continues to increase, causing tremendous pressure on the medical system and social economy. The traditional chronic disease management model mainly relies on patient self-management and regular hospital visits. This model has many information and management limitations. In recent years, with the continuous advancement of technologies such as big data, cloud computing, and the Internet of Things, artificial intelligence has been increasingly used in the field of medical health. AI technology, with its powerful data processing and pattern recognition capabilities, can provide a solid technical foundation for information management of chronic disease patients.

[0003] In the information management of chronic disease patients, it often relies on the experience and professional knowledge of medical institutions, and there are problems of strong subjectivity and high misjudgment rate. Therefore, how to objectively evaluate the health status of patients and then assist medical institutions in implementing targeted medical services. To this end, a chronic disease patient information management system and method based on intelligent AI is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: In the first aspect, a chronic disease patient information management system based on intelligent AI, the information management system includes a patient information management module, a data acquisition module, a data management module, a data analysis and evaluation module, a risk warning module, a health management module and a telemedicine service module, wherein the modules are electrically connected;

[0005] The patient information management module establishes and maintains the patient's health records, including basic information, medical history records, and examination results, to achieve comprehensive and unified management of patient information, which is convenient for medical institutions to review and update at any time;

[0006] The data acquisition module collects the patient's original health data in real time and accurately through smart wearable devices and mobile applications, where the health data includes physiological signs and medication data, providing the system with a rich and accurate patient health data foundation for subsequent analysis and processing;

[0007] The data management module pre-processes the collected raw health data, including cleaning, denoising, and formatting, to ensure the quality and consistency of the data, and stores and manages the pre-processed health data to ensure the security and integrity of the data;

[0008] The data analysis and evaluation module uses AI algorithms to analyze the patient's health data, identify the patient's health status and disease development trends, generate objective and accurate health assessment reports, and provide scientific decision-making basis for medical institutions;

[0009] The risk warning module monitors the patient's health data in real time based on the data analysis results, and in combination with the patient's vital signs, issues a warning once an abnormality is found, and gives corresponding intervention suggestions to prevent and control the deterioration of the disease in a timely manner and reduce the risk of complications;

[0010] The health management module develops personalized health management plans based on the patient's health data and risk warning analysis results, combined with the experience and expertise of medical institutions, to provide targeted medical services and improve treatment effects and patient satisfaction;

[0011] The telemedicine service module implements telemedicine services and follow-up functions. Telemedicine services include online consultations, remote monitoring, and health consultations, which facilitate real-time communication and exchanges between patients and medical institutions, break geographical restrictions, and improve the convenience and accessibility of medical services.

[0012] Preferably, in the patient information management module, the process of establishing and maintaining the patient's health record includes:

[0013] Establish a health record in the system, enter the patient's basic information, medical history information and diagnosis and treatment records. Basic information includes name, gender, age, ID number, contact number, home address to ensure the uniqueness and traceability of the patient's identity. Medical history information includes past medical history, family history, allergy history, and the patient's diet, exercise, sleep, smoking and drinking habits to assess their impact on health. Diagnosis and treatment records include diagnosis results, treatment plans, medication records, surgery records and important information during the treatment process to track treatment effects and adjust treatment plans in a timely manner. Various examination reports of patients are collected, including blood tests, imaging examinations, pathological examinations, etc., so that doctors can accurately assess the patient's condition.

[0014] Regularly check and update the patient information in the health record to ensure that the personal information, medical history, diagnosis results, etc. in the patient file are kept up to date so that doctors can make accurate diagnosis and treatment decisions. Provide information update and error correction channels on the mobile application end to enable patients to participate in the maintenance of health records and improve the accuracy and reliability of data;

[0015] The data in the health records are encrypted to ensure the security of the data during transmission. A secure transmission protocol is used to prevent the data from being intercepted or tampered with during transmission. An access control mechanism is established and multi-factor authentication is used to ensure that only authorized personnel can access patient health records to enhance security.

[0016] Preferably, in the data collection module, the health data collection process includes:

[0017] The patient wears the smart wearable device and performs device binding and initialization settings through the mobile application. The smart wearable device monitors the patient's physiological signs in real time, including heart rate, blood pressure, blood oxygen saturation, and sleep quality score parameters, to ensure that the patient can understand his or her physical condition in a timely manner;

[0018] The sensors of smart wearable devices convert the patient's physiological signs into electrical signals, which are then digitally processed to obtain physiological sign data. The physiological sign data is then transmitted to the mobile application end through wireless communication technologies such as Bluetooth and Wi-Fi to ensure the stability and security of data transmission.

[0019] A medication record module is set up on the mobile application end. Through the reminder function, patients are reminded to regularly enter medication data, including drug name, dosage, and medication time parameters. A historical data query function is also provided to facilitate patients to review and analyze the changing trends of their health status;

[0020] The mobile application synchronizes data with the smart wearable device, integrating the patient's physiological signs data and manually entered medication data to form the patient's original health data.

[0021] Preferably, in the data management module, the preprocessing process of health data includes:

[0022] Extract the original health data collected by smart wearable devices and mobile applications, and perform pre-processing operations such as data cleaning, data denoising and data formatting on the health data;

[0023] Integrate the preprocessed health data into a dataset, add timestamps to each record, ensure the data is in chronological order, and associate each record in the dataset with a point in time;

[0024] Build a data warehouse, store the preprocessed data in the data warehouse, and set the backup frequency to back up data regularly to prevent data loss.

[0025] Preferably, in the data analysis and evaluation module, the analysis process of health data includes:

[0026] Extract pre-processed vital signs data and medication data from the data warehouse, set baseline values ​​for each parameter of vital signs and medication based on the patient's health status, mark data that deviate from the baseline values ​​as outliers, and divide the data set into a training set and a test set. The baseline values ​​are calculated based on clinical guidelines and historical data.

[0027] The vital signs evaluation model is trained based on the decision tree model using the vital signs data in the training set combined with the machine learning algorithm. The trained vital signs evaluation model is evaluated using the test set data. The model performance is evaluated by calculating indicators such as accuracy, recall, and F1 score. The model parameters are adjusted based on the evaluation results to optimize the model performance.

[0028] The medication use data in the training set is combined with the neural network model to build a medication use evaluation model, and the trained medication use evaluation model is evaluated using the test set data to adjust the model parameters;

[0029] Based on the vital signs evaluation model and the patient's vital signs data, the vital signs evaluation indicators are calculated, and the changing trends of the patient's vital signs data are analyzed. Combined with the medication situation evaluation model and the patient's medication situation data, the medication trend evaluation indicators are calculated, and the patient's medication compliance and drug efficacy are analyzed.

[0030] Preferably, the calculation process of the vital sign evaluation index is:

[0031] For the collected vital sign data of heart rate H, blood pressure P, blood oxygen saturation S and sleep quality score L, determine their respective baseline values ​​and normal fluctuation ranges;

[0032] For each vital sign parameter, the deviation from the baseline value was calculated and divided by the respective range to calculate the deviation value of each parameter;

[0033] The deviation values ​​of all vital sign parameters are integrated, substituted into the exponential function, and the output of the exponential function is converted into a value between 0 and 1 using the Sigmoid function;

[0034] Combine the minimum heart rate value and the patient's real-time heart rate to calculate the root penalty term of the heart rate, and multiply the output of the Sigmoid function by the root penalty term of the heart rate to obtain the vital sign evaluation index;

[0035] The calculation process of the medication trend evaluation index is:

[0036] For medication data, determine the baseline value and normal fluctuation range of medication time, and collect the patient's actual medication dose D and medication time T;

[0037] Calculate the deviation between the actual medication time and the baseline medication time value, and divide it by the normal fluctuation range of the medication time to calculate the medication time deviation value;

[0038] Substitute the medication time deviation value into the exponential function, and use the Sigmoid function to convert the output of the exponential function into a value between 0 and 1;

[0039] The root penalty term of the medication dosage is calculated by combining the minimum value of the medication dosage and the actual medication dosage of the patient, and the output of the Sigmoid function is multiplied by the root penalty term of the medication dosage to obtain the medication trend evaluation index.

[0040] Preferably, in the risk warning module, the analysis process of abnormal warning includes:

[0041] Based on the analysis results of the patient's vital signs and medication status, combined with the patient's medical history information, the patient's vital signs and medication dosage are analyzed to determine the patient's health risk tolerance, that is, the level of health risk that the patient can bear;

[0042] Comprehensively consider various parameters of the patient's vital signs and medication dosage, calculate health risk indicators, and analyze the changing trend of the patient's health risk bearing capacity;

[0043] Combined with vital signs evaluation indicators, medication trend evaluation indicators, and health risk indicators, the risk warning coefficient is calculated to analyze the current health risk level faced by the patient;

[0044] The warning threshold θ is set according to the risk warning coefficient, and the patient's vital signs and medication status are monitored in real time. Once the risk warning coefficient is found to deviate from the warning threshold, the warning mechanism is immediately triggered, warning information is issued, and detailed abnormal data and risk assessment results are provided.

[0045] Preferably, the calculation expression of the risk warning coefficient is:

[0046]

[0047] Among them, R is the risk warning coefficient, V is the vital sign evaluation index, which reflects the health status of the patient's vital signs, M is the medication trend evaluation index, which reflects the patient's medication compliance and drug efficacy, RC is the health risk bearing index, which reflects the level of health risk that the patient can bear, w1, w2, and w3 are weight coefficients used to adjust the relative importance of V, M, and RC in the calculation of R, D is the patient's actual medication dosage, and D min is the minimum value of the drug dosage, k is a constant used to adjust the influence of the root term, the value range of RC is limited to between 0 and 1, and the value range of R is limited to between 0 and 1, where 1 represents the lowest risk level and 0 represents the highest risk level.

[0048] Preferably, in the health management module, the process of formulating a health management plan includes:

[0049] Through physical examinations, questionnaires, and medical equipment monitoring, we comprehensively collect all kinds of health-related data of patients, including but not limited to physiological characteristics, living habits, family medical history, past medical history, medication status, etc. We combine the risk warning analysis results with the experience and professional knowledge of medical institutions to conduct a comprehensive assessment of the current health risk level faced by patients and identify the main health problems and high-risk areas of patients;

[0050] Intelligently analyze the collected health data to generate personalized health reports that detail the patient's health status, potential disease risks, and health issues that require attention;

[0051] Based on the health report and combined with the experience and expertise of the medical institution, we tailor a personalized health management plan for the patient and determine the specific content of the health management plan, including lifestyle adjustments, diet plans, exercise plans, and medication guidance;

[0052] Communicate the health management plan to patients and guide them in its implementation, regularly monitor patients' health data, and track the implementation of the health management plan.

[0053] In a second aspect, a method for managing chronic disease patient information based on intelligent AI is implemented based on the above-mentioned intelligent AI-based chronic disease patient information management system, comprising the following steps:

[0054] Step 1: Collect the patient's physiological sign data and medication data through smart wearable devices and mobile applications, integrate the patient's basic information, medical history records, and examination results, and establish a comprehensive health record;

[0055] Step 2: Use AI algorithms to intelligently analyze the collected health data and calculate the vital signs evaluation index and medication trend evaluation index;

[0056] Step 3: Based on the data analysis results, monitor the patient's health data in real time, calculate the risk warning coefficient, and set the warning threshold. Once the risk warning coefficient is found to deviate from the preset warning threshold, the warning mechanism is immediately triggered and a warning message is issued;

[0057] Step 4: Combine the health report and risk warning analysis results to tailor a personalized health management plan for the patient;

[0058] Step 5. Implement telemedicine services and follow-up, communicate the health management plan to patients, guide patients to implement it, regularly monitor patients' health data, and track the implementation of the health management plan.

[0059] The present invention provides an information management system and method for chronic disease patients based on intelligent AI. It has the following beneficial effects:

[0060] 1. This chronic disease patient information management system and method based on intelligent AI learns and analyzes the patient's comprehensive health data to achieve an accurate assessment of the patient's health risks. It integrates the patient's current health data and combines the patient's medical history and living habits to make the assessment results more comprehensive and accurate. At the same time, it predicts the health risks that the patient may face in the future and issues early warnings, providing sufficient time for medical institutions to formulate intervention measures, which helps to promptly discover and deal with potential health problems and prevent the disease from worsening.

[0061] 2. This chronic disease patient information management system and method based on intelligent AI can accurately assess the health risk level of chronic disease patients through data analysis, integrate and analyze multi-dimensional data related to patients' health, and quickly identify potential health problems and disease development trends. Based on AI technology, it not only improves the accuracy of the assessment, but also greatly improves the efficiency of the assessment, allowing medical institutions to understand the health status of patients more promptly and provide a scientific basis for formulating personalized health management plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a module structure diagram of the present invention;

[0063] Figure 2 is a flow chart for analyzing health data of the present invention;

[0064] Figure 3 This is an analysis flow chart of abnormal warning of the present invention;

[0065] Figure 4 It is a step diagram of the method of the present invention. DETAILED DESCRIPTION

[0066] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0067] The first embodiment, as Figure 1 , Figure 2As shown, the present invention provides a technical solution: an information management system for chronic disease patients based on intelligent AI, the information management system includes a patient information management module, a data acquisition module, a data management module, a data analysis and evaluation module, a risk warning module, a health management module and a telemedicine service module, wherein each module is electrically connected;

[0068] The patient information management module establishes and maintains the patient's health record, including basic information, medical history records, and examination results, to achieve comprehensive and unified management of patient information, which is convenient for medical institutions to access and update at any time. A health record is established in the system, and the patient's basic information, medical history information, and diagnosis and treatment records are entered. Basic information includes name, gender, age, ID number, contact number, and home address to ensure the uniqueness and traceability of the patient's identity. Medical history information includes previous medical history, family history, allergy history, and the patient's diet, exercise, sleep, and smoking and drinking habits to assess their impact on health. Diagnosis and treatment records include diagnosis results, treatment plans, medication records, and surgical records. Important information during the treatment process is used to track treatment effects and adjust treatment plans in a timely manner, and is collected Collect various examination reports of patients, including blood tests, imaging tests, pathological tests, etc., so that doctors can accurately assess the patient's condition, regularly check and update the patient information in the health record, ensure that the personal information, medical history, diagnosis results, etc. in the patient's file are kept up to date, so that doctors can make accurate diagnosis and treatment decisions, provide information update and error correction channels on the mobile application side, enable patients to participate in the maintenance of health records, improve the accuracy and reliability of data, encrypt the data in the health record to ensure the security of data during transmission, adopt a secure transmission protocol to prevent data from being intercepted or tampered with during transmission, and establish an access control mechanism and adopt multi-factor authentication to ensure that only authorized personnel can access the patient's health record to enhance security;

[0069] The data acquisition module collects the patient's original health data in real time and accurately through smart wearable devices and mobile applications. Among them, health data includes physiological signs and medication data, providing the system with a rich and accurate patient health data foundation for subsequent analysis and processing. The patient wears the smart wearable device and performs device binding and initialization settings through the mobile application. The smart wearable device is used to monitor the patient's physiological signs in real time, including heart rate, blood pressure, blood oxygen saturation, and sleep quality score parameters, to ensure that the patient can understand his or her physical condition in a timely manner. The sensor of the smart wearable device converts the patient's physiological sign signal into an electrical signal, which is then digitized to obtain physiological sign data, and the physiological sign data is transmitted to the mobile application through wireless communication technologies such as Bluetooth and Wi-Fi to ensure the stability and security of data transmission. A medication record module is set on the mobile application. Through the reminder function, the patient is reminded to regularly enter medication data, including drug name, dosage, and medication time parameters, and a historical data query function is provided to facilitate patients to review and analyze the changing trends of their own health status. The mobile application synchronizes data with the smart wearable device, integrates the patient's physiological sign data and manually entered medication data, and forms the patient's original health data;

[0070] The data management module pre-processes the collected raw health data, including cleaning, denoising, and formatting to ensure the quality and consistency of the data, and stores and manages the pre-processed health data to ensure the security and integrity of the data. It extracts the raw health data collected by smart wearable devices and mobile applications, and performs data cleaning, data denoising, and data formatting pre-processing operations on the health data. Among them, data cleaning is used to remove duplicate, invalid, or erroneous data, and the mean, median, and previous and next value interpolation are used for estimation, missing values ​​are filled, and data outside the normal range is identified and corrected or deleted to handle outliers. Data denoising is used to average, Remove the sudden changes of noise by sliding average or weighted average, retain the trend information of data, use filters to filter data, remove the high-frequency components of noise, identify and remove the impact of noise by calculating and analyzing data, standardize data to ensure consistency of data at different scales, integrate preprocessed health data into a data set, add timestamps to each record, ensure that data is arranged in chronological order, and associate each record in the data set with a time point, build a data warehouse, store the preprocessed data in the data set in the data warehouse, and set the backup frequency to back up data regularly to prevent data loss;

[0071] The data analysis and evaluation module uses AI algorithms to analyze the patient's health data, identify the patient's health status and disease development trends, generate objective and accurate health assessment reports, and provide scientific decision-making basis for medical institutions. It extracts pre-processed vital signs data and medication data from the data warehouse, sets the baseline values ​​of each parameter of vital signs and medication based on the patient's health status, marks the data that deviates from the baseline value as an outlier, and divides the data set into a training set and a test set. The baseline value is calculated based on clinical guidelines and historical data. The vital signs data in the training set is combined with a machine learning algorithm to train a vital signs evaluation model based on a decision tree model, and the test set is used The trained vital signs evaluation model is evaluated by using the data, and the model performance is evaluated by calculating the accuracy, recall rate, F1 score and other indicators. The model parameters are adjusted according to the evaluation results to optimize the model performance. The medication situation evaluation model is constructed by combining the neural network model with the medication situation data in the training set, and the trained medication situation evaluation model is evaluated by using the test set data to adjust the model parameters. Based on the vital signs evaluation model and the patient's vital signs data, the vital signs evaluation indicators are calculated, and the changing trend of the patient's vital signs data is analyzed. The medication situation evaluation model and the patient's medication situation data are combined to calculate the medication trend evaluation indicators, and the patient's medication compliance and drug efficacy are analyzed.

[0072] Furthermore, the calculation process of the vital sign evaluation index is:

[0073] For the collected vital sign data of heart rate H, blood pressure P, blood oxygen saturation S, and sleep quality score L, determine their respective baseline values ​​and normal fluctuation ranges. For each vital sign parameter, calculate its deviation from the baseline value, divide it by its respective range, calculate the deviation value of each parameter, combine the deviation values ​​of all vital sign parameters, substitute them into the exponential function, and use the Sigmoid function to convert the output of the exponential function into a value between 0 and 1. Combine the minimum heart rate and the patient's real-time heart rate to calculate the root penalty term of the heart rate, and multiply the output of the Sigmoid function by the root penalty term of the heart rate to obtain the vital sign evaluation index;

[0074] The calculation expression of vital sign evaluation index is:

[0075]

[0076] Among them, V is the vital sign evaluation index, H is the patient's real-time heart rate, and H b is the baseline value of heart rate, calculated based on clinical guidelines and historical data. r is the normal fluctuation range of heart rate, P is the patient's real-time blood pressure, and P b is the baseline value of blood pressure, P ris the normal fluctuation range of blood pressure, S is the patient’s real-time blood oxygen saturation, S b is the baseline value of blood oxygen saturation, S r is the normal fluctuation range of blood oxygen saturation, L is the patient's sleep quality score, L b is the baseline value of sleep quality, L r is the normal fluctuation range of sleep quality, is the minimum value of heart rate, and the value range of V is limited to between 0 and 1, where 1 represents the best state of vital signs and 0 represents the worst state. As each vital sign approaches or exceeds the baseline value, the value of V increases; conversely, if the vital sign deviates from the baseline value, the value of V decreases;

[0077] Furthermore, the calculation process of the medication trend evaluation index is:

[0078] For medication data, determine the baseline value and normal fluctuation range of medication time, collect the patient's actual medication dose D and medication time T, calculate the deviation between the actual medication time and the baseline value of medication time, and divide it by the base normal fluctuation range of medication time to calculate the medication time deviation value, substitute the medication time deviation value into the exponential function, use the Sigmoid function to convert the output of the exponential function to a value between 0 and 1, combine the minimum value of medication dose and the patient's actual medication dose, calculate the root penalty term of medication dose, and multiply the output of the Sigmoid function by the root penalty term of medication dose to obtain the medication trend evaluation index;

[0079] The calculation expression of the medication trend evaluation index is:

[0080]

[0081] Among them, M is the evaluation index of medication trend, D is the actual medication dosage of the patient, and D min is the minimum value of the medication dosage, T is the actual medication time of the patient, and T b is the benchmark value for medication duration, calculated based on clinical guidelines and historical data. r The value of M is limited to the normal fluctuation range of medication time. The value range of M is limited to between 0 and 1, where 1 represents the best medication compliance and drug efficacy, and 0 represents the worst state. As the patient's medication dosage and medication time approach the baseline value and the minimum value, the value of M increases; conversely, if the medication dosage and medication time deviate from the baseline value and the minimum value, the value of M decreases.

[0082] The risk warning module monitors the patient's health data in real time based on the data analysis results. Combined with the patient's vital signs, it issues a warning once an abnormality is found, and gives corresponding intervention suggestions to prevent and control the deterioration of the disease in a timely manner and reduce the risk of complications.

[0083] The health management module develops personalized health management plans based on the patient's health data and risk warning analysis results, combined with the experience and expertise of medical institutions, to provide targeted medical services and improve treatment effects and patient satisfaction;

[0084] The telemedicine service module implements telemedicine services and follow-up functions. Telemedicine services include online consultations, remote monitoring, and health consultations, which facilitate real-time communication and exchanges between patients and medical institutions, break geographical restrictions, and improve the convenience and accessibility of medical services.

[0085] The second embodiment is based on the first embodiment. Figure 3 As shown in the figure, in the risk warning module, the analysis process of abnormal warning includes:

[0086] Based on the analysis results of the patient's vital signs and medication status, combined with the patient's medical history information, analyze the patient's vital signs and medication dosage to determine the patient's health risk bearing capacity, that is, the level of health risk that the patient can bear, and comprehensively consider the various parameters of the patient's vital signs and medication dosage to calculate the health risk bearing index, analyze the changing trend of the patient's health risk bearing capacity, combine the vital signs evaluation index and the medication trend evaluation index, and the health risk bearing index to calculate the risk warning coefficient, analyze the current health risk level faced by the patient, set the warning threshold θ according to the risk warning coefficient, monitor the patient's vital signs and medication status in real time, and immediately trigger the warning mechanism once the risk warning coefficient deviates from the warning threshold, issue warning information, and provide detailed abnormal data and risk assessment results;

[0087] The calculation expression of risk warning coefficient is:

[0088]

[0089] Among them, R is the risk warning coefficient, V is the vital sign evaluation index, which reflects the health status of the patient's vital signs, M is the medication trend evaluation index, which reflects the patient's medication compliance and drug efficacy, RC is the health risk bearing index, which reflects the level of health risk that the patient can bear, w1, w2, and w3 are weight coefficients used to adjust the relative importance of V, M, and RC in the calculation of R, D is the patient's actual medication dosage, and D minis the minimum value of the medication dosage, k is a constant used to adjust the influence of the radical term, the value range of RC is limited to between 0 and 1, where 1 represents the best health risk bearing capacity and 0 represents the worst state. As the patient's vital signs approach or exceed the benchmark value and the medication dosage is appropriate, the value of RC increases, indicating that the health risk bearing capacity is enhanced. On the contrary, if the vital signs deviate from the benchmark value or the medication dosage is inappropriate, the value of RC decreases, indicating that the health risk bearing capacity is reduced. The value range of R is limited to between 0 and 1, where 1 represents the lowest risk level and 0 represents the highest risk level. As the values ​​of V and M increase (i.e., the patient's vital signs and medication conditions are better) and the value of RC increases (i.e., the patient can bear higher health risks), the value of R decreases, indicating that the risk level is reduced. On the contrary, if the values ​​of V and M decrease, or the value of RC decreases, the value of R increases, indicating that the risk level is increased. R<θ, triggering the early warning mechanism;

[0090] In the health management module, the process of formulating a health management plan includes:

[0091] Through physical examinations, questionnaires, and medical equipment monitoring, we comprehensively collect all kinds of health-related data of patients, including but not limited to physiological characteristics, living habits, family medical history, past medical history, medication status, etc., and combine the risk warning analysis results with the experience and expertise of the medical institutions to conduct a comprehensive assessment of the current health risk level faced by the patient, determine the patient's major health problems and high-risk areas, conduct intelligent analysis of the collected health data, and generate personalized health reports, which detail the patient's health status, potential disease risks, and health issues that need attention. Based on the health report and combined with the experience and expertise of the medical institutions, we tailor personalized health management plans for patients and determine the specific content of the health management plans, including lifestyle adjustments, diet plans, exercise plans, and medication guidance. We communicate the health management plans to patients and guide them in their implementation. We regularly monitor patients' health data and track the implementation of the health management plans.

[0092] The third embodiment is based on the first and second embodiments. Figure 4 As shown, the present invention also provides a technical solution: a method for managing chronic disease patient information based on intelligent AI, which is implemented based on an intelligent AI-based chronic disease patient information management system, comprising the following steps:

[0093] Step 1: Collect the patient's physiological sign data and medication data through smart wearable devices and mobile applications, integrate the patient's basic information, medical history records, and examination results, and establish a comprehensive health record;

[0094] Step 2: Use AI algorithms to intelligently analyze the collected health data and calculate the vital signs evaluation index and medication trend evaluation index;

[0095] Step 3: Based on the data analysis results, monitor the patient's health data in real time, calculate the risk warning coefficient, and set the warning threshold. Once the risk warning coefficient is found to deviate from the preset warning threshold, the warning mechanism is immediately triggered and a warning message is issued;

[0096] Step 4: Combine the health report and risk warning analysis results to tailor a personalized health management plan for the patient;

[0097] Step 5. Implement telemedicine services and follow-up, communicate the health management plan to patients, guide patients to implement it, regularly monitor patients' health data, and track the implementation of the health management plan.

[0098] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A chronic disease patient information management system based on intelligent AI, characterized in that: The information management system includes a patient information management module, a data collection module, a data management module, a data analysis and evaluation module, a risk warning module, a health management module and a telemedicine service module, wherein each module is electrically connected; The patient information management module establishes and maintains the patient's health records; The data collection module collects the patient's original health data through smart wearable devices and mobile applications, wherein the health data includes physiological signs and medication status data; The data management module performs preprocessing and storage management on the collected raw health data; The data analysis and evaluation module uses AI algorithms to analyze the patient's health data and identify the patient's health status and disease development trends; The risk warning module monitors the patient's health data in real time based on the data analysis results. Once an abnormality is found, it issues a warning and gives corresponding intervention suggestions; The health management module formulates a personalized health management plan based on the patient's health data and risk warning analysis results; The telemedicine service module implements telemedicine service and follow-up functions.

2. According to claim 1, a chronic disease patient information management system based on intelligent AI is characterized by: In the patient information management module, the process of establishing and maintaining the patient's health record includes: Establish a health record in the system, enter the patient's basic information, medical history information and diagnosis and treatment records. Basic information includes name, gender, age, ID number, contact number, and home address. Medical history information includes past medical history, family history, allergy history, and the patient's diet, exercise, sleep, smoking and drinking habits. Diagnosis and treatment records include diagnosis results, treatment plans, medication records, and collect various examination reports of patients; Regularly check and update patient information in health records, provide information update and error correction channels on the mobile application, and enable patients to participate in maintaining health records; The data in the health records are encrypted, a secure transmission protocol is adopted, and an access control mechanism is established with multi-factor authentication to ensure that only authorized personnel can access patient health records.

3. According to claim 2, a chronic disease patient information management system based on intelligent AI is characterized by: In the data collection module, the health data collection process includes: The patient wears the smart wearable device and performs device binding and initialization settings through the mobile application. The smart wearable device is used to monitor the patient's physiological signs in real time, including heart rate, blood pressure, blood oxygen saturation, and sleep quality score parameters; The sensors of smart wearable devices convert the patient's physiological signs into electrical signals, which are then digitally processed to obtain physiological sign data, and then transmitted to the mobile application end through wireless communication technology; Set up a medication record module on the mobile application end, and use the reminder function to remind patients to regularly enter medication data, including drug name, dosage, and medication time parameters; The mobile application synchronizes data with the smart wearable device, integrating the patient's physiological signs data and manually entered medication data to form the patient's original health data.

4. According to claim 3, the information management system for chronic disease patients based on intelligent AI is characterized by: In the data management module, the preprocessing process of health data includes: Extract the original health data collected by smart wearable devices and mobile applications, and perform pre-processing operations such as data cleaning, data denoising and data formatting on the health data; Integrate the preprocessed health data into a dataset and add a timestamp to each record so that each record in the dataset is associated with a point in time; Build a data warehouse, store the preprocessed data in the data warehouse, and set the backup frequency to back up the data regularly.

5. According to claim 4, a chronic disease patient information management system based on intelligent AI is characterized by: In the data analysis and evaluation module, the analysis process of health data includes: Extract pre-processed vital signs data and medication data from the data warehouse, set baseline values ​​for each parameter of vital signs and medication based on the patient's health status, mark data that deviate from the baseline values ​​as outliers, and divide the data set into a training set and a test set. The baseline values ​​are calculated based on clinical guidelines and historical data. Using the vital signs data in the training set combined with the machine learning algorithm, the vital signs evaluation model is trained based on the decision tree model, and the trained vital signs evaluation model is evaluated using the test set data. The model parameters are adjusted according to the evaluation results to optimize the model performance. The medication use data in the training set is combined with the neural network model to build a medication use evaluation model, and the trained medication use evaluation model is evaluated using the test set data to adjust the model parameters; Based on the vital signs evaluation model and the patient's vital signs data, the vital signs evaluation indicators are calculated, and the changing trends of the patient's vital signs data are analyzed. Combined with the medication situation evaluation model and the patient's medication situation data, the medication trend evaluation indicators are calculated, and the patient's medication compliance and drug efficacy are analyzed.

6. According to claim 5, a chronic disease patient information management system based on intelligent AI is characterized by: The calculation process of the vital sign evaluation index is: For the collected vital sign data of heart rate H, blood pressure P, blood oxygen saturation S and sleep quality score L, determine their respective baseline values ​​and normal fluctuation ranges; For each vital sign parameter, the deviation from the baseline value was calculated and divided by the respective range to calculate the deviation value of each parameter; The deviation values ​​of all vital sign parameters are integrated, substituted into the exponential function, and the output of the exponential function is converted into a value between 0 and 1 using the Sigmoid function; Combine the minimum heart rate and the patient's real-time heart rate to calculate the root penalty term of the heart rate, and multiply the output of the Sigmoid function by the root penalty term of the heart rate to obtain the vital sign evaluation index V; The calculation process of the medication trend evaluation index is: For medication data, determine the baseline value and normal fluctuation range of medication time, and collect the patient's actual medication dose D and medication time T; Calculate the deviation between the actual medication time and the baseline medication time value, and divide it by the normal fluctuation range of the medication time to calculate the medication time deviation value; Substitute the medication time deviation value into the exponential function, and use the Sigmoid function to convert the output of the exponential function into a value between 0 and 1; The root penalty term of the medication dosage is calculated by combining the minimum value of the medication dosage and the actual medication dosage of the patient, and the output of the Sigmoid function is multiplied by the root penalty term of the medication dosage to obtain the medication trend evaluation index M.

7. According to claim 6, a chronic disease patient information management system based on intelligent AI is characterized by: In the risk warning module, the analysis process of abnormal warning includes: Based on the analysis results of the patient's vital signs and medication status, combined with the patient's medical history information, analyze the patient's vital signs and medication dosage to determine the patient's health risk tolerance; Comprehensively consider various parameters of the patient's vital signs and medication dosage, calculate the health risk bearing index RC, and analyze the changing trend of the patient's health risk bearing capacity; Combined with vital signs evaluation indicators, medication trend evaluation indicators, and health risk bearing indicators, the risk warning coefficient R is calculated to analyze the current health risk level faced by the patient; The warning threshold θ is set according to the risk warning coefficient, and the patient's vital signs and medication status are monitored in real time. Once the risk warning coefficient is found to deviate from the warning threshold, the warning mechanism is immediately triggered, warning information is issued, and detailed abnormal data and risk assessment results are provided.

8. According to claim 7, a chronic disease patient information management system based on intelligent AI is characterized by: The calculation expression of the risk warning coefficient is: Among them, R is the risk warning coefficient, V is the vital sign evaluation index, M is the medication trend evaluation index, RC is the health risk bearing index, w1, w2, w3 are weight coefficients, D is the actual medication dose of the patient, and D min is the minimum value of the drug dosage, k is a constant used to adjust the influence of the root term, and the value range of R is limited to between 0 and 1, where 1 represents the lowest risk level and 0 represents the highest risk level. When R<θ, the early warning mechanism is triggered.

9. According to claim 8, a chronic disease patient information management system based on intelligent AI is characterized by: In the health management module, the process of formulating a health management plan includes: Through physical examinations, questionnaires, and medical equipment monitoring, we comprehensively collect all kinds of health-related data from patients. We combine the risk warning analysis results with the experience and expertise of medical institutions to conduct a comprehensive assessment of the current health risk level faced by patients and identify the main health problems and high-risk areas of patients. Intelligently analyze the collected health data to generate personalized health reports that detail the patient's health status, potential disease risks, and health issues that require attention; Based on the health report and combined with the experience and expertise of the medical institution, we tailor a personalized health management plan for the patient and determine the specific content of the health management plan, including lifestyle adjustments, diet plans, exercise plans, and medication guidance; Communicate the health management plan to patients and guide them in its implementation, regularly monitor patients' health data, and track the implementation of the health management plan.

10. A method for managing chronic disease patient information based on intelligent AI, implemented based on the chronic disease patient information management system based on intelligent AI as described in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Collect the patient's physiological sign data and medication data through smart wearable devices and mobile applications, integrate the patient's basic information, medical history records, and examination results, and establish a comprehensive health record; Step 2: Use AI algorithms to intelligently analyze the collected health data and calculate the vital signs evaluation index and medication trend evaluation index; Step 3: Based on the data analysis results, monitor the patient's health data in real time, calculate the risk warning coefficient, and set the warning threshold. Once the risk warning coefficient is found to deviate from the preset warning threshold, the warning mechanism is immediately triggered and a warning message is issued; Step 4: Combine the health report and risk warning analysis results to tailor a personalized health management plan for the patient; Step 5. Implement telemedicine services and follow-up, communicate the health management plan to patients, guide patients to implement it, regularly monitor patients' health data, and track the implementation of the health management plan.

Images