Follow-up chronic disease management system based on Internet technology

Abstract

The present invention discloses a follow-up chronic disease management system based on Internet technology, which relates to the field of data processing technology. The system includes: a chronic disease acquisition module, which is used to obtain the target chronic disease of a target patient and the first reference chronic disease of a first reference patient; a region determination module, which is used to determine the main incidence area of the target chronic disease based on the first reference chronic disease of each first reference patient and the region to which each first reference patient belongs; a chronic disease analysis module, which is used to determine the similarity of the number of illnesses and the symptom matching factor between the target patient and each second reference patient based on the target chronic disease and the second reference chronic disease of each second reference patient; a follow-up number determination module, which is used to determine the first follow-up number of the target patient within a preset time period based on the similarity of the number of illnesses, the symptom matching factor, and the reference follow-up number of each second reference patient within a preset time period. The present invention can improve the accuracy of the follow-up number of the target patient.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a follow-up chronic disease management system based on Internet technology. Background Art

[0002] Chronic diseases, or CWDs, are conditions with a long course and relatively gradual progression. Given the significant differences in the progression of different types of CWDs, and the distinct differences in the progression of the same CWD across different patients, effective and scientific management of CWDs requires long-term, continuous monitoring. The key to precise CWD management lies in tailoring follow-up visits based on the patient's current health status and the specific progression of the disease.

[0003] Currently, in actual operations, individual characteristic information such as the patient's age, gender, and past medical history is usually collected first. With the help of machine learning models, these personalized data are deeply analyzed to predict the patient's health trend. Based on this, the theoretically appropriate number of follow-up visits is calculated for each patient.

[0004] However, this method has obvious limitations. It only focuses on the basic characteristics of individual patients, which directly leads to the poor accuracy of the calculated number of patient follow-up visits. Summary of the Invention

[0005] The embodiment of the present invention provides a follow-up chronic disease management system based on Internet technology, which can effectively improve the accuracy of the number of follow-up visits for target patients.

[0006] A first aspect of an embodiment of the present invention provides a follow-up chronic disease management system based on Internet technology, comprising:

[0007] A chronic disease acquisition module, used to acquire a target chronic disease of a target patient and a first reference chronic disease of a first reference patient;

[0008] A region determination module, configured to determine a major incidence region of a target chronic disease based on the first reference chronic disease of each first reference patient and the region to which each first reference patient belongs;

[0009] a chronic disease analysis module for determining, based on the target chronic disease of the target patient and the second reference chronic disease of each second reference patient, a similarity in the number of diseases suffered by the target patient and a symptom matching factor, wherein the second reference patient is the first reference patient whose region is a major incidence region of the target chronic disease;

[0010] The follow-up number determination module is used to determine the first follow-up number of the target patient within the preset time period based on the similarity of the number of diseases, the matching factors of the diseases, and the reference follow-up number of each second reference patient within the preset time period.

[0011] In some possible implementations, the chronic disease analysis module specifically includes:

[0012] A quantity similarity determination unit is configured to determine the similarity in the number of diseases of the target patient and the target second reference patient using the number of the first identical chronic disease in the target chronic disease of the target patient and the target second reference patient, where the target second reference patient is any second reference patient;

[0013] a symptom similarity determination unit, configured to compare each target chronic disease with each target second reference chronic disease, respectively, to obtain symptom similarities between each target chronic disease and each target second reference chronic disease;

[0014] The matching factor determination unit is used to determine the disease matching factor between the target patient and the target second reference patient by using the similarities of each disease.

[0015] In some possible implementations, the disease similarity determination unit is specifically configured to:

[0016] Obtaining first symptom description information of a target chronic disease and second symptom description information of a target second reference chronic disease;

[0017] Performing word segmentation processing on the first symptom description information and the second symptom description information respectively to obtain a first word segmentation set and a second word segmentation set;

[0018] A similarity calculation is performed on the first segmentation set and the second segmentation set to obtain the symptom similarity between the target chronic disease and the target second reference chronic disease.

[0019] In some possible implementations, the follow-up number determination module is specifically configured to:

[0020] Using the similarity of the number of illnesses and the matching factor of each symptom, the matching degree of the target patient's condition with each second reference patient is determined respectively;

[0021] The first follow-up number of the target patient within the preset time period is determined by using the matching degree of each disease condition and the reference follow-up number.

[0022] In some possible implementations, the region determination module is specifically configured to:

[0023] Based on the first reference chronic disease of each first reference patient and the region to which each first reference patient belongs, determining the number of second identical chronic diseases in each region, where the number of second identical chronic diseases is the number of first reference chronic diseases that are identical to the target chronic disease in the region;

[0024] The reference value for each region was determined using the number of the second common chronic disease in each region;

[0025] The areas with the greatest reference value will be identified as the main incidence areas of the target chronic diseases.

[0026] In some possible implementations, after determining the first number of follow-up visits for the target patient within the preset time period based on the similarity of the number of illnesses, the matching factor of each disease, and the reference number of follow-up visits for each second reference patient within the preset time period, the system further includes:

[0027] a distribution consistency determination module, configured to determine the consistency of disease distribution between the target patient's region and the main incidence area based on the number of various chronic diseases in the main incidence area of the target chronic disease and the number of various chronic diseases in the target patient's region;

[0028] A climate consistency determination module is used to determine the climate consistency between the target patient's location and the main disease-prone area based on the climate data of the main disease-prone area and the climate data of the target patient's location;

[0029] A comprehensive similarity determination module is used to determine the comprehensive similarity between the target patient's location and the main disease-prone area by using the consistency of symptom distribution and climate consistency;

[0030] The follow-up number correction module is used to use the comprehensive similarities to correct the first follow-up number of the target patient within the preset time period to obtain the second follow-up number of the target patient within the preset time period.

[0031] In some possible implementations, the distribution consistency determination module is specifically configured to:

[0032] Chronic diseases whose ratio of the number of chronic diseases in the main incidence areas to the total number of corresponding chronic disease patients is greater than a preset threshold are determined as the main chronic diseases in the main incidence areas, and chronic diseases whose ratio of the number of chronic diseases in the target patient's area to the total number of corresponding chronic disease patients is greater than a preset threshold are determined as the main chronic diseases in the target patient's area;

[0033] The major chronic diseases in the main incidence areas constitute the first chronic disease set, and the major chronic diseases in the target patients' areas constitute the second chronic disease set;

[0034] The number of the third identical chronic disease in the first chronic disease set and the second chronic disease set is determined as the consistency of disease distribution between the target patient's region and the main disease-causing region.

[0035] In some possible implementations, the climate consistency determination module is specifically configured to:

[0036] Obtaining a first climate data series of multiple climate dimensions in the main disease-prone areas, and a second climate data series of multiple climate dimensions in the areas where the target patients are located;

[0037] Calculate the similarity between the first climate data sequence and the corresponding second climate data sequence to obtain the local consistency of each climate dimension;

[0038] The local consistency of each climate dimension was averaged to obtain the climate consistency between the target patient's area and the main disease area.

[0039] In some possible implementations, after modifying the first number of follow-up visits for the target patient within the preset time period using the comprehensive similarities to obtain the second number of follow-up visits for the target patient within the preset time period, the system further includes:

[0040] a risk factor determination module, configured to determine a disease risk factor for the target patient based on a third reference chronic disease of each family member corresponding to the target patient;

[0041] The follow-up number correction module is also used to use the target patient's disease risk factor to correct the target patient's second follow-up number within the preset time period to obtain the target patient's third follow-up number within the preset time period.

[0042] In some possible implementations, the risk factor determination module is specifically configured to:

[0043] Obtain the genetic similarity between each family member and the target patient, as well as the number of third hidden chronic diseases of each family member. The number of third hidden chronic diseases is the number of third reference chronic diseases that the target patient does not have.

[0044] The genetic similarities and the corresponding number of third latent chronic diseases are used to determine the disease risk factors of the target patients.

[0045] The present invention has the following beneficial effects:

[0046] In the Internet-based follow-up chronic disease management system provided by the present invention, the chronic disease information of the target patient and the first reference patient is first obtained, and the main incidence area of the target chronic disease is accurately located based on the chronic disease and the region to which the first reference patient belongs. Breaking the limitations of traditional single information and introducing the regional dimension, it is possible to capture the incidence patterns of chronic diseases in specific regions, making subsequent analysis more targeted. Then, focusing on the second reference patient in the main incidence area, the similarity of the number of illnesses and the symptom matching factor between the target patient and the second reference patient are calculated. Through multi-dimensional comparison, the disease association between the target patient and the second reference patient is deeply analyzed, accurately reflecting the degree of similarity between the target patient and the second reference patient in the main incidence area. Finally, the similarity of the number of illnesses, the symptom matching factor and the reference follow-up number of the second reference patient are comprehensively considered to accurately evaluate the follow-up number of the target patient. In this way, this comprehensive consideration method not only takes into account the individual characteristics of the patient, but also combines the actual follow-up experience of the same disease group in the main incidence area of the target chronic disease, so that the calculation result of the number of follow-up visits is highly consistent with the actual condition, which can effectively improve the accuracy of the follow-up number of the target patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 This is a schematic structural diagram of a first Internet-based follow-up chronic disease management system provided by one embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of a chronic disease analysis module provided by one embodiment of the present invention;

[0050] Figure 3 This is a schematic structural diagram of a second Internet-based follow-up chronic disease management system provided by one embodiment of the present invention;

[0051] Figure 4 This is a structural diagram of a third Internet-based follow-up chronic disease management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation method, structure, features and effects of the follow-up chronic disease management system based on Internet technology proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0053] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0054] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention comply with the relevant provisions of laws and regulations.

[0055] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary and their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0056] Chronic diseases, commonly referred to as "chronic diseases," are characterized by a long course and relatively slow progression. There are many types of chronic diseases, and different types differ in their pathological mechanisms, symptoms, and degree of harm. Even the same chronic disease can have very different progression trajectories in different patients. Some patients experience slow progression, with mild and stable symptoms; others experience fluctuating conditions, with a rapid deterioration. Given the significant individualization and diversity of chronic disease progression, long-term and continuous disease monitoring is essential for the scientific and effective management of chronic diseases. Disease monitoring can capture subtle changes in a patient's health status in real time, providing a basis for adjustments to subsequent treatment and management strategies. The key to accurate chronic disease management is to tailor a personalized follow-up plan based on the patient's current health status and the specific degree of disease progression, especially to determine the appropriate number of follow-up visits.

[0057] In actual clinical operations, the currently commonly used method is to first collect individual characteristic information such as the patient's age, gender, and medical history, and then use machine learning models to conduct in-depth analysis of these personalized data to predict the patient's health trends and calculate a theoretically reasonable number of follow-up visits for the patient.

[0058] However, this approach has significant shortcomings. It relies too heavily on individual patient characteristics, ignoring the common characteristics of the disease across different regions and living environments, as well as the potential correlations between patients with the same disease. This directly results in a significant deviation between the calculated number of follow-up visits and the patient's actual medical needs, resulting in poor accuracy.

[0059] The purpose of the present invention is to provide a follow-up chronic disease management system based on Internet technology. In the follow-up chronic disease management system based on Internet technology provided by the embodiment of the present invention, the chronic disease information of the target patient and the first reference patient is first obtained, and based on the chronic disease and the region to which the first reference patient belongs. Then, the second reference patient in the main disease area is focused on, and the similarity of the number of illnesses and the symptom matching factor between the target patient and the second reference patient are calculated. Finally, the similarity of the number of illnesses, the symptom matching factor and the reference follow-up number of the second reference patient are comprehensively considered to accurately evaluate the follow-up number of the target patient.

[0060] The following describes a specific embodiment of the Internet-based follow-up chronic disease management system provided by an embodiment of the present invention.

[0061] like Figure 1 , a schematic diagram of a follow-up chronic disease management system based on Internet technology is provided. The follow-up chronic disease management system 100 based on Internet technology includes a chronic disease acquisition module 110, a region determination module 120, a chronic disease analysis module 130, and a follow-up number determination module 140.

[0062] A chronic disease acquisition module 110 is configured to acquire a target chronic disease of a target patient and a first reference chronic disease of a first reference patient;

[0063] In the chronic disease acquisition module 110 , the target patient is a specific individual patient for whom the number of follow-up visits is to be determined, who needs to be paid special attention to and undergo follow-up planning; the target chronic disease is a chronic disease suffered by the target patient.

[0064] The first reference patients are a group of patients serving as reference samples, and the first reference chronic diseases are chronic diseases suffered by the first reference patients.

[0065] As an example, the chronic disease acquisition module 110 enters or queries the basic information of the target patient, including name, age, gender, etc., through the hospital's electronic medical record system, health management platform and other channels, and extracts their diagnosis records to determine the target chronic diseases suffered by the target patient, such as diabetes, hypertension, etc.

[0066] At the same time, a certain number of first reference patients are screened from sources such as the hospital's historical case database and the disease monitoring database of the public health system. The basic information and diagnostic records of these patients are also extracted to obtain the first reference chronic diseases they suffer from.

[0067] The region determination module 120 is configured to determine a major onset region of a target chronic disease based on the first reference chronic disease of each first reference patient and the region to which each first reference patient belongs;

[0068] In the region determination module 120 , the region is the geographical area information where the first reference patient is located, such as a province, city, district, or county, and is used to analyze the distribution of chronic diseases in different regions.

[0069] The main incidence areas are areas where the target chronic diseases are more concentrated and the incidence rates are relatively high, which are obtained by analyzing the first reference chronic diseases and the regions to which they belong of each first reference patient.

[0070] As an example, the region determination module 120 organizes the first reference chronic disease information and region information of the acquired first reference patient and creates a data table including fields such as patient number, first reference chronic disease name, and region.

[0071] Next, use data analysis tools to perform statistical analysis on the data. Count the number of first-reference patients with the target chronic disease in each region, sort them by region, and identify regions with the highest number of patients. These regions are designated as the primary outbreak areas for the target chronic disease. For example, if statistics show that City A in a province ranks first among all cities in that province in terms of the number of first-reference patients with the target chronic disease, City A can be identified as one of the primary outbreak areas.

[0072] A chronic disease analysis module 130 is configured to determine, based on the target chronic disease of the target patient and the second reference chronic disease of each second reference patient, a similarity in the number of diseases suffered by the target patient and a symptom matching factor, wherein the second reference patient is the first reference patient whose region is a major incidence region of the target chronic disease;

[0073] In the chronic disease analysis module 130, the second reference patients are a specific group selected from the first reference patients, and the region to which they belong is the main incidence area of the target chronic disease, which is used for more accurate comparative analysis with the target patients; the second reference chronic disease is the chronic disease suffered by the second reference patient.

[0074] The similarity in the number of diseases is used to measure the degree of similarity between the target patient and the second reference patient in the number of chronic diseases they suffer from. The symptom matching factor is an indicator obtained by comprehensively considering the similarities in symptom manifestations, severity, etc. of the chronic diseases suffered by the target patient and the second reference patient, and is used to reflect the degree of fit between the two in terms of symptom characteristics.

[0075] As an example, the chronic disease analysis module 130 selects patients whose regions are major incidence regions of the target chronic disease from the first reference patients as second reference patients.

[0076] Next, the number of chronic diseases suffered by the target patient and each second reference patient is counted. The absolute difference between the number of chronic diseases suffered by the target patient and each second reference patient is calculated. The similarity of the number of chronic diseases is then calculated using a formula, such as "Similarity of disease number = 1 - (Absolute value of difference / Larger number of disease numbers). Similarity values typically range from 0 to 1, with values closer to 1 indicating greater similarity in the number of disease numbers.

[0077] Next, a disease feature library is established, containing information such as common symptoms and severity levels for various chronic diseases. For the target patient and each second reference patient, the disease feature of each chronic disease is extracted. By comparing the disease features of the two, a disease matching factor is calculated. For example, a vector similarity algorithm (such as the cosine similarity algorithm) can be used to convert the disease features into vectors. The similarity between the two vectors is calculated as the disease matching factor, which also ranges from 0 to 1, with larger values indicating a higher degree of disease matching.

[0078] The follow-up number determination module 140 is used to determine the first follow-up number of the target patient within the preset time period based on the similarity of the number of diseases, the matching factors of the diseases, and the reference follow-up number of each second reference patient within the preset time period.

[0079] In the follow-up number determination module 140 , the reference follow-up number is the number of follow-up visits actually received by each second reference patient within a preset time period, and serves as a reference for determining the number of follow-up visits for the target patient.

[0080] The preset time period is a pre-set time range, such as one month, one quarter, one year, etc., which is used to determine the time span of the number of follow-up visits.

[0081] The first number of follow-up visits is the number of follow-up visits that the target patient should undergo within the preset time period, calculated by comprehensively analyzing factors such as the similarity of the number of patients, the symptom matching factor, and the reference number of follow-up visits.

[0082] As an example, the follow-up number determination module 140 collects the reference follow-up number of each second reference patient within a preset time period, and integrates it with the previously calculated similarity of the number of illnesses and the symptom matching factor to form a data set including fields such as the second reference patient number, similarity of the number of illnesses, symptom matching factor, and reference follow-up number.

[0083] Then, a machine learning algorithm (such as a linear regression model or a decision tree model) was used to construct a follow-up number prediction model. The model was trained using the similarity of the number of cases and the symptom matching factor as input features and the reference number of follow-up visits as the output label.

[0084] The similarity in the number of illnesses and the symptom matching factor between the target patient and each second reference patient are then input into the trained model to obtain the predicted number of follow-up visits for the target patient corresponding to each second reference patient. These predicted follow-up visits are then weighted averaged or otherwise processed (for example, by assigning different weights based on the similarity and matching factor) to ultimately determine the target patient's first follow-up visit number within the preset time period.

[0085] Furthermore, after determining the target patient's first follow-up visit frequency within a preset time period, a customized follow-up plan is generated based on the target patient's first follow-up visit frequency. Specifically, SMS, push notifications, emails, and other methods can be used to remind the target patient to attend a health checkup or participate in a remote video consultation on time. Reminders can also be automatically pushed based on the patient's follow-up frequency, such as monthly or quarterly follow-up appointments.

[0086] As an optional embodiment, Figure 2 As shown, the chronic disease analysis module 130 specifically includes the following units:

[0087] A quantity similarity determining unit 131 is configured to determine the similarity in the number of diseases of the target patient and the target second reference patient using the number of the first common chronic disease in the target chronic disease of the target patient and the target second reference patient, where the target second reference patient is any second reference patient;

[0088] a symptom similarity determination unit 132 for comparing each target chronic disease with each target second reference chronic disease, and obtaining symptom similarities between each target chronic disease and each target second reference chronic disease;

[0089] The matching factor determination unit 133 is configured to determine a disease matching factor between the target patient and the target second reference patient by using the similarities of the diseases.

[0090] In the quantity similarity determination unit 131, the first number of identical chronic diseases is the number of chronic diseases of the same type between the target chronic disease suffered by the target patient and the target second reference chronic disease suffered by the target second reference patient. For example, if the target patient suffers from diabetes, hypertension, and coronary heart disease, and the target second reference patient suffers from diabetes, hyperlipidemia, and coronary heart disease, then the first number of identical chronic diseases is 2 (diabetes and coronary heart disease).

[0091] Symptom similarity is an indicator that measures the degree of similarity in symptom characteristics between the target chronic disease and the target second reference chronic disease by comparing their symptoms, disease mechanisms, complications, etc.

[0092] The disease matching factor is a comprehensive indicator that integrates multiple disease similarity results and is used to comprehensively reflect the degree of fit between the target patient and the target second reference patient in terms of disease characteristics.

[0093] As an example, the quantitative similarity determination unit 131 extracts a list of target chronic diseases suffered by the target patient and a list of target second reference chronic diseases suffered by the target second reference patient from the target patient's electronic medical record and the target second reference patient's medical record, respectively. The two lists are collated to ensure that each chronic disease has a clear name and code (e.g., ICD code) to facilitate subsequent accurate comparison.

[0094] Next, write a program or use a data processing tool to traverse and compare the chronic condition lists of the target patient and the target second reference patient. For each chronic condition in the list, check whether the same chronic condition exists in the other list. Count the number of identical chronic conditions, which is the first number of identical chronic conditions.

[0095] Then, the similarity of the number of diseases between the target patient and the target second reference patient is determined by the following formula 1:

[0096] Formula 1

[0097] In formula 1, Used to characterize the similarity between the number of illnesses of the target patient h and the target second reference patient g, The number of the first common chronic diseases used to characterize the target patient h and the target second reference patient g, Used to characterize the total number of chronic diseases suffered by the target patient h.

[0098] Next, the symptom similarity determination unit 132 collects detailed symptom information for various chronic diseases, including common symptoms (such as fever, cough, and pain), symptom severity levels (such as mild, moderate, and severe), disease stages, and common complications. This information is organized into structured data and stored in a symptom feature library. Each chronic disease corresponds to a feature vector, and each element in the vector represents a symptom feature.

[0099] For each target chronic disease in the target patient and each target second reference chronic disease in the target second reference patient, extract the corresponding feature vectors from the disease feature library. Use a similarity calculation algorithm (such as the cosine similarity algorithm) to compare these two feature vectors. The cosine similarity algorithm measures the degree of similarity between two vectors by calculating the cosine value of the angle between them. The value ranges from -1 to 1. In disease similarity comparisons, the results are typically mapped between 0 and 1, with larger values indicating greater disease similarity.

[0100] Finally, the matching factor determination unit 133 determines the disease matching factor between the target patient and the target second reference patient using the following formula 2:

[0101] Formula 2

[0102] In formula 2, The disease matching factor used to characterize the target patient h and the target second reference patient g, Used to characterize the similarity of symptoms between the x-th target chronic disease and the y-th target second reference chronic disease. Used to represent the preset adjustment coefficient between the xth target chronic condition and the yth target second reference chronic condition. Specifically, when the xth target chronic condition is the same as the yth target second reference chronic condition, the preset adjustment coefficient is 1; when the xth target chronic condition is different from the yth target second reference chronic condition, the preset adjustment coefficient is 0. X is used to represent the total number of target chronic conditions, and Y is used to represent the total number of target second reference chronic conditions.

[0103] Among them, if the xth target chronic disease is the same as the yth target second reference chronic disease, the greater the reference degree of their symptom similarity; if the xth target chronic disease is different from the yth target second reference chronic disease, the smaller the reference degree of their symptom similarity. The greater the similarity of each symptom between the target patient h and the target second reference patient g, the greater the symptom matching factor of the target patient h and the target second reference patient g.

[0104] Chronic disease analysis module 130 comprehensively considers the similarity in disease status between the target patient and the target second reference patient, taking into account both the number of cases and the symptom matching factor. Follow-up strategies developed based on this scientific assessment can better meet the actual needs of patients and improve the effectiveness and quality of follow-up.

[0105] As an optional embodiment, the disease similarity determining unit 132 is specifically configured to:

[0106] Obtaining first symptom description information of a target chronic disease and second symptom description information of a target second reference chronic disease;

[0107] Performing word segmentation processing on the first symptom description information and the second symptom description information respectively to obtain a first word segmentation set and a second word segmentation set;

[0108] A similarity calculation is performed on the first segmentation set and the second segmentation set to obtain the symptom similarity between the target chronic disease and the target second reference chronic disease.

[0109] In the symptom similarity determination unit 132, the first symptom description information is a textual description of the target chronic disease, extracted from medical literature, electronic medical records, disease diagnostic standards, and other materials, including detailed features such as the symptoms, signs, course of disease, and complications of the chronic disease. For example, for diabetes, the first symptom description information may include "polydipsia, polyphagia, polyuria, weight loss, and long-term high blood sugar levels can lead to complications such as retinopathy and nephropathy."

[0110] The second symptom description is a detailed textual description of the symptoms of the target second reference chronic disease, obtained from various medical data. For example, if the target second reference chronic disease is hypertension, the second symptom description might be "Headache, dizziness, palpitations. Long-term poor blood pressure control can lead to damage to the heart, brain, kidneys, and other organs."

[0111] For example, when the target chronic disease and the target second reference chronic disease belong to the same chronic disease, the first symptom description information and the second symptom description information are the diagnosis results noted by the doctor in the case; when the target chronic disease and the target second reference chronic disease belong to different chronic diseases, the first symptom description information and the second symptom description information are text description information obtained from medical materials.

[0112] The first and second segmentation sets are sets of words obtained after segmenting the first and second symptom descriptions, respectively. Segmentation involves breaking down a continuous text into semantically or grammatically meaningful lexical units according to specific rules. For example, segmenting "polydipsia, polyphagia, polyuria, weight loss" yields a set consisting of the four words "polydipsia," "polyphagia," "polyuria," and "weight loss."

[0113] As an example, the symptom similarity determination unit 132 collects symptom description information for related chronic diseases from multiple sources. For the target chronic disease, this information can be obtained from authoritative medical textbooks, professional medical journals, clinical diagnosis and treatment guidelines, and patient medical records in electronic medical record systems. For the target second reference chronic disease, corresponding symptom description information is also obtained from these sources. For example, in the electronic medical record system, by searching for diagnostic keywords for the target chronic disease and the target second reference chronic disease, the symptom description section in the medical records of the relevant patients is extracted.

[0114] Then, sort out the first disease description information and the second disease description information collected, remove irrelevant text content, such as the patient's personal information, examination items, etc., and only retain the descriptive text directly related to the disease characteristics. At the same time, merge and de-duplicate the information from different sources to ensure that the obtained disease description information is accurate, complete and non-repetitive.

[0115] Next, input the first disease description information and the second disease description information into the selected word segmentation tool respectively. For example, use the Jieba word segmentation tool and call its word segmentation function in the Python environment to segment the text. During the word segmentation process, the tool will cut the continuous text into word units according to the built-in dictionary and algorithm rules. For some professional medical terms, the word segmentation tool may not be able to accurately identify them. At this time, common medical terms can be added to the dictionary by customizing the dictionary to improve the accuracy of word segmentation. After word segmentation is completed, store the word segmentation results in the form of a set to obtain the first word segmentation set and the second word segmentation set. When storing, preprocess the words, such as removing stop words (such as words like "of", "is", "and" that are not very meaningful for disease description), unifying case, removing special symbols, etc., to reduce interference in subsequent similarity calculations.

[0116] Finally, select a similarity calculation algorithm to calculate the similarity between the first word segmentation set and the second word segmentation set, so as to realize the calculation of the disease similarity between the target chronic disease and the target second reference chronic disease. Specifically, commonly used text similarity calculation algorithms include Jaccard similarity coefficient, cosine similarity, edit distance, etc.

[0117] Through the disease similarity determination unit 132, using word segmentation processing and similarity calculation algorithms, it is possible to accurately analyze the disease description information of the target chronic disease and the target second reference chronic disease at the text level. Compared with manual experience judgment, it reduces the interference of subjective factors and improves the accuracy and objectivity of disease similarity evaluation.

[0118] As an optional embodiment, the follow-up frequency determination module 140 is specifically used for:

[0119] Use the similarity of the number of patients with each disease and each disease matching factor to determine the disease matching degree between the target patient and each second reference patient respectively;

[0120] Use each disease matching degree and each reference follow-up frequency to determine the first follow-up frequency of the target patient within a preset time period.

[0121] In the follow-up frequency determination module 140, the disease matching degree is an index used to quantify the similarity degree of the overall disease condition between the target patient and each second reference patient after comprehensively considering the similarity of the number of patients with each disease and the disease matching factor. This index can more comprehensively reflect the similarity of their conditions.

[0122] As an example, the follow-up number determination module 140 may determine the condition matching degree between the target patient and each second reference patient using the following formula 3:

[0123] Formula 3

[0124] In formula 3, It is used to characterize the matching degree between the target patient h and the target second reference patient g. Used to characterize the similarity between the number of illnesses of the target patient h and the target second reference patient g, The disease matching factor used to characterize the target patient h and the target second reference patient g.

[0125] Then, the first follow-up number of each target chronic disease of the target patient within the preset time period is determined by the following formula 4:

[0126] Formula 4

[0127] In formula 4, It is used to represent the first follow-up number of the target chronic disease of the target patient h within the preset time period. Used to characterize the number of second reference patients in the main incidence area of the mth target chronic disease. It is used to represent the reference follow-up number of the g-th second reference patient within the preset time period, Used to characterize the matching degree between the target patient h and the gth second reference patient.

[0128] The greater the disease matching degree, the more suitable the corresponding reference follow-up number is for the target chronic disease corresponding to the target patient. In this case, if the reference follow-up number is greater, the first follow-up number of the target chronic disease corresponding to the target patient within the preset time period will be greater.

[0129] Finally, the first follow-up times of the target patient for various target chronic diseases within the preset time period are accumulated and rounded up to obtain the first follow-up times of the target patient within the preset time period.

[0130] Follow-up number determination module 140 comprehensively considers the similarity of the number of patients and the symptom matching factor to determine the disease matching degree, and then calculates the first follow-up number in combination with the reference follow-up number. This avoids the irrationality of formulating a follow-up plan based on only a single factor. It can more accurately formulate a follow-up plan that meets the needs of the target patient based on their actual disease characteristics, thereby improving the relevance and effectiveness of follow-up.

[0131] As an optional embodiment, the region determination module 120 is specifically configured to:

[0132] Based on the first reference chronic disease of each first reference patient and the region to which each first reference patient belongs, determining the number of second identical chronic diseases in each region, where the number of second identical chronic diseases is the number of first reference chronic diseases that are identical to the target chronic disease in the region;

[0133] The reference value for each region was determined using the number of the second common chronic disease in each region;

[0134] The areas with the greatest reference value will be identified as the main incidence areas of the target chronic diseases.

[0135] In the region determination module 120 , the second number of identical chronic diseases is the number of first reference chronic diseases of the same type as the target chronic disease in a specific region, reflecting the scale of the target chronic disease in the first reference patient group in the region.

[0136] The reference value is a quantitative evaluation indicator of the importance and usability of different regions in terms of the incidence and epidemic trends of the target chronic diseases, taking into account factors such as the number of the second same chronic diseases in each region.

[0137] As an example, the region determination module 120 categorizes the first reference patient data by region according to pre-defined regional classification criteria (e.g., administrative divisions). For example, the patient data may be categorized into different regional categories, such as Beijing, Shanghai, and Guangdong. For each region, the first reference chronic disease information for all first reference patients within that region is traversed, and the number of first reference chronic diseases that are identical to the target chronic disease is counted. For example, if the target chronic disease is diabetes, and there are 50 first reference patients in the Beijing region, 15 of whom suffer from diabetes as the first reference chronic disease, then the number of second reference chronic diseases that are identical to the target chronic disease in the Beijing region is 15.

[0138] Then, for each region, the number of the second identical chronic disease in the region is divided by the number of the first reference patients in the region to obtain the reference value of the region.

[0139] Finally, the calculated reference values for each region are ranked from highest to lowest to clearly define their order of reference value. The region with the highest reference value in the ranking is identified as the primary prevalence area for the target chronic disease. For example, if Beijing has the highest reference value among all regions, then Beijing is the primary prevalence area for the target chronic disease.

[0140] Through the region determination module 120, by comprehensively considering the number of first reference chronic diseases that are the same as the target chronic disease in the region, the main incidence area of the target chronic disease can be accurately determined, providing a clear direction for subsequent disease prevention and control and research.

[0141] As an optional embodiment, Figure 3 As shown, based on the similarity of the number of illnesses, the matching factors of the symptoms, and the reference follow-up times of the second reference patients within the preset time period, after determining the first follow-up times of the target patient within the preset time period, the follow-up chronic disease management system 100 based on Internet technology further includes the following modules:

[0142] A distribution consistency determination module 150 is configured to determine the consistency of disease distribution between the target patient's region and the major disease-incidence region based on the number of various chronic diseases in the major disease-incidence region of the target chronic disease and the number of various chronic diseases in the target patient's region;

[0143] A climate consistency determination module 160 is configured to determine the climate consistency between the target patient's location and the main disease-prone region based on the climate data of the main disease-prone region and the climate data of the target patient's location;

[0144] A comprehensive similarity determination module 170 is used to determine the comprehensive similarity between the target patient's location and the main disease-prone areas by using the consistency of symptom distribution and climate consistency;

[0145] The follow-up number correction module 180 is used to correct the first follow-up number of the target patient within the preset time period by using the comprehensive similarity to obtain the second follow-up number of the target patient within the preset time period.

[0146] In the follow-up frequency correction module 180, chronic diseases are often closely related to the patient's region. Factors such as the region's environment, lifestyle, medical resources, and economic level all influence the incidence of chronic diseases, management methods, and patient health status. For example, cities with severe air pollution may have higher incidences of respiratory and cardiovascular diseases, and thus may achieve better results in respiratory disease control and complication prevention. Therefore, by understanding the types of chronic diseases in each region, we can initially understand the overall characteristics and common patterns of such diseases in that region, providing a reference for determining personalized follow-up frequencies.

[0147] Symptom distribution consistency measures the similarity between the target patient's region and the target chronic disease's primary outbreak area in terms of the distribution of various chronic diseases. By comparing the incidence of different chronic diseases in the two regions, we can determine the degree of consistency in the types and numbers of chronic diseases.

[0148] Climate data covers a variety of climate-related information, such as temperature (average temperature, maximum temperature, minimum temperature), humidity, precipitation (annual precipitation, seasonal precipitation), air pressure, wind speed, sunshine duration, etc. These data can reflect the climate characteristics of a region.

[0149] Climate consistency refers to the degree of similarity between the climate data of the target patient's region and the main disease outbreak area, reflecting the proximity of the two regions in terms of climate environment.

[0150] Comprehensive similarity is a quantitative indicator obtained by comprehensively considering the consistency of symptom distribution and climate consistency. It is used to comprehensively evaluate the similarity between the target patient's region and the main disease incidence area in terms of chronic disease incidence environment and climatic conditions.

[0151] The second follow-up number is obtained by correcting the first follow-up number using the comprehensive similarity between the target patient's region and the main disease area. It is more in line with the impact of the target patient's environment on the disease condition and is more targeted and reasonable.

[0152] As an example, the distribution consistency determination module 150 collects data on the number of various chronic diseases in major disease outbreak areas and the target patient's region from channels such as medical statistics systems and medical record databases. The collected data is cleaned to remove outliers and duplicate data to ensure data accuracy and reliability. The number of chronic diseases is also standardized, specifically using range normalization. Methods such as cosine similarity or the Pearson correlation coefficient are then used to calculate the consistency of symptom distribution between the target patient's region and the major disease outbreak areas.

[0153] Next, climate consistency determination module 160 obtains climate data for the primary outbreak area and the target patient's region from sources such as meteorological departments and meteorological data websites, including data on temperature, humidity, and precipitation over different time periods. Feature extraction is performed on the acquired climate data, such as calculating statistical indicators such as annual average temperature, annual precipitation, and seasonal humidity variations to reflect the regional climate characteristics. Similarly, methods such as cosine similarity or Pearson correlation coefficient are used to calculate the climate consistency between the target patient's region and the primary outbreak area.

[0154] Next, comprehensive similarity determination module 170 assigns weights to symptom distribution consistency and climate consistency based on the degree of impact of symptom distribution and climate on the onset of chronic diseases. For example, if expert consultation or data analysis reveals that symptom distribution has a greater impact on the onset of chronic diseases, a higher weight, such as 0.7, may be assigned to symptom distribution consistency, while a weight of 0.3 may be assigned to climate consistency. The weights range from 0 to 1, and the sum of the two weights is 1. A weighted summation method is then used to calculate the comprehensive similarity between the target patient's region and the main onset areas.

[0155] Finally, the follow-up number correction module 180 determines the second follow-up number of the target patient within the preset time period using the following formula 5:

[0156] Formula 5

[0157] In formula 5, It is used to represent the second follow-up number of the target patient h within the preset time period. The number of target chronic diseases used to characterize the target patient h, Used to characterize the first follow-up number of the mth target chronic disease of the target patient h within the preset time period. It is used to characterize the comprehensive similarity between the target patient h’s corresponding target patient region and the main incidence region of the mth target chronic disease. The reference value used to characterize the main incidence area of the mth target chronic disease.

[0158] Among them, the greater the comprehensive similarity, the more similar the environment and main symptoms between the region where the target patient h is located and the main incidence area of the target chronic disease are, the more specific the medical data of the main incidence area of the target chronic disease is, and the greater the weight of the first follow-up number of the target chronic disease of the target patient needs to be given.

[0159] Through the comprehensive similarity determination module 170 and the follow-up frequency correction module 180, the follow-up frequency is adjusted after comprehensively considering the consistency of symptom distribution and climate consistency, so that the follow-up plan can more accurately tailor the impact of the target patient's environment on the condition. Chronic disease characteristics and climate differences in different regions may lead to different changes in the condition. By adjusting the follow-up frequency, changes in the condition can be detected in a timely manner and improve treatment effectiveness.

[0160] As an optional embodiment, the distribution consistency determination module 150 is specifically configured to:

[0161] Chronic diseases whose ratio of the number of chronic diseases in the main incidence areas to the total number of corresponding chronic disease patients is greater than a preset threshold are determined as the main chronic diseases in the main incidence areas, and chronic diseases whose ratio of the number of chronic diseases in the target patient's area to the total number of corresponding chronic disease patients is greater than a preset threshold are determined as the main chronic diseases in the target patient's area;

[0162] The major chronic diseases in the main incidence areas constitute the first chronic disease set, and the major chronic diseases in the target patients' areas constitute the second chronic disease set;

[0163] The number of the third identical chronic disease in the first chronic disease set and the second chronic disease set is determined as the consistency of disease distribution between the target patient's region and the main disease-causing region.

[0164] In the distribution consistency determination module 150 , the number of chronic diseases refers to the statistical result of the number of patients suffering from a specific chronic disease in a specific area (such as the main disease-prone area, the area where the target patients are located).

[0165] The total number of chronic disease patients is the sum of the number of all chronic disease patients in a specific area, that is, the value obtained by adding up the number of patients with various chronic diseases in the area.

[0166] Major chronic diseases refer to chronic diseases in a specific region where the ratio of the number of chronic diseases to the total number of chronic disease patients in the region is greater than the preset threshold, which means that the chronic disease has a higher incidence rate in the region and has an important impact on the local chronic disease prevalence.

[0167] The first chronic disease set is a set consisting of major chronic diseases identified in major disease-incidence areas, and the elements in the set are representative types of chronic diseases in the area.

[0168] The second chronic disease set is a set consisting of the main chronic diseases identified in the area where the target patient is located, reflecting the chronic disease incidence characteristics of the environment where the target patient is located.

[0169] The third number of identical chronic diseases is the number of chronic disease types that exist simultaneously in the first chronic disease set and the second chronic disease set, reflecting the degree of overlap in the types of chronic diseases between the target patient's region and the main disease-incidence area.

[0170] As an example, the distribution consistency determination module 150 collects chronic disease-related data from channels such as medical institutions' medical record systems and public health department statistical databases for the main incidence areas and the target patient's area, including the number of patients with each chronic disease and the total number of chronic disease patients in the area. For each chronic disease in the main incidence area and the target patient's area, the ratio of the number of chronic disease patients to the total number of chronic disease patients is calculated. For example, if there are 500 patients with hypertension in the main incidence area and the total number of chronic disease patients in the area is 2000, then the ratio of the number of patients with hypertension to the total number of chronic disease patients is 500 ÷ 2000 = 0.25. The calculated ratio is then compared with a preset threshold. Assuming the preset threshold is 0.2, if the ratio of a chronic disease is greater than 0.2, then the chronic disease is determined to be the main chronic disease in the corresponding area. For example, if the ratio of hypertension in the main incidence area is 0.25> 0.2, then hypertension is the main chronic disease in the main incidence area.

[0171] Next, all major chronic diseases identified in the primary incidence areas are collected and organized according to specific rules (such as sorting by ratio from high to low or categorizing by chronic disease type) to form the first chronic disease set. For example, if the major chronic diseases in the primary incidence area are hypertension, diabetes, and coronary heart disease, the first chronic disease set would be {hypertension, diabetes, coronary heart disease}. Similarly, the major chronic diseases identified in the target patient's area are collected and organized to form the second chronic disease set. For example, if the major chronic diseases in the target patient's area are diabetes, hyperlipidemia, and hypertension, the second chronic disease set would be {diabetes, hyperlipidemia, hypertension}.

[0172] Finally, compare the first and second chronic disease sets to identify chronic diseases that coexist in both sets. These chronic diseases are referred to as third common chronic diseases. In the above example, the third common chronic diseases between the first and second chronic disease sets are hypertension and diabetes. Count the number of third common chronic diseases, which represents the consistency of symptom distribution between the target patient's region and the main disease outbreak area. In this example, the number of third common chronic diseases is 2, indicating a certain degree of similarity in chronic disease incidence between the two regions.

[0173] Through the distribution consistency determination module 150, the number of the third identical chronic disease is used as a measurement indicator for the consistency of the symptom distribution, and the originally abstract similarity of the incidence types of chronic diseases between regions is quantified, making the evaluation results more objective and accurate, and providing a strong basis for further research on the epidemic patterns and influencing factors of chronic diseases between regions.

[0174] As an optional embodiment, the climate consistency determination module 160 is specifically configured to:

[0175] Obtaining a first climate data series of multiple climate dimensions in the main disease-prone areas, and a second climate data series of multiple climate dimensions in the areas where the target patients are located;

[0176] Calculate the similarity between the first climate data sequence and the corresponding second climate data sequence to obtain the local consistency of each climate dimension;

[0177] The local consistency of each climate dimension was averaged to obtain the climate consistency between the target patient's area and the main disease area.

[0178] In the climate consistency determination module 160, climate dimensions refer to multiple different aspects used to describe climate characteristics. Common climate dimensions include temperature (such as average temperature, maximum temperature, minimum temperature), humidity (such as relative humidity, absolute humidity), precipitation (such as annual precipitation, monthly precipitation, precipitation intensity), air pressure (such as average air pressure, air pressure variation range), wind speed (such as average wind speed, maximum wind speed, wind direction frequency), sunshine duration (such as annual sunshine duration, seasonal sunshine duration), etc. Each dimension reflects the climate conditions from a specific perspective.

[0179] The first climate data series is a chronological sequence of climate data collected across multiple climate dimensions for the main disease-affecting areas. For example, in the temperature dimension, the average daily temperature data for the region over the past year is recorded. These data, arranged in chronological order, constitute the first climate data series for the temperature dimension.

[0180] The second climate data series is a chronologically ordered collection of climate data across multiple climate dimensions in the target patient's region. Taking the temperature dimension as an example, the average daily temperature data for the target patient's region over the past year is recorded and arranged by date to form a series.

[0181] As an example, the climate consistency determination module 160 obtains climate data from channels such as meteorological departments, professional meteorological data websites, and meteorological monitoring stations. These channels typically provide detailed and accurate meteorological records, including various climate parameters at different time points. Based on the study's timeframe and accuracy requirements, data on multiple climate dimensions is selected for the primary outbreak area and the target patient's region. For example, if the study's timeframe is the past year, daily temperature, humidity, precipitation, and other data for the two regions over the past year are collected. The collected data is organized to ensure a uniform data format and a complete time series, removing outliers and missing values. Missing values can be filled using interpolation methods (such as linear interpolation or spline interpolation). The organized data is then arranged in chronological order to construct a first climate data series for the primary outbreak area and a second climate data series for the target patient's region. For example, for the temperature dimension, the daily average temperature data for the two regions over the past year are arranged in chronological order to form climate data series for the two temperature dimensions.

[0182] Then, based on the characteristics of the climate data and research needs, select an appropriate similarity calculation method. For example, the Dynamic Time Warping (DTW) method can be used. DTW calculates the similarity between two climate data series by finding the optimal alignment path. Its basic idea is to allow the series to be stretched and compressed to a certain extent on the time axis to find the optimal match. Specifically, the inverse of the DTW distance between the first and second climate data series can be used as the local consistency of the corresponding climate dimension.

[0183] Finally, the local consistencies of each climate dimension are averaged to obtain climate consistency.

[0184] By comprehensively considering multiple climate dimensions through the Climate Consistency Determination Module 160, a more comprehensive and accurate assessment of the climate similarity between the target patient's region and the primary outbreak area can be achieved. While a single climate dimension may not fully reflect the overall differences in the climate environments between two regions, a comprehensive analysis of multiple climate dimensions can address this deficiency and provide a more reliable climate basis for subsequent research.

[0185] As an optional embodiment, Figure 4 As shown, after the first follow-up number of the target patient within the preset time period is corrected by using the comprehensive similarities to obtain the second follow-up number of the target patient within the preset time period, the Internet-based follow-up chronic disease management system 100 further includes the following modules:

[0186] A risk factor determination module 190 is configured to determine a disease risk factor of the target patient based on a third reference chronic disease of each family member corresponding to the target patient;

[0187] The follow-up number correction module 180 is further configured to correct the second follow-up number of the target patient within the preset time period using the disease risk factor of the target patient to obtain a third follow-up number of the target patient within the preset time period.

[0188] In the follow-up frequency correction module 180, the third reference chronic disease refers to the type of chronic disease suffered by each family member of the target patient. The chronic disease status of family members may be associated with the target patient's disease risk through factors such as genetics, lifestyle, and family environment. Therefore, this chronic disease information can serve as an important reference for assessing the target patient's disease risk.

[0189] Disease risk factors are quantitative indicators or key factors that reflect the likelihood that a target patient will develop a specific chronic disease or diseases within a specific timeframe, calculated through analysis and calculation based on information such as third-party chronic diseases of the target patient's family members. These factors comprehensively consider the impact of multiple factors on the target patient, including family genetics and disease comorbidity.

[0190] The third follow-up number is calculated by adjusting the second follow-up number using the target patient's risk factors. This number better reflects the target patient's actual situation, taking into account factors such as family genetics that may affect disease progression and patient health, and thus providing a more reasonable and personalized follow-up plan.

[0191] As an example, risk factor determination module 190 collects chronic disease information for the target patient and their family members (e.g., parents, siblings, children, etc.) to identify the third reference chronic disease category for each family member. This data can be obtained through hospital medical record systems, health records, questionnaires, and other methods. Using medical statistical methods and epidemiological research principles, the module analyzes the correlation between chronic diseases in family members and chronic diseases that the target patient may have. For example, the module can study the transmission patterns of a certain hereditary chronic disease within a family to determine which chronic diseases have a higher risk of co-occurrence within the family. Furthermore, the module considers the interactions between different chronic diseases, such as the relationship between diabetes and cardiovascular disease.

[0192] Based on the results of the association analysis, a disease risk assessment model is constructed. This model can comprehensively consider multiple factors, such as the number of chronic diseases a family member has, the severity of the disease, and the degree of closeness to the target patient. For example, a higher risk weight is assigned to first-degree relatives (parents, children, siblings) with serious chronic diseases. The model calculates a factor value or risk level that quantifies the target patient's disease risk. The output of the risk assessment model is used as the target patient's disease risk factor. These factors can be specific values, such as a risk score (ranging from 0 to 100, with higher values indicating greater risk), or risk levels, such as low risk, medium risk, and high risk.

[0193] Then, the follow-up number correction module 180 determines the third follow-up number of the target patient within the preset time period by using the following formula 6:

[0194] Formula 6

[0195] In formula 6, It is used to represent the third follow-up number of the target patient h within the preset time period. It is used to represent the second follow-up number of the target patient h within the preset time period. Used to characterize the disease risk factors of the target patient h, is the ceiling function.

[0196] Through the risk factor determination module 190 and the follow-up frequency correction module 180, the chronic disease status of the target patient's family members is considered to determine the disease risk factor, and the follow-up frequency is adjusted accordingly, so that a follow-up plan more closely tailored to the target patient's individual health status can be developed. The number of follow-up visits will vary from patient to patient due to different family genetic backgrounds and disease risks, avoiding a "one-size-fits-all" follow-up model and improving the targeted and effective nature of medical services.

[0197] As an optional embodiment, the risk factor determination module 190 is specifically configured to:

[0198] Obtain the genetic similarity between each family member and the target patient, as well as the number of third hidden chronic diseases of each family member. The number of third hidden chronic diseases is the number of third reference chronic diseases that the target patient does not have.

[0199] The genetic similarities and the corresponding number of third latent chronic diseases are used to determine the disease risk factors of the target patients.

[0200] In the risk factor determination module 190, since some chronic diseases have a genetic predisposition, family history often increases the probability of the target patient suffering from multiple chronic diseases. For example, patients with a family history of hypertension, diabetes, heart disease, etc., will have a higher risk of their offspring developing these diseases. Moreover, the genetic susceptibility of certain chronic diseases may cross-act, leading to the coexistence of multiple diseases. Therefore, it is necessary to further consider whether the patient has any hidden diseases that have not yet been manifested. When the patient has a high probability of having a genetic hidden disease, the number of follow-up visits needs to be increased to ensure that the patient's physical condition is reflected in a timely manner.

[0201] Genetic similarity refers to the degree of similarity between each family member and the target patient at the level of genetic material (primarily DNA sequence). It reflects the closeness of genetic inheritance between family members. Because genes carry a wealth of information related to the occurrence and development of diseases, higher genetic similarity means the target patient is more likely to have inherited certain disease-related gene mutations from that family member, thereby affecting their risk of disease.

[0202] The number of third-hidden chronic conditions refers to the number of third-reference chronic conditions each family member has that are different from the target patient's chronic condition. By counting the number of family members with this chronic condition, we can understand the clustering of this condition within the family and assess the target patient's potential risk of developing the disease due to family history.

[0203] As an example, based on blood relationship, a genetic similarity (such as 0-1 points) is assigned to the target patient and each family member, for example, the genetic similarity between parents and children is 0.9 points, the genetic similarity between siblings is 0.8 points, the genetic similarity between grandparents and grandchildren is 0.6 points, the genetic similarity between uncles and aunts and nephews and nieces is 0.5 points, and the genetic similarity between cousins is 0.3 points.

[0204] Then, the collected chronic disease information of family members is compared with the target chronic disease of the target patient, and the number of family members suffering from a third reference chronic disease different from the target chronic disease, that is, the number of third hidden chronic diseases, is counted.

[0205] Finally, the disease risk factor of the target patient is determined by the following formula 7:

[0206] Formula 7

[0207] In formula 7, Used to characterize the disease risk factors of the target patient h, The number of family members used to characterize the target patient h, Used to characterize the number of third hidden chronic diseases of the jth family member of the target patient h, Used to characterize the genetic similarity of the jth family member of the target patient h. Used to represent the normalization function, which is used to normalize the value to the range of [0,1].

[0208] Among them, the greater the genetic similarity, the more likely the target patient h is to inherit a genetic susceptibility similar to that of the jth family member, further increasing the disease risk of the target patient h, that is, the greater the disease risk factor of the target patient h.

[0209] Risk factor determination module 190 comprehensively considers the genetic similarity between family members and the target patient, as well as the number of family members with conditions other than the target chronic disease, to more comprehensively capture the genetic and family history factors that may influence the target patient's disease. Compared to methods that only consider a single factor, this comprehensive assessment approach more accurately reflects the target patient's actual disease risk, providing a more reliable basis for early disease prevention and intervention.

[0210] It should be understood that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted. In the above embodiments, several specific steps are described and illustrated as examples. However, the method of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art may make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present invention.

[0211] It should also be noted that the exemplary embodiments described herein describe methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the steps described above. In other words, the steps may be performed in the order described in the embodiments, or in a different order, or several steps may be performed simultaneously.

[0212] The above description is only a specific embodiment of the present invention. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention.

Claims

1. A follow-up chronic disease management system based on Internet technology, characterized in that: include: A chronic disease acquisition module, used to acquire a target chronic disease of a target patient and a first reference chronic disease of a first reference patient; a region determination module, which determines the number of second identical chronic diseases in each region based on the first reference chronic disease of each first reference patient and the region to which each first reference patient belongs, wherein the number of second identical chronic diseases is the number of first reference chronic diseases in the region that are identical to the target chronic disease, and uses the number of second identical chronic diseases in each region to determine the reference value of each region, and determines the region with the largest reference value as the main incidence region of the target chronic disease; a chronic disease analysis module for determining, based on the target chronic disease of the target patient and the second reference chronic disease of each second reference patient, a similarity in the number of diseases suffered by the target patient and a symptom matching factor, wherein the second reference patient is the first reference patient whose region is a major incidence region of the target chronic disease; A follow-up number determination module is used to determine the first follow-up number of the target patient within a preset time period based on the similarity of the number of diseases, the matching factor of each disease, and the reference follow-up number of each second reference patient within a preset time period; a distribution consistency determination module, configured to determine a chronic disease for which the ratio of the number of chronic diseases in a major incidence area to the total number of corresponding chronic disease patients is greater than a preset threshold as the major chronic disease in the major incidence area, and to determine a chronic disease for which the ratio of the number of chronic diseases in the target patient's area to the total number of corresponding chronic disease patients is greater than a preset threshold as the major chronic disease in the target patient's area, to form a first chronic disease set from each major chronic disease in the major incidence area, and to form a second chronic disease set from each major chronic disease in the target patient's area, and to determine the number of the third identical chronic disease in the first chronic disease set and the second chronic disease set as the symptom distribution consistency between the target patient's area and the major incidence area; A climate consistency determination module is used to obtain a first climate data sequence of multiple climate dimensions in the main disease-prone area and a second climate data sequence of multiple climate dimensions in the target patient's area, perform similarity calculations on the first climate data sequence and the corresponding second climate data sequence to obtain local consistency in each climate dimension, perform mean processing on the local consistency in each climate dimension, and obtain the climate consistency between the target patient's area and the main disease-prone area; A comprehensive similarity determination module is used to determine the comprehensive similarity between the target patient's location and the main disease-prone area by using the consistency of symptom distribution and climate consistency; The follow-up number correction module is used to use the comprehensive similarity to correct the first follow-up number of the target patient within the preset time period to obtain the second follow-up number of the target patient within the preset time period.

2. The Internet-based chronic disease management system according to claim 1 is characterized in that: Chronic disease analysis module, including: A quantity similarity determination unit is configured to determine the similarity in the number of diseases of the target patient and the target second reference patient using the number of the first identical chronic disease in the target chronic disease of the target patient and the target second reference patient, where the target second reference patient is any second reference patient; a symptom similarity determination unit, configured to compare each target chronic disease with each target second reference chronic disease, respectively, to obtain symptom similarities between each target chronic disease and each target second reference chronic disease; The matching factor determination unit is used to determine the disease matching factor between the target patient and the target second reference patient by using the similarities of each disease.

3. The Internet-based follow-up chronic disease management system according to claim 2 is characterized in that: The disease similarity determination unit is used to: Obtaining first symptom description information of a target chronic disease and second symptom description information of a target second reference chronic disease; Performing word segmentation processing on the first symptom description information and the second symptom description information respectively to obtain a first word segmentation set and a second word segmentation set; A similarity calculation is performed on the first segmentation set and the second segmentation set to obtain the symptom similarity between the target chronic disease and the target second reference chronic disease.

4. The Internet-based follow-up chronic disease management system according to claim 1 is characterized in that: Follow-up number determination module, used for: Using the similarity of the number of illnesses and the matching factor of each symptom, the matching degree of the target patient's condition with each second reference patient is determined respectively; The first follow-up number of the target patient within the preset time period is determined by using the matching degree of each disease condition and the reference follow-up number.

5. The Internet-based follow-up chronic disease management system according to claim 1 is characterized in that: After modifying the first number of follow-up visits of the target patient within the preset time period by using the comprehensive similarities to obtain the second number of follow-up visits of the target patient within the preset time period, the system further includes: a risk factor determination module, configured to determine a disease risk factor for the target patient based on a third reference chronic disease of each family member corresponding to the target patient; The follow-up number correction module is also used to use the target patient's disease risk factor to correct the target patient's second follow-up number within the preset time period to obtain the target patient's third follow-up number within the preset time period.

6. The Internet-based follow-up chronic disease management system according to claim 5 is characterized in that: Risk factor determination module, used to: Obtain the genetic similarity between each family member and the target patient, as well as the number of third latent chronic diseases of each family member, where the number of third latent chronic diseases is the number of third reference chronic diseases that the target patient does not have; The genetic similarities and the corresponding number of third latent chronic diseases are used to determine the disease risk factors of the target patients.

Images