A chronic disease monitoring method, system, device and storage medium

Abstract

The present application relates to the technical field of data processing, and particularly relates to a chronic disease monitoring method, system, device and storage medium, comprising obtaining disease information of a patient, and determining a disease category of the patient according to the disease information; obtaining a to-be-collected information type associated with the disease category according to the disease category; obtaining a follow-up physical parameter of the patient according to the to-be-collected information type and a preset follow-up cycle; establishing follow-up physical change trend information according to the follow-up physical parameter; performing trend prediction on the follow-up physical change trend information based on a preset prediction cycle, to obtain physical prediction change trend information of the patient within the prediction cycle; generating a monitoring analysis result according to the physical prediction change trend information and the disease information; by setting a fixed follow-up cycle, collecting specific follow-up indexes of the patient, and combining the indexes and the disease condition, predicting the disease development trend of the patient, so as to improve the monitoring efficiency in the treatment process of the chronic disease patient.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more particularly to a method, system, device, and storage medium for chronic disease monitoring. Background Technology

[0002] Chronic diseases, such as hypertension, hyperlipidemia, and hyperglycemia, are becoming a significant health concern among the elderly. Patients with chronic diseases require regular follow-up appointments during treatment. However, primary healthcare institutions currently face challenges in monitoring these conditions and providing interventions.

[0003] It is evident that existing technologies still need improvement and enhancement. Summary of the Invention

[0004] In order to overcome the shortcomings of the prior art, the present invention aims to provide a method, system, device and storage medium for chronic disease monitoring, which collects specific follow-up indicators of patients according to a certain follow-up cycle, and predicts the changes in the patient's condition in the future by combining the patient's follow-up indicators and condition, thereby improving the monitoring efficiency of chronic disease patients in the treatment process.

[0005] The first aspect of this invention provides a method for monitoring chronic diseases, comprising: acquiring a patient's condition information and determining the patient's condition category based on the condition information; acquiring a type of information to be collected associated with the condition category based on the condition category; acquiring the patient's follow-up physical parameters based on the type of information to be collected and a preset follow-up period; establishing follow-up physical change trend information based on the follow-up physical parameters; performing trend prediction on the follow-up physical change trend information based on a preset prediction period to obtain the patient's predicted physical change trend information within the prediction period; and generating monitoring analysis results based on the predicted physical change trend information and the condition information.

[0006] Optionally, in the first implementation of the first aspect of the present invention, obtaining the patient's condition information and determining the patient's condition category based on the condition information includes: determining the patient's follow-up verification information and extracting associated electronic medical record data based on the follow-up verification information; performing traversal processing on the electronic medical record data to obtain condition information; performing word segmentation processing on the condition information to obtain multiple condition feature characters; performing matching processing on each condition feature character according to a preset condition feature lookup table to obtain the condition feature character with matching results as the target condition character; and determining the patient's condition category based on the target condition character.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of obtaining the type of information to be collected associated with the disease category includes: obtaining a set of typical physical sign parameters based on the characteristics of the hypertensive patient group, the hyperlipidemic patient group, and the diabetic patient group; constructing multiple collection lists based on each set of typical physical sign parameters and preset specific habit indicators; obtaining type information that has a mapping relationship with each collection list according to the disease category, and generating the type of information to be collected based on the obtained type information.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the step of obtaining the patient's follow-up physical parameters according to the type of information to be collected and a preset follow-up cycle includes: obtaining the corresponding follow-up cycle from a preset cycle standard library according to the type of illness; correcting the follow-up cycle based on the illness information to obtain a corrected follow-up cycle; generating access question and answer information based on the corrected follow-up cycle and the type of information to be collected; and obtaining the follow-up physical parameters fed back by the patient based on the access question and answer information.

[0009] Optionally, in the fourth implementation of the first aspect of the present invention, the step of establishing follow-up physical change trend information based on follow-up physical parameters includes: performing data analysis on the follow-up physical parameters to obtain blood pressure parameters, blood glucose parameters, blood lipid parameters, disease type characteristic parameters, and physical sign parameters; obtaining the patient's normal blood pressure value, normal blood glucose value, normal blood lipid value, normal disease type characteristic value, and normal physical sign value, and constructing multiple monitoring reference coordinate systems using the normal blood pressure value, normal blood glucose value, normal blood lipid value, normal disease type characteristic value, and normal physical sign value as the coordinate origin; and using the physical sign parameter as the independent variable and the blood pressure parameter as the dependent variable. The following methods were used to measure blood pressure changes and construct a blood pressure change coordinate system based on the monitoring baseline coordinate system; blood glucose changes and blood lipid changes were constructed based on the monitoring baseline coordinate system; blood lipid changes and disease type characteristics were constructed based on the monitoring baseline coordinate system; and follow-up information on the trend of physical changes was established based on the blood pressure change coordinate system, blood glucose change coordinate system, blood lipid change coordinate system, and disease condition change coordinate system.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the step of predicting the trend of follow-up physical changes based on a preset prediction period to obtain the patient's predicted physical change trend information within the prediction period includes: obtaining the latest physical change parameters from the follow-up physical change trend information and determining the patient's disease level based on the latest physical change parameters; determining a baseline change period associated with the disease level and determining the patient's prediction period based on the baseline change period; and adjusting the time period and curve change of the follow-up physical change trend information based on the prediction period to obtain the predicted physical change trend information.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the step of generating monitoring and analysis results based on the predicted change trend information of the body and the disease information includes: analyzing the predicted change trend information of the body to obtain the predicted change results of the disease, the predicted change results of the physical signs, and the trend of the disease level; extracting the predictive features associated with the disease information from the predicted change results of the disease, the predicted change results of the physical signs, and the trend of the disease level, and generating monitoring and analysis results based on the predictive features.

[0012] A second aspect of the present invention provides a chronic disease monitoring system, comprising: an acquisition module for acquiring patient condition information and determining the patient's condition category based on the condition information; an association module for acquiring information types to be collected associated with the condition category; a follow-up module for acquiring patient follow-up physical parameters based on the information types to be collected and a preset follow-up period; a change module for establishing follow-up physical change trend information based on the follow-up physical parameters; a prediction module for performing trend prediction on the follow-up physical change trend information based on a preset prediction period to obtain the patient's predicted physical change trend information within the prediction period; and an analysis module for generating monitoring analysis results based on the predicted physical change trend information and the condition information.

[0013] A third aspect of the present invention provides a chronic disease monitoring device, the chronic disease monitoring device comprising: a memory and at least one processor, the memory storing instructions; at least one processor calling the instructions in the memory to cause the chronic disease monitoring device to perform the various steps of the chronic disease monitoring method described in any of the preceding claims.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the steps of any of the above-described chronic disease monitoring methods.

[0015] In this invention, by collecting and analyzing patient information, the type of chronic disease is comprehensively determined, and the severity and stage of the disease are assessed, which helps in formulating monitoring and treatment plans. For each chronic disease, key information is identified, irrelevant data is avoided, and accurate basis for decision-making is provided. Patient status is dynamically monitored to promptly detect fluctuations in the condition. Regularly acquired follow-up data is used to observe disease trends, providing data support for adjusting treatment plans, preventing complications, and improving quality of life. Follow-up data is compiled and presented visually using charts or models to help patients understand and take intervention measures. A trend prediction system for follow-up information is established to reduce the risk of disease deterioration and provide comprehensive analysis and assessment, including disease control evaluation, risk warnings, and treatment recommendations. Attached Figure Description

[0016] Figure 1 A flowchart of a chronic disease monitoring method provided in an embodiment of the present invention;

[0017] Figure 2 This is a schematic diagram of the structure of a chronic disease monitoring system provided in an embodiment of the present invention;

[0018] Figure 3 This is a schematic diagram of the structure of a chronic disease monitoring device provided in an embodiment of the present invention. Detailed Implementation

[0019] This invention provides a method, system, device, and storage medium for chronic disease monitoring. By collecting and analyzing patient information, this invention comprehensively determines the type of chronic disease, assesses its severity and stage of development, and helps in formulating monitoring and treatment plans. For each chronic disease, key information is identified, irrelevant data is avoided, and accurate data is provided for decision-making. Patient status is dynamically monitored to promptly detect fluctuations in the condition. Regularly acquired follow-up data is used to observe disease trends, providing data support for adjusting treatment plans, preventing complications, and improving quality of life. Follow-up data is organized and presented visually using charts or models to help patients understand and take intervention measures. A trend prediction system for follow-up information is established to reduce the risk of disease deterioration and provides comprehensive analysis and assessment, including disease control evaluation, risk warnings, and treatment recommendations.

[0020] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the chronic disease monitoring method in this invention includes:

[0022] 101. Obtain the patient's medical information and determine the patient's condition category based on the medical information;

[0023] In this embodiment, by comprehensively collecting and analyzing multi-dimensional information such as the patient's medical records, examination reports, and symptoms, a comprehensive determination of the type of chronic disease can be achieved, including but not limited to hypertension, diabetes, and hyperlipidemia. Simultaneously, the severity and stage of the disease are assessed; given that different chronic diseases have their specific pathological mechanisms, treatment strategies, and development patterns, accurate classification helps in developing targeted follow-up monitoring and treatment plans, thereby improving the accuracy of monitoring and the effectiveness of treatment.

[0024] 102. Obtain the type of information to be collected that is associated with the disease category;

[0025] In this embodiment, specific information requiring focused attention and collection is identified for each type of chronic disease. For example, for diabetic patients, the information to be collected may include blood glucose levels (fasting, postprandial, etc.), glycated hemoglobin, weight, dietary habits, and exercise patterns. For hypertensive patients, the main information collected includes blood pressure, heart rate, family medical history, and lifestyle habits. This approach helps to focus on key information, avoid collecting irrelevant or redundant data, and improve the efficiency and quality of information collection. Furthermore, this specific information is crucial for assessing chronic disease control, predicting disease progression, and adjusting treatment plans, providing institutions with accurate decision-making support.

[0026] 103. Obtain the patient's follow-up physical parameters according to the type of information to be collected and the preset follow-up cycle;

[0027] 104. Establish follow-up physical parameters to track trends;

[0028] In this embodiment, according to a pre-set follow-up cycle, such as weekly, monthly, or quarterly, various physical parameters of patients are collected through outpatient follow-ups, telephone interviews, and online platform records, based on the specific information to be collected. For example, diabetic patients need to measure and record their blood glucose levels, recent diet, and exercise at each follow-up visit; hypertensive patients need to measure their blood pressure and heart rate, and report whether they have taken their medication on time and whether they have any discomfort symptoms. By regularly obtaining follow-up physical parameters, the physical condition of patients with chronic diseases can be dynamically monitored, the changing trend of the patient's condition can be observed, fluctuations or abnormalities can be detected in a timely manner, providing timely data support for adjusting the treatment plan, helping to prevent the occurrence of complications, and improving the patient's quality of life. The physical parameters obtained from each follow-up visit are organized and analyzed, and the changing trends of various physical indicators over time are presented intuitively using charts (such as line graphs, bar charts, etc.) or mathematical models. For example, by plotting a line graph of blood glucose levels over time, one can clearly see the stability of blood glucose control in diabetic patients, as well as whether there is a gradual upward or downward trend. This helps institutions and patients to understand the development of the disease more intuitively, facilitates the early detection of potential problems, and enables early intervention. It also provides patients with a basis for self-management, enhancing their awareness of the disease and adherence to treatment.

[0029] 105. Based on the preset prediction period, the trend of follow-up physical changes is predicted to obtain the predicted trend of physical changes of the patient within the prediction period.

[0030] In this embodiment, the information on predicted changes in the body mainly includes predicted data of core disease indicators, data related to organ function and complications, treatment and intervention response data, disease progression stage data, and multi-indicator comprehensive analysis data.

[0031] Predictive data for key disease indicators include:

[0032] The predicted range of specific indicator values ​​(e.g., predicted fasting blood glucose is 6.5-7.8 mmol / L), the direction of indicator change (increasing / decreasing / stabilizing), and the rate of change (e.g., blood pressure increases by 5 mmHg per month); Example data: The predicted value of postprandial 2-hour blood glucose in diabetic patients gradually increases from the current 8.5 mmol / L to 9.2 mmol / L (in the next 3 months)).

[0033] Predicted data on the achievement of indicators (e.g., the percentage of days with blood glucose levels within the target range decreases from 70% to 50%).

[0034] Predicted frequency of outliers (e.g., the percentage of days with systolic blood pressure ≥140 mmHg in hypertensive patients is predicted to be 40%).

[0035] Treatment and intervention response data include:

[0036] Predictive data on drug efficacy: prediction of changes in indicators after medication (e.g., LDL-C decreasing from 3.6 mmol / L to 3.0 mmol / L after statin treatment).

[0037] Predicting dosage adjustment needs (e.g., increasing antihypertensive medication from 10 mg / day to 15 mg / day to control blood pressure).

[0038] Changes in indicators after exercise intervention (e.g., exercising 3 times a week can result in a weight loss of 2 kg / month).

[0039] The effects of dietary adjustments on indicators (e.g., a low-salt diet can reduce systolic blood pressure by 8 mmHg).

[0040] Data on disease progression stages include:

[0041] The probability of progression of chronic disease stages (e.g., the probability of chronic kidney disease progressing from stage G3 to stage G4 is 15%).

[0042] Predicted rate of progression (e.g., a 30 ml / year decrease in FEV1 for lung function).

[0043] Short-term forecast data (e.g., blood glucose fluctuation range of 6.0-7.5 mmol / L within 1 month);

[0044] Long-term predictive data (such as the risk of blood pressure continuing to rise to 160 / 95 mmHg within 1 year).

[0045] The data from the multi-indicator comprehensive analysis includes:

[0046] Synergistic trends of multiple indicators (e.g., for every 1 mmol / L increase in blood glucose, blood pressure increases by 2 mmHg simultaneously).

[0047] The comprehensive score of metabolic indicators (such as the predicted insulin resistance index HOMA-IR, which increased from 2.5 to 3.0).

[0048] Cardiovascular risk score (e.g., the 10-year risk of coronary heart disease increases from 12% to 18%).

[0049] Individualized disease risk indices (such as the diabetic foot risk score, which increased from 3 to 5 points).

[0050] 106. Generate monitoring and analysis results based on the predicted trend of changes in the body and the information on the condition.

[0051] In this embodiment, by establishing follow-up information on changes in physical condition and predicting trends based on a preset prediction period, the potential development of the disease can be foreseen, providing data support for the formulation of long-term monitoring and treatment plans. By analyzing historical data and current trends, institutions can predict the future trajectory of the disease, thereby preparing in advance and reducing the risk of disease deterioration. For example, based on the blood glucose change trends of a diabetic patient over the past six months, as well as recent treatment and lifestyle adjustments, the possible fluctuation range and direction of blood glucose changes over the next three months can be predicted. A comprehensive analysis and evaluation are conducted, taking into account both the predicted physical change trends and the patient's underlying medical information, such as disease type, disease course, and comorbidities. The analysis results include an evaluation of the patient's current disease control, risk warnings for future disease development, and suggestions for adjusting the treatment plan. For example, for a patient with hypertension and diabetes, based on the predicted trends of blood pressure and blood glucose, combined with current medication and lifestyle, specific suggestions are given regarding adjusting the dosage of antihypertensive and hypoglycemic drugs, strengthening exercise, and dietary control.

[0052] In this embodiment of the invention, through detailed information collection and analysis, the type of chronic disease is comprehensively determined, and the severity and stage of the disease are assessed, which helps in the formulation of monitoring and treatment plans. For each chronic disease, key information is identified, irrelevant data is avoided, and accurate basis for decision-making is provided. Patient status is dynamically monitored to promptly detect fluctuations in the condition. Regularly acquired follow-up data is used to observe disease trends, providing data support for adjusting treatment plans, preventing complications, and improving quality of life. Follow-up data is compiled and presented visually using charts or models to help patients understand and take intervention measures. A trend prediction system for follow-up information is established to reduce the risk of disease deterioration and provide comprehensive analysis and assessment, including disease control evaluation, risk warnings, and treatment recommendations.

[0053] This invention targets patients with hypertension, diabetes, and hyperlipidemia, implementing an information-based and standardized management process based on service standards and technical guidelines. This process covers annual, quarterly, and in-clinic management, as well as some treatment pathways. Personalized health prescriptions are automatically created using health data collected before and during treatment. Patient risk factors are automatically identified using their health examination information, corresponding intervention measures are developed, and risk assessment reports are automatically generated. The number of contracted patients and the quality of contract fulfillment are monitored and managed in real time. The effectiveness of group disease interventions is analyzed and evaluated. Automatic data integration with pre-diagnosis examination data from integrated health machines and data interconnection with higher-level public health systems ensures automatic uploading of data related to these two diseases.

[0054] In a second embodiment of the chronic disease monitoring method of the present invention, step S101 includes:

[0055] 201. Determine the patient's follow-up verification information and extract the associated electronic medical record data based on the follow-up verification information;

[0056] In this embodiment, follow-up verification information can accurately locate the patient's relevant electronic medical record data, ensuring that the acquired data is accurate and directly related to the patient. Electronic medical record data contains rich medical information, such as symptom descriptions, examination results, and diagnostic records, providing comprehensive and detailed raw data for subsequent disease analysis and avoiding misjudgments due to inaccurate or incomplete data.

[0057] 202. Perform a traversal process on the electronic medical record data to obtain patient information;

[0058] 203. Perform word segmentation on the disease information to obtain multiple disease characteristic characters;

[0059] In this embodiment, by traversing and processing electronic medical record data, various types of information can be systematically organized. This comprehensive information extraction method can cover multiple aspects of the illness, including symptoms, progression, and treatment, thus providing sufficient evidence for accurately determining the illness category. It helps to discover key illness information hidden within large amounts of data, improving the accuracy of illness identification. Furthermore, word segmentation transforms complex illness information into individual illness feature characters with specific meanings, making the information more structured and easier to process. These feature characters accurately reflect key elements of the illness, such as symptoms, signs, and disease names, facilitating the rapid location and extraction of key information from massive amounts of text information. This provides more targeted foundational data for subsequent matching and classification work, improving the efficiency and accuracy of illness category identification.

[0060] 204. Match each disease feature character according to the preset disease feature comparison table, and use the disease feature characters with matching results as the target disease characters.

[0061] 205. Determine the patient's condition category based on the target condition character.

[0062] In this embodiment, the pre-defined disease feature lookup table is a standard reference system established based on medical knowledge and clinical experience. By matching the extracted disease feature characters with the lookup table, the patient's disease information can be compared with known disease characteristics, thereby accurately filtering out key information related to specific disease categories. This standardized matching process reduces the subjectivity and uncertainty of human judgment, improves the accuracy and consistency of disease category identification, and ensures that the identification results comply with medical norms and standards. The target disease characters are key information obtained through rigorous screening and matching; they accurately reflect the essence of the patient's condition. Determining the disease category based on these target disease characters can directly and accurately classify the patient's condition into the corresponding category, avoiding classification errors caused by vague or inaccurate information. At the same time, this classification method based on explicit feature characters has high repeatability and reliability; different doctors or systems can obtain relatively consistent results when processing the same data, which is conducive to the unified management of disease information and the consistency of medical decisions.

[0063] In a third embodiment of the chronic disease monitoring method of the present invention, step S102 includes:

[0064] 301. Obtain the corresponding typical physical sign parameter type set based on the characteristics of patients with hypertension, hyperlipidemia, and diabetes;

[0065] 302. Construct multiple collection lists based on various typical vital sign parameter types and preset specific habit indicators;

[0066] 303. Based on the disease category, retrieve the type information that has a mapping relationship with each collection list, and generate the information type to be collected based on the retrieved type information.

[0067] In this embodiment, the disease categories are preset to hypertension, hyperlipidemia, and diabetes. The system searches and matches each disease category in a specific collection list. Based on the character characteristics of the disease category, all type information related to that character characteristic is retrieved from each collection list. (It should be noted that there is a mapping relationship between the information in each collection list and different disease types; for example, hypertension is mapped to blood pressure-related parameters, weight, and height; hyperlipidemia to lipid-related parameters, weight, and height; and diabetes to blood glucose-related parameters, weight, and height.) All type information matching the character characteristic in each collection list is integrated, and then deduplication is performed to remove duplicate information, ultimately forming the information type to be collected corresponding to the disease category. By linking multiple collection lists with disease categories, the system can accurately filter out the relevant information type based on the specific disease category. This method effectively improves the efficiency of patient follow-up information collection, helping patients quickly and accurately provide relevant follow-up information according to the information type to be collected, thus ensuring that the collected information is closely related to the patient's condition.

[0068] In this embodiment, different chronic diseases often manifest differently in patients' physical signs and lifestyle habits. By clarifying the group characteristics of patients with various chronic diseases and obtaining typical physical signs and lifestyle parameter types accordingly, a precise direction can be provided for subsequent data collection. For example, hypertensive patients may have excessive sodium intake and be overweight, while diabetic patients may have fatty liver and a sedentary lifestyle. Transforming these characteristics into specific parameter types, such as sitting for more than 8 hours a day or a waist circumference increase of 3 cm or more per quarter, makes the collected information more targeted, directly reflecting the patient's condition and helping to accurately determine the patient's disease progression and develop personalized treatment and management plans. Combining typical physical sign parameter types with preset specific habit indicators to construct a collection list further improves the comprehensiveness of the collected information. Integrating physical sign parameters and habit indicators into the collection list not only allows for the acquisition of information on the patient's current physical state but also reveals potential factors affecting the condition, such as lifestyle. Such a collection list can provide institutions with richer information, helping to assess the patient's health status from multiple perspectives, providing a more comprehensive basis for disease diagnosis, treatment, and prevention, and improving the effectiveness and practicality of the collected information. By identifying correlated data from multiple data collection lists based on disease category, the system can accurately filter out the types of information to be collected. For example, for patients with hypertension, the data acquisition process will determine hypertension-related vital signs (such as blood pressure and weight) and specific habitual indicators (such as salt intake and exercise) as the information to be collected. This approach avoids collecting irrelevant information, improves collection efficiency, and ensures that the collected information is closely related to the patient's condition. This provides accurate and useful data support for subsequent disease assessment, treatment plan development, and follow-up, making the data collection more targeted and professional, and contributing to improving the quality and effectiveness of chronic disease management.

[0069] In the fourth embodiment of the chronic disease monitoring method of the present invention, step S103 includes:

[0070] 401. Obtain the corresponding follow-up cycle from the preset cycle standard library according to the type of illness;

[0071] 402. Adjust the follow-up cycle based on the patient's condition information to obtain the adjusted follow-up cycle;

[0072] In this embodiment, the patient's age, complication severity, and disease severity are obtained from the disease information. Then, the age, complication severity, and disease severity are graded and assigned values. Corresponding quantitative values ​​are preset according to different severity information to convert this information into numerical values ​​for easy quantification.

[0073] Specifically, the quantitative index is 1 for the age group of 0-44 years old; 2 for the age group of 45-59 years old; 3 for the age group of 60-75 years old; and 4 for the age group of 75 years old and above. The quantitative index is 0 for no complications; 1 for mild complications; 2 for moderate complications; and 3 for severe complications. The quantitative index is 1 for mild chronic disease; 2 for moderate chronic disease; and 3 for severe chronic disease.

[0074] The weighting coefficients for age information, complication severity information, and disease severity information are preset. The risk score is calculated based on the weighting coefficients and the corresponding quantitative values. The formula is: Risk score = weighting coefficient × corresponding quantitative value.

[0075] In this embodiment, the weighting coefficient for age information is 0.25, the weighting coefficient for complication severity information is 0.4, and the weighting coefficient for chronic disease severity information is 0.35.

[0076] Then, a corresponding correction coefficient is matched based on the risk score. When the risk score is within the first threshold range (e.g., 0-1), the first correction coefficient is obtained (e.g., 1.2, which indicates low risk and the follow-up period can be extended by 20%). When the risk score is within the second threshold range (e.g., 1.1-2), the second correction coefficient is obtained (e.g., 1, which indicates medium risk and the preset follow-up period is maintained). When the risk score is within the third threshold range (e.g., 2.1-3), the third correction coefficient is obtained (e.g., 0.8, which indicates high risk and the follow-up period is shortened by 20%). When the risk score is within the fourth threshold range (e.g., 3.1 and above), the fourth correction coefficient is obtained (e.g., 0.5, which indicates high risk and the follow-up period can be extended by 50%).

[0077] Finally, the corrected return period is calculated by adjusting the coefficient and the preset return period. The formula is: Corrected return period = Preset return period × Correction coefficient.

[0078] 403. Generate access Q&A information based on the revised follow-up cycle and the type of information to be collected;

[0079] 404. Obtain follow-up physical parameters based on patient feedback from access question and answer information.

[0080] In this embodiment, the preset follow-up cycle standard library is established based on extensive clinical experience and medical research. Different disease types correspond to different follow-up cycles, ensuring the scientific and standardized nature of the follow-up visits. For example, for some relatively stable chronic diseases, the follow-up cycle may be longer; while for diseases that are prone to fluctuation or are more severe, the follow-up cycle will be shorter. Retrieving the follow-up cycle directly from the standard library based on the disease type provides a basic time framework for follow-up work, ensuring that the frequency of follow-ups is both timely in monitoring changes in the patient's condition and does not place an excessive burden on the patient. Although the preset follow-up cycle has general applicability, each patient's specific condition varies. Adjusting the follow-up cycle based on the patient's detailed condition information allows for personalized adjustments. For example, even for the same disease, factors such as the patient's age, complications, and disease severity will affect the progression and recovery of the condition. By adjusting the follow-up cycle, it is possible to more accurately adapt to each patient's actual situation, ensuring that the follow-up work is more aligned with the patient's needs, improving the targeting and effectiveness of the follow-up, and promptly detecting subtle changes in the patient's condition and taking appropriate measures. By combining the revised follow-up cycle with the types of information to be collected to generate follow-up Q&A information, the follow-up process becomes more standardized and regulated. The Q&A information clearly defines the specific questions to be asked of the patient and the information to be collected within a given follow-up cycle, allowing institutions to conduct follow-ups according to a unified standard and avoiding omissions or arbitrariness. This approach also helps improve patient cooperation, as patients clearly understand the purpose and content of each follow-up, reducing unnecessary confusion and misunderstandings. The Q&A information provides clear guidance for obtaining the patient's follow-up physical parameters. Institutions can collect targeted physical parameters such as blood pressure, blood sugar, and weight based on these questions, ensuring that the collected data is accurate, complete, and closely related to the patient's condition. These follow-up physical parameters directly reflect changes in the patient's physical condition over a period of time, providing important evidence for institutions to assess disease progression and adjust treatment plans, thus facilitating dynamic monitoring and precise management of the patient's condition.

[0081] In the fifth embodiment of the chronic disease monitoring method of the present invention, step S104 includes:

[0082] 501. Perform data analysis on follow-up physical parameters to obtain parameters such as blood pressure, blood glucose, blood lipids, disease type characteristics, and physical signs;

[0083] 502. Obtain the patient's normal blood pressure, normal blood glucose, normal blood lipid, normal disease type characteristic value, and normal physical sign value, and construct multiple monitoring reference coordinate systems using the normal blood pressure, normal blood glucose, normal blood lipid, normal disease type characteristic value, and normal physical sign value as the coordinate origin;

[0084] In this embodiment, by analyzing follow-up physical parameters and breaking them down into different key parameters, a clearer understanding of the patient's overall physical condition can be achieved. Blood pressure, blood glucose, and blood lipids are important indicators in chronic disease monitoring, directly reflecting the disease's progression. Disease type characteristic parameters help to further clarify the specific characteristics and development stages of the disease, while physical sign parameters may be related to the occurrence and development of the disease; for example, obesity may be a risk factor for many chronic diseases. A monitoring baseline coordinate system is constructed using normal reference values ​​as the origin, providing a clear reference standard for assessing various patient indicators. By comparing the patient's actual measurements with the normal range, the degree to which the patient's indicators deviate from normal levels can be visually observed, facilitating timely detection of abnormalities. For example, in the blood pressure change coordinate system, if the patient's blood pressure parameter deviates from the position with the normal blood pressure value as the origin, it can be determined that their blood pressure has experienced abnormal fluctuations, helping to detect abnormal blood pressure trends early and providing a basis for disease prevention and control.

[0085] It should be noted that the disease type characteristic parameters are quantitative indicators that reflect the specific characteristics and development stages of a particular disease. Different disease types correspond to different physical quantities. To facilitate understanding, the following examples are provided for illustration:

[0086] The characteristic parameter for hypertension is the diurnal blood pressure fluctuation range.

[0087] The characteristic parameter for diabetes-related disease types is the postprandial blood glucose fluctuation range.

[0088] The characteristic parameter for hyperlipidemia-related disease types is the number of dietary control responses (the number of times a low-fat diet was followed).

[0089] 503. Take vital signs as independent variables and blood pressure as dependent variables, and construct a blood pressure change coordinate system based on the monitoring reference coordinate system;

[0090] 504. Using vital signs as independent variables and blood glucose as dependent variables, a blood glucose change coordinate system is constructed based on the monitoring baseline coordinate system.

[0091] 505. Using vital signs as independent variables and blood lipid parameters as dependent variables, a blood lipid change coordinate system is constructed based on the monitoring benchmark coordinate system.

[0092] 506. Take the vital signs parameters as independent variables and the disease type characteristic parameters as dependent variables, and construct a disease change coordinate system based on the monitoring baseline coordinate system;

[0093] In this embodiment, vital signs are used as independent variables, and other parameters are used as dependent variables to construct different coordinate systems. This helps to clearly reveal the relationship between vital signs and other chronic disease-related indicators. For example, in the blood pressure change coordinate system, it is possible to observe how blood pressure changes accordingly with changes in vital signs (such as weight, waist circumference, etc.). This helps to discover potential patterns, such as weight gain potentially leading to elevated blood pressure, thus providing a basis for developing targeted interventions. Each coordinate system can visually display the trend of the corresponding indicator with changes in vital signs. By observing the distribution and trends of data points in these coordinate systems, institutions can promptly identify the direction and speed of changes in patients' blood pressure, blood glucose, blood lipids, and disease type characteristic parameters. For example, in the blood glucose change coordinate system, if the data points show an upward trend, it indicates that the patient's blood glucose may be gradually increasing, facilitating timely adjustments to the treatment plan or providing lifestyle guidance. The establishment of multiple coordinate systems makes comparative analysis between different indicators possible. Institutions can simultaneously observe changes in data in different coordinate systems to comprehensively assess the patient's overall health status. For example, comparing blood pressure and blood sugar changes on a coordinate system may indicate that the patient's condition is more complex and requires more comprehensive treatment and management measures.

[0094] 507. Establish follow-up information on the trend of physical changes based on the coordinate systems of blood pressure changes, blood glucose changes, blood lipid changes, and disease condition changes.

[0095] In this embodiment, by integrating multiple coordinate systems to establish follow-up information on changes in physical condition, the dynamic changes in the patient's physical status can be comprehensively reflected. It integrates trends in blood pressure, blood sugar, blood lipids, and disease type characteristics, enabling institutions to gain a more comprehensive and systematic understanding of the progression of the patient's chronic disease. This comprehensive trend information helps institutions make accurate judgments and predictions about the patient's condition, ensuring consistency in treatment outcomes across different institutions. It also provides strong support for developing personalized treatment plans, adjusting treatment strategies, and conducting targeted health management.

[0096] In the sixth embodiment of the chronic disease monitoring method of the present invention, step S105 includes:

[0097] 601. Obtain the latest physical change parameters from the follow-up physical change trend information, and determine the patient's disease level based on the latest physical change parameters;

[0098] In this embodiment, after obtaining the latest body change parameters, that is, the latest data pair of blood pressure parameter + vital sign parameter, or blood glucose parameter + vital sign parameter, or blood lipid parameter + vital sign parameter and disease type characteristic parameter + vital sign parameter are obtained; the normal parameter value is determined based on the coordinate origin of each change coordinate system, and then the deviation value is calculated based on the normal reference value and the latest parameter value. The formula is: deviation = (latest parameter value - normal parameter value) / normal parameter value × 100%.

[0099] Then, the corresponding parameters are graded based on the degree of deviation. For example, a deviation of 10%-20% for blood pressure parameters results in a score of 1; 20%-30% results in a score of 2; and 30% or more results in a score of 3. Similarly, a deviation of 10%-20% for diurnal blood pressure fluctuations results in a score of 1; 20%-30% results in a score of 2; and 30% or more results in a score of 3. For vital signs parameters, a deviation of 5%-10% results in a score of 1; 10%-20% results in a score of 2; and 20% or more results in a score of 3. It should be noted that the calculation method for deviation values ​​of blood glucose, blood lipids, and other disease-related characteristic parameters is the same and will not be repeated here.

[0100] Subsequently, a comprehensive score is calculated based on preset scoring weights. The formula for the comprehensive blood pressure score is: Comprehensive Blood Pressure Score = (Blood Pressure Parameter Deviation Score × First Weight) + (Deviation Score of Hypertension Disease Type Characteristic Parameter (i.e., Deviation Score of Diurnal Blood Pressure Fluctuation) × Second Weight) + (Deviation Score of Vital Sign Parameter × Third Weight). Similarly, the calculation methods for the comprehensive blood lipid score and the comprehensive blood glucose score are the same, and will not be listed here. It should be noted that the first weight is configured as 0.4, the second weight as 0.5, and the third weight as 0.1.

[0101] Once the comprehensive blood pressure score, blood glucose score, or blood lipid score is calculated, it is compared with a preset reference table. If the comprehensive blood pressure score, blood glucose score, or blood lipid score is within the first comprehensive range (e.g., 0-0.5 points), the condition is rated as stable; if the comprehensive blood pressure score, blood glucose score, or blood lipid score is within the second comprehensive range (e.g., 0.6-1.5 points), the condition is rated as mildly abnormal; if the comprehensive blood pressure score, blood glucose score, or blood lipid score is within the third comprehensive range (e.g., 1.6-3.0 points), the condition is rated as moderately abnormal; if the comprehensive blood pressure score, blood glucose score, or blood lipid score is within the fourth comprehensive range (e.g., greater than 3.0 points), the condition is rated as severely abnormal.

[0102] The above methods can accurately determine the patient's condition level based on the latest changes in their physical parameters.

[0103] 602. Determine the baseline change period associated with the severity of the illness, and determine the patient's prediction period based on the baseline change period;

[0104] In this embodiment, a baseline period is preset for different disease severity levels, with shorter periods for more severe conditions. For example: stable - 3 months, mild abnormality - 1 month, moderate abnormality - 2 weeks, severe abnormality - 1 week. The baseline period is adjusted based on factors such as disease progression rate and treatment intervention frequency. For example, for rapidly progressing diseases (meaning that in the last n follow-ups, the increase in core indicators (such as blood pressure, blood sugar, blood lipids, etc.) exceeds the moderate abnormality standard for the corresponding disease level each time, and shows an accelerating trend; or the standard deviation of the indicator fluctuation in the last n follow-ups exceeds the upper limit of the corresponding disease level, and shows no downward trend; here, n can be set to 3, 4, 5, etc., depending on actual needs), the predicted period is 0.8 times the baseline period; for stable treatment plans, the predicted period is the same as the baseline period.

[0105] To aid understanding, the following example illustrates this: Patient B's condition is classified as moderately abnormal, corresponding to a baseline change period of 2 weeks. Considering the need for close monitoring of blood pressure response to drug treatment in cases of hypertension, the prediction period is adjusted to 0.8 times the baseline period, i.e., 1.6 weeks (two weeks is 14 days, and the baseline period is 14 days × 0.8 = 11.2 days; for ease of clinical practice, it is rounded down to 11 days here).

[0106] 603. Based on the time period and curve changes of the predicted periodic adjustment follow-up information on the trend of changes in the body, the predicted trend of changes in the body is obtained.

[0107] In this embodiment, the disease severity is determined by obtaining the latest physical change parameters from follow-up physical change trend information, which can reflect the current severity of the patient's condition in a timely manner. These parameters are extracted based on the change trends presented in multiple coordinate systems, integrating information from multiple aspects such as blood pressure, blood sugar, blood lipids, and disease type characteristics. The disease severity determined based on this can provide an accurate starting point and basis for subsequent predictions. For example, if the latest physical change parameters show that the patient's various indicators fluctuate greatly and the disease severity is high, then when making predictions for each coordinate system, it is necessary to consider the factor that the disease may develop rapidly, and adjust the prediction parameters accordingly to make the prediction results more consistent with the patient's actual situation and improve the accuracy of the prediction. The disease severity is associated with a baseline change period, which allows the prediction period to be customized according to the specific severity of the patient's condition. Different disease severity levels often mean that the speed and pattern of disease development are different. By determining the corresponding baseline change period, the rhythm of disease changes can be grasped more accurately. For example, for patients with a high disease severity, their baseline change period may be shorter, indicating that the condition may change significantly in a short period of time. Therefore, the prediction period will also be shortened accordingly, requiring more frequent monitoring and prediction of the patient's physical condition. This allows for the timely detection of subtle changes in the patient's condition, providing doctors with more timely information to adjust treatment plans and helping to better control disease progression. For each coordinate system, a reasonable prediction period ensures that the prediction results more closely match actual trends, avoiding errors caused by predictions that are too long or too short. Adjusting the follow-up body change trend information according to the prediction period allows the data and curves in each coordinate system to more accurately reflect future trends. By adjusting the time period, past trends can be reasonably extended into future prediction periods, taking into account the continuity and regularity of disease development. Simultaneously, adjusting curve changes can modify the slope and amplitude of the curves based on factors such as the severity of the disease and the baseline change period, making them more consistent with the patient's disease progression characteristics. For example, if the patient's condition is likely to worsen rapidly within the prediction period, adjusting the curve changes will make the curves in each coordinate system steeper to reflect the potential for indicators to deviate from the normal range more quickly. The resulting predicted body change trend information provides doctors with more intuitive and accurate prediction results, helping them to develop intervention measures in advance, more effectively manage and control patients' chronic diseases, and improve treatment outcomes and patients' quality of life.

[0108] Time period extraction: Data from the past follow-up data, up to 10 days prior to the most recent follow-up, is extracted as the basis for analysis. For example, daily blood pressure measurements, fasting and postprandial blood glucose levels, and blood lipid test results for the past 10 days are obtained.

[0109] Curve Adjustment: Using a time series analysis model, combined with the patient's disease severity and baseline change period, the curves in each coordinate system were adjusted. Due to the severity of the patient's condition and its accelerating deterioration trend, in the blood pressure coordinate system, the slope of the predicted curve was adjusted to be steeper, with an increase of 1 mmHg per day (from 160 mmHg to 170 mmHg within 10 days), which is three times the initial slope. It is predicted that after 10 days, systolic blood pressure may rise to 170 mmHg and diastolic blood pressure to 105 mmHg. In the blood glucose coordinate system, the fasting blood glucose curve is expected to rise to 10.0 mmol / L, and the 2-hour postprandial blood glucose curve is expected to rise to 14.5 mmol / L. In the blood lipid coordinate system, the total cholesterol and LDL-C curves also show an upward trend, with total cholesterol expected to reach 7.0 mmol / L and LDL-C expected to reach 4.5 mmol / L.

[0110] Through this adjustment, the resulting information on predicted changes in the body is presented to doctors in an intuitive chart format. Based on these predictions, doctors can develop intervention measures in advance, such as adjusting the dosage of antihypertensive and hypoglycemic drugs, advising patients to strengthen dietary control and increase exercise, thereby enabling more effective management of their chronic diseases, reducing the risk of complications, and improving their quality of life.

[0111] It should be noted that the time series analysis models here mainly refer to the ARIMA model (autoregressive integral moving average model) and the Prophet model, which are combined to capture the dynamic changes of chronic disease indicators.

[0112] ARIMA models excel at handling short-term fluctuating data (such as daily measurements of blood pressure and blood sugar). By analyzing the autocorrelation of historical data (such as the influence of blood pressure from the previous 3 days on the current day) and eliminating non-stationarity (such as removing abnormal fluctuations caused by random factors), they provide basic trend parameters for curve prediction.

[0113] The Prophet model is more suitable for data with long-term trends and periods (such as changes in blood lipids with dietary cycles). It can automatically identify trend items (such as continuous increases caused by disease deterioration) and periodic items (such as regular fluctuations in weekly measurements). It also has strong tolerance for missing values ​​and outliers (such as missed blood glucose values) commonly found in follow-up data.

[0114] In practical applications, the two models are used in combination: first, ARIMA is used to capture short-term fluctuation characteristics, and then Prophet is used to correct long-term trends, ensuring that the predictions not only match recent indicator changes but also conform to the long-term patterns of disease development (such as the coordinated upward trend of indicators in patients with hypertension and diabetes).

[0115] When adjusting the slope, if the condition progresses slowly (e.g., stable or mildly abnormal), the slope is close to the historical average (e.g., a 3-5 mmHg increase per week in hypertensive patients); if the condition worsens rapidly, the slope increases significantly (i.e., the curve is steeper) to reflect the trend of the indicator rapidly deviating from the normal range.

[0116] In the seventh embodiment of the chronic disease monitoring method of the present invention, step S106 includes:

[0117] 701. Analyze the information on predicted changes in the body to obtain the results of predicted changes in the disease condition, the results of predicted changes in physical signs, and the trend of changes in the disease severity.

[0118] To aid understanding, the following example will be used to illustrate the point:

[0119] Case 1: Hypertension patient

[0120] Suppose a 58-year-old female patient has a 5-year history of hypertension. Her predicted health trend information shows that within the next 2 months, her systolic blood pressure will gradually increase from the current 150 mmHg to 165 mmHg, her diastolic blood pressure will increase from 95 mmHg to 105 mmHg, and her heart rate may increase from 75 beats / minute to 85 beats / minute.

[0121] Predicted changes in condition: Persistently elevated blood pressure indicates a worsening of hypertension, which may increase the risk of cardiovascular and cerebrovascular complications.

[0122] Predictive changes in vital signs: Increased systolic blood pressure, diastolic blood pressure, and heart rate indicate increased cardiac load and increased pressure on blood vessel walls.

[0123] Disease severity trend: According to the hypertension grading criteria, this patient's condition will progress from mild to moderate abnormality.

[0124] Case 2: Diabetic patient

[0125] Suppose a 62-year-old male patient has been diagnosed with type 2 diabetes for 8 years. Predictive data shows that in the next 3 months, his fasting blood glucose will rise from 8.5 mmol / L to 9.8 mmol / L, his glycated hemoglobin will rise from 7.2% to 8.0%, and he will also experience a worsening of lower limb numbness.

[0126] Predicted changes in condition: Worsening blood sugar control indicates progression of diabetes and may accelerate the development of complications such as diabetic nephropathy and retinopathy.

[0127] Predictive changes in physical signs: Elevated blood glucose and glycated hemoglobin, accompanied by worsening lower limb neuropathy, reflect the increased damage of diabetes to multiple systems of the body.

[0128] The trend of disease severity changes: the disease progresses from a mild fluctuating state to a severe fluctuating state.

[0129] Case 3: Patients with hyperlipidemia

[0130] Suppose a 45-year-old male patient has a 3-year history of hyperlipidemia. It is predicted that in the next month, total cholesterol will rise from 6.0 mmol / L to 6.8 mmol / L, LDL cholesterol will rise from 3.8 mmol / L to 4.5 mmol / L, and there will be a trend of increasing carotid artery plaque.

[0131] Predicted changes in the condition: Blood lipid levels continue to rise, the process of atherosclerosis accelerates, and the risk of coronary heart disease and stroke increases significantly.

[0132] Predictive changes in vital signs: worsening of blood lipid levels and enlargement of carotid artery plaques indicate increased lipid deposition in blood vessels.

[0133] The disease severity trend shows a progression from the early stage of hyperlipidemia to the high-risk stage.

[0134] 702. Extract predictive features associated with disease information from the predicted changes in disease status, predicted changes in physical signs, and trends in disease severity, and generate monitoring and analysis results based on these predictive features.

[0135] In this embodiment, the predictive feature extraction needs to be determined based on preset parameters corresponding to different disease types, such as:

[0136] Hypertension: The magnitude of the increase in systolic and diastolic blood pressure, changes in heart rate, and other symptoms are extracted as predictive features. For example, a patient's systolic blood pressure rising by 15 mmHg and diastolic blood pressure rising by 10 mmHg are closely related to the worsening of hypertension.

[0137] Diabetes mellitus: Changes in fasting blood glucose and glycated hemoglobin (HbA1c) are selected as predictive features. For example, if a patient's fasting blood glucose increases by 1.3 mmol / L and HbA1c increases by 0.8%, these are key predictive features of diabetes progression.

[0138] Hyperlipidemia: Changes in total cholesterol and LDL cholesterol, as well as the presence of other cardiovascular risk factors (such as smoking and obesity), are used as predictive features. For example, if a patient has elevated LDL cholesterol of 0.7 mmol / L and a smoking habit, these features are crucial for assessing the risk of hyperlipidemia.

[0139] The monitoring and analysis results are also categorized according to different disease types, such as:

[0140] Hypertension: Monitoring and analysis results show that a patient's hypertension has worsened, and the risk of cerebral hemorrhage in the next 2 months has increased by 15%. It is recommended to immediately adjust the dosage of antihypertensive drugs, increase the frequency of blood pressure monitoring (from once a day to twice a day), and strictly control sodium intake.

[0141] Diabetes: The analysis results show that a patient with poorly controlled diabetes has a 20% risk of developing diabetic foot within 3 months. It is recommended to adjust the blood sugar control regimen, increase the insulin dose, and at the same time strengthen foot care and regular check-ups.

[0142] Hyperlipidemia: Monitoring and analysis results of a patient indicated that their atherosclerosis was progressing rapidly, with a 12% increase in the risk of myocardial infarction within one month. It was recommended to add high-intensity statin therapy to enhance lipid-lowering treatment, while quitting smoking and controlling weight.

[0143] In this embodiment, the predicted trend information of physical changes is analyzed to obtain the predicted changes in disease condition, physical signs, and disease severity, providing a comprehensive overview of the patient's physical condition from multiple dimensions. The predicted changes in disease condition directly reflect the direction of disease development and the potential degree of change, enabling institutions to quickly understand whether the patient's condition is improving, stabilizing, or worsening. The predicted changes in physical signs focus on the trends in the patient's external physical form, which is significant for monitoring certain chronic diseases related to physical signs, such as obesity-related diseases, as changes in physical signs may indicate potential changes in the disease or the manifestation of treatment effects. The disease severity trend integrates the disease condition and other relevant factors, presenting the overall severity of the patient's condition from a more macroscopic perspective, providing a strong basis for a comprehensive assessment of the patient's condition. Extracting predictive features associated with disease information from multiple prediction results allows for precise filtering of the most valuable information for disease monitoring and analysis. This avoids interference from a large amount of irrelevant or secondary information, making the monitoring and analysis results more focused and accurate. By selectively extracting these features, we can delve deeper into the potential patterns and key factors in disease progression, such as the correlation between specific indicator changes or signs and disease worsening, providing a more direct and effective basis for subsequent analysis and decision-making. The monitoring and analysis results generated from the extracted predictive features can provide targeted guidance for the institution's clinical practice. These results are based on in-depth analysis of individual patient disease-related information, taking into account the specific characteristics of the patient's condition and predicted trends, thus better meeting the needs of personalized medicine. Institutions can use these monitoring and analysis results to develop personalized treatment plans, adjust follow-up strategies, or provide more precise health advice for patients.

[0144] Specifically, once the predicted features are obtained, they are then visualized and edited based on a preset visualization template to generate monitoring and analysis results for user reference.

[0145] It should be noted that feature selection is mainly determined based on different disease types.

[0146] Hypertension: Extract the rate of change of systolic / diastolic blood pressure, diurnal blood pressure fluctuation range, age, weight, etc.

[0147] Diabetes: blood glucose-related parameters, weight change trends, etc.

[0148] High blood lipids: blood lipid-related parameters, frequency of dietary control responses, weight change trends, etc.

[0149] For example, a patient with hypertension and diabetes has predictive characteristics showing: a monthly increase of 5 mmHg in systolic blood pressure and 3 mmHg in diastolic blood pressure; persistently high fasting blood glucose (>8.0 mmol / L) and glycated hemoglobin (>7.5%); a body mass index (BMI) increasing from 28 kg / m² to 30 kg / m², and triglycerides increasing from 2.5 mmol / L to 3.2 mmol / L. These characteristics collectively point to an exacerbation of metabolic disorder, suggesting the need for simultaneous and intensive treatment to lower blood pressure, blood sugar, and lipids, as well as weight control.

[0150] The chronic disease monitoring method in the embodiments of the present invention has been described above. The chronic disease monitoring system in the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 2 One embodiment of the chronic disease monitoring system in this invention includes:

[0151] The acquisition module 801 is used to acquire the patient's medical information and determine the patient's medical condition category based on the medical information;

[0152] The association module 802 is used to obtain the type of information to be collected that is associated with the disease category based on the disease category;

[0153] The follow-up module 803 is used to obtain the patient's follow-up physical parameters according to the type of information to be collected and the preset follow-up cycle;

[0154] The change module 804 is used to establish follow-up body change trend information based on follow-up body parameters;

[0155] The prediction module 805 is used to predict the trend of follow-up physical changes based on a preset prediction period, and to obtain the predicted trend of physical changes of the patient within the prediction period.

[0156] Analysis module 806 is used to generate monitoring and analysis results based on the predicted trend of changes in the body and the information on the condition.

[0157] above Figure 2 The chronic disease monitoring system in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The chronic disease monitoring device in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0158] Figure 3 This is a schematic diagram of the structure of a chronic disease monitoring device 900 provided in an embodiment of the present invention. The chronic disease monitoring device 900 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 910 (e.g., one or more processors) and a memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and storage media 930 can be temporary or persistent storage. The program stored in the storage media 930 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the chronic disease monitoring device 900. Furthermore, the processor 910 may be configured to communicate with the storage media 930 and execute the series of instruction operations in the storage media 930 on the chronic disease monitoring device 900 to implement the steps of the chronic disease monitoring method provided in the above-described method embodiments.

[0159] The chronic disease monitoring device 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 3 The illustrated chronic disease monitoring device structure does not constitute a limitation on the chronic disease monitoring device and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0160] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of a chronic disease monitoring method.

[0161] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system or system / unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0162] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0163] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring chronic diseases, characterized in that, include: Obtain the patient's medical information and determine the patient's condition category based on the information; Obtain the type of information to be collected that is associated with the disease category; Obtain the patient's follow-up physical parameters based on the type of information to be collected and the preset follow-up cycle; Establish information on the trend of changes in body characteristics based on follow-up body parameters; Based on the preset prediction period, the trend of follow-up physical changes is predicted to obtain the predicted trend of physical changes of the patient within the prediction period. Monitoring and analysis results are generated based on predicted trends in bodily changes and disease information; The step of obtaining the patient's follow-up physical parameters based on the type of information to be collected and the preset follow-up period includes: Data analysis was performed on the follow-up physical parameters to obtain parameters such as blood pressure, blood glucose, blood lipids, disease type characteristics, and physical signs. The normal blood pressure, blood glucose, blood lipid, normal disease type characteristic value, and normal physical sign value of the patient were obtained, and multiple monitoring reference coordinate systems were constructed using the normal blood pressure, blood glucose, blood lipid, normal disease type characteristic value, and normal physical sign value as the coordinate origin. Vital signs parameters are used as independent variables, blood pressure parameters are used as dependent variables, and a blood pressure change coordinate system is constructed based on the monitoring baseline coordinate system. Vital signs parameters are used as independent variables, blood glucose parameters are used as dependent variables, and a blood glucose change coordinate system is constructed based on the monitoring baseline coordinate system. Vital signs parameters were used as independent variables, blood lipid parameters were used as dependent variables, and a blood lipid change coordinate system was constructed based on the monitoring benchmark coordinate system. Using vital signs parameters as independent variables and disease type characteristic parameters as dependent variables, a disease condition change coordinate system is constructed based on the monitoring baseline coordinate system. Information on the trend of physical changes was established based on the coordinate systems of blood pressure changes, blood sugar changes, blood lipid changes, and disease condition changes.

2. The chronic disease monitoring method according to claim 1, characterized in that, The process of obtaining the patient's medical information and determining the patient's medical condition category based on the medical information includes: Determine the patient's follow-up verification information and extract the associated electronic medical record data based on the follow-up verification information; The electronic medical record data is traversed and processed to obtain patient information; The disease information is segmented into words to obtain multiple disease characteristic characters; The disease feature characters are matched according to the preset disease feature comparison table to obtain the disease feature characters with matching results as the target disease characters. The patient's condition category is determined based on the target condition character.

3. The chronic disease monitoring method according to claim 1, characterized in that, The process of obtaining the type of information to be collected that is associated with the disease category based on the disease category includes: Based on the characteristics of patients with hypertension, hyperlipidemia, and diabetes, obtain the corresponding typical sign parameter type sets; Multiple collection lists are constructed based on various typical vital sign parameter types and preset specific habit indicators; Based on the disease category, retrieve the type information that has a mapping relationship with each collection list, and generate the type of information to be collected based on the retrieved type information.

4. The chronic disease monitoring method according to claim 1, characterized in that, The process of obtaining the patient's follow-up physical parameters based on the type of information to be collected and the preset follow-up period includes: The corresponding follow-up cycle is obtained from the preset cycle standard library according to the type of illness; The follow-up cycle is adjusted based on the patient's condition information to obtain the revised follow-up cycle. Generate access Q&A information based on the revised follow-up cycle and the type of information to be collected; Follow-up physical parameters obtained from patient feedback are based on access question and answer information.

5. The chronic disease monitoring method according to claim 1, characterized in that, The process of predicting the trend of physical changes based on a preset prediction period to obtain the patient's predicted physical change trend information within the prediction period includes: The latest physical change parameters are obtained from the follow-up physical change trend information, and the patient's disease level is determined based on the latest physical change parameters; The baseline change period associated with the severity of the illness is determined, and the patient's prediction period is determined based on this baseline change period. Based on the time period and curve changes of the predicted periodic adjustment follow-up information on the trend of changes in the body, information on the predicted trend of changes in the body is obtained.

6. The chronic disease monitoring method according to claim 1, characterized in that, The generation of monitoring and analysis results based on predicted changes in the body and disease information includes: Analyze the information on predicted changes in the body to obtain the predicted changes in the disease condition, the predicted changes in physical signs, and the trend of changes in the disease severity. Predictive features associated with disease information are extracted from the predicted changes in disease status, predicted changes in physical signs, and trends in disease severity, and monitoring and analysis results are generated based on these predictive features.

7. A chronic disease monitoring system, characterized in that, include: The acquisition module is used to acquire the patient's medical information and determine the patient's medical condition category based on the medical information; The association module is used to obtain the types of information to be collected that are associated with the disease category; The follow-up module is used to acquire patients' follow-up physical parameters according to the type of information to be collected and the preset follow-up cycle; to perform data analysis on the follow-up physical parameters to obtain blood pressure, blood glucose, blood lipid, disease type characteristic parameters, and vital sign parameters; to acquire the patient's normal blood pressure, normal blood glucose, normal blood lipid, normal disease type characteristic values, and normal vital sign values, and to construct multiple monitoring benchmark coordinate systems using normal blood pressure, normal blood glucose, normal blood lipid, normal disease type characteristic values, and normal vital sign values ​​as the origin; and to use vital sign parameters as independent variables and blood pressure parameters as dependent variables, and to monitor... A blood pressure change coordinate system is constructed using a baseline coordinate system. A blood glucose change coordinate system is constructed using vital signs as independent variables and blood lipid parameters as dependent variables. A disease condition change coordinate system is constructed using vital signs as independent variables and disease condition type characteristics as dependent variables. Based on these coordinate systems, information on the trend of physical changes during follow-up is established. The change module is used to establish follow-up physical change trend information based on follow-up physical parameters; The prediction module is used to predict the trend of follow-up physical changes based on a preset prediction period, and to obtain the predicted trend of physical changes of the patient within the prediction period. The analysis module is used to generate monitoring and analysis results based on the predicted trend of changes in the body and the information on the condition.

8. A chronic disease monitoring device, characterized in that, The chronic disease monitoring device includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the chronic disease monitoring device to perform the steps of the chronic disease monitoring method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the chronic disease monitoring method as described in any one of claims 1-6.

Images