Intelligent family doctor recommendation method and system and storage medium

Abstract

The invention belongs to the technical field of medical big data systems, and particularly relates to an intelligent family doctor recommendation method and system and a storage medium. According to the method, the matching degree of a doctor and a patient is represented based on a dynamic comprehensive score, and specific indexes included in the dynamic comprehensive score include the ability matching degree, the space-time matching degree and the economic matching degree. According to the method, the matching degree of the patient and the doctor can be dynamically evaluated, existing medical big data resources can be fully applied, objective and accurate judgment can be made, the patient is assisted to efficiently find the most adaptive family doctor, and the method has a good application prospect.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical big data systems, and particularly relates to an intelligent family doctor recommendation method, system and storage medium. BACKGROUND

[0002] In the traditional medical service mode, a patient needs to go through the following links: registration, waiting, treatment, examination, waiting for results, payment, treatment, taking medicine, discharge, and re-treatment. The non-medical time consumption is much longer than the treatment time. With the development of medical industry technology and Internet technology, introducing a data-based and information-based platform system into the medical and health industry helps to improve the medical technology level, share digital medical resources and medical information, and thus solve the above problems.

[0003] The family doctor service system can realize hierarchical diagnosis and treatment, and plays a significant role in reducing medical costs, optimizing the use of health resources, and improving the health status of the public. The family doctor is a team composed of general practitioners, team secretaries, specialist doctors, public health doctors and other members, which usually provides services to contracted patients in the form of a team.

[0004] The family doctor provides comprehensive, continuous, effective, timely and personalized medical and health care services to the service object, has comprehensive and systematic prevention, health care, medical treatment and rehabilitation knowledge, has strong language expression ability, interpersonal communication ability and work coordination ability, and can provide timely and effective health services throughout the life cycle. The family doctor provides personalized prevention, health care, treatment, rehabilitation, health education services and guidance, so that the general public can solve daily health problems and health care needs, receive family treatment and family rehabilitation nursing services without leaving home.

[0005] In the prior art, there is still a lack of a perfect family doctor recommendation and management system using medical big data, which specifically shows that: the artificial intelligence auxiliary role is not considered, the dynamic correlation between the family doctor big data information and the overall medical big data information is poor, which is not conducive to the development of family doctor services; the existing family doctor related system is still a standardized service, and the best medical resources are not matched for each patient individual, so the problem that patients cannot match the appropriate family doctor may occur. Therefore, developing a new intelligent family doctor recommendation system to realize personalized family doctor matching for patient individuals is a problem to be solved in the field. SUMMARY

[0006] In view of the problems in the prior art, the application provides an intelligent family doctor recommendation method, system and storage medium.

[0007] An intelligent family doctor recommendation method, which represents the matching degree of doctors and patients based on a dynamic comprehensive score, and the calculation formula of the dynamic comprehensive score is: wherein the is a weight, is a specific index, is specifically selected from the following three items: ability matching degree , space-time matching degree and economic matching degree .

[0008] Preferably, the calculation formula of the ability matching degree is: wherein, is the historical score of the doctor, is the order saturation, is the disease correlation degree calculated based on the medical knowledge graph; the calculation method of the is: wherein, represents the set of chronic diseases suffered by the patient, represents a specific disease belonging to ; represents the specialist field that the doctor is good at, represents a specific disease belonging to ; is the diagnosis and treatment path associated with the disease in the medical knowledge graph, represents the longest path length from the current disease node to the associated node in the medical knowledge graph.

[0009] Preferably, the type of specific disease is represented based on ICD-10 coding.

[0010] Preferably, the calculation formula of the space-time matching degree is: wherein, is the latitude and longitude of the patient's residence, is the latitude and longitude of the doctor's residence; is the Haversine distance calculated according to the latitude and longitude of the doctor's and patient's residence, with the unit of km; is the distance attenuation factor, is the expected response time; is the average response time, with the unit of h; is the maximum response time of the doctor allowed by the system.

[0011] Preferably, the calculation formula of the economic matching degree is: wherein, a patient budget, a doctor's out-of-office price, a patient compliance score.

[0012] Preferably, the weight is dynamically adjusted, and the dynamic adjustment manner is: if , the importance of the specific indicators is ranked from high to low as: the ability matching degree, the space-time matching degree, and the economic matching degree; if = 3, the importance of the specific indicators is ranked as: the ability matching degree is higher than the economic matching degree and the space-time matching degree; if , the importance of the specific indicators is ranked from high to low as: the economic matching degree, the ability matching degree, and the space-time matching degree; wherein, an emergency degree.

[0013] Preferably, the weight is dynamically adjusted, and the dynamic adjustment manner is: if , the weights of the economic matching degree, the ability matching degree, and the space-time matching degree are: ; if = 3, the weights of the economic matching degree, the ability matching degree, and the space-time matching degree are: W = [0.3, 0.4, 0.3]; if , the weights of the economic matching degree, the ability matching degree, and the space-time matching degree are: .

[0014] Preferably, the doctor list is ranked in descending order according to , and the doctor ranked first is recommended to the patient; if multiple doctors have the same score and are ranked first, all of them are recommended to the patient for selection.

[0015] The application further provides an intelligent family doctor recommendation method system, which integrates a module for implementing the above intelligent family doctor recommendation method, and comprises: a data acquisition module configured to acquire data of patients and doctors and access medical knowledge graph data; a dynamic comprehensive score calculation module configured to calculate a dynamic comprehensive score; a recommendation module configured to recommend doctors to patients based on the dynamic comprehensive score.

[0016] The application further provides a computer readable storage medium having stored thereon a computer program for implementing the above intelligent family doctor recommendation method.

[0017] The present application aims at the family doctor recommendation problem, and constructs a system for evaluating the matching degree of patients and doctors, including the capability matching degree, the space-time matching degree and the economic matching degree, and adjusts the indexes that are emphasized in different cases by dynamically adjusting the weights. The evaluation and recommendation system of the present application can fully apply the existing medical big data resources, objectively and accurately judge the matching degree of doctors and patients, so as to assist patients to efficiently find the most suitable family doctor for themselves. The method and system of the present application can be integrated into various medical related management systems, application software and mobile phone APPs, and have good application prospects.

[0018] Obviously, according to the above content of the present application, according to the ordinary technical knowledge and conventional means in the art, other various forms of modifications, substitutions or changes can be made without departing from the above basic technical idea of the present application.

[0019] The above content of the present application will be further described in detail through the specific embodiments in the form of examples. However, this should not be understood as limiting the scope of the above subject matter of the present application to the following examples. Any technology realized based on the above content of the present application belongs to the scope of the present application. DETAILED DESCRIPTION

[0020] It should be particularly noted that the algorithms of the data collection, transmission, storage and processing steps not specifically described in the examples, and the hardware structure, circuit connection and the like not specifically described can be realized through the existing technology.

[0021] Example 1: Intelligent family doctor recommendation method system and method The system and method of the present embodiment are used for recommending the most suitable family doctor for patients, and the system composition includes: A data collection module configured to collect data of patients and doctors, and access medical knowledge graph data; A dynamic comprehensive score calculation module configured to calculate a dynamic comprehensive score; A recommendation module configured to recommend doctors to patients based on the dynamic comprehensive score.

[0022] The method for recommending family doctors by applying the system specifically includes the following steps: Step 1: Data input and preprocessing 1. Patient quantitative index input: input patient basic information, including budget (unit: yuan), chronic disease set (based on ICD-10 coded disease set, such as E11.9=type 2 diabetes), emergency degree (1-5 scale, 1 = routine consultation, 5 = critical illness, automatically determined according to symptom keywords), compliance score , patient's residence longitude and latitude .

[0023] Among them, the value of Ep can refer to the "Emergency Pre-examination and Diagnosis Standard" (2018), and the value is 1-5. The specific standard is: 5: Key word matching "chest pain", "dyspnea", "loss of consciousness", "severe bleeding", "severe burns", "convulsions", "stroke symptoms", "cardiac arrest"; 4: Key word matching "high fever", "severe abdominal pain", "persistent vomiting", "severe headache", "fracture", "dyspnea but not severe", "anaphylaxis"; 3: Key word matching "fever", "cough", "diarrhea", "mild pain", "rash", "dizziness", "nausea"; 2: Key word matching "follow-up visit for chronic disease", "routine examination", "prescription", "health consultation", "vaccination"; 1: Key word matching "physical examination report interpretation", "health management consultation", "lifestyle guidance", "psychological support".

[0024] Patient compliance is derived from medication compliance, examination completion rate, and follow-up completion rate. Medication compliance is scored by weighted average of examination completion rate (the number of times patients complete examinations on time after completing the visit / total number of times) and follow-up completion rate (the number of times patients complete follow-up visits on time after completing the visit / total number of times). When calculating patient compliance, the weights used can be adaptively set according to the effect of matching the calculation results with the system.

[0025] 2. Doctor quantitative index input: read doctor information in the doctor library, including consultation price (unit: yuan / time), specialty field (ICD-10 mapped disease expertise set, such as I10 = hypertension), doctor historical score (patient evaluation average, 0-5 points), order saturation (current workload proportion, 0%-100%, 100% = full load), average response time (unit: hours), doctor's residence longitude and latitude .

[0026] Among them, the order saturation calculation method is: Order saturation = Actual number of consultations / Theoretical maximum number of consultations; Actual number of consultations = single The average consultation time per case (e.g., 30 minutes) and the theoretical maximum number of cases are based on the doctor's working hours (e.g., 8 hours per day).

[0027] Step 2: Deep matching based on medical knowledge graph 1. Calculate the disease association degree Collect patients' chronic diseases With medical specialty fields Mapping to a medical knowledge graph (which uses existing medical knowledge graphs such as Clinical Knowledge Graph, Hetionet, and Bio2RDF, and can be built based on ICD-10 and clinical pathway libraries, containing relationships between diseases and treatment pathways), calculate the disease association degree: in, To link diseases in a medical knowledge graph Related treatment pathways typically include common complications, related diseases requiring co-treatment, relevant examinations, medications, and treatment plans (i.e., related to...). A set of directly related diseases. Indicates from the current disease node The longest path length to the associated node (such as complications or treatment methods). The greater the depth, the weaker the association.

[0028] For example, when a diabetic patient (E11.9) is matched with an endocrinologist, the numerator is the number of intersections between the patient's disease and the doctor's specialty path (e.g., diabetes + complications); the denominator is the total number of the patient's diseases × path depth (the deeper the depth, the weaker the association, because a deeper depth indicates that the doctor may have less direct association with the disease and more indirect association).

[0029] For example: Patient disease collection: = {E11.9 (Type 2 Diabetes), I10 (Primary Hypertension)}; Collection of doctors' specialties: = {E11.9 (Type 2 Diabetes), I25.1 (Coronary Artery Disease)}; The path to obtaining doctors' expertise from the constructed medical knowledge graph is as follows: Path(E11.9) = { "Core Treatments": ["Glucose Monitoring", "Insulin Therapy", "Oral Hypoglycemic Agents"], #Depth=1.0 "Direct Complications": ["Diabetic Nephropathy", "Retinopathy", "Neuropathy"], #Depth=1.2 "Metabolic Association": ["Hypertension Management", "Dyslipidemia Management"], #Depth=1.5 "Long-term Management": ["Foot Care", "Nutritional Guidance", "Sports Rehabilitation"]#Depth=1.3} Path(I25.1) = { "Core Treatment": ["Antibacterial Therapy", "Beta-Blockers", "Revascularization"], # Depth=1.0 "Risk Factors": ["Hypertension Management", "Diabetes Management", "Lipid Management"], # Depth=1.4 "Complications": ["Heart Failure", "Arrhythmia", "Prevention of Sudden Cardiac Death"], # Depth=1.6 "Rehabilitation Management": ["Cardiac Rehabilitation", "Lifestyle Intervention"]# Depth=1.3} The depth and weight of each level are quantitatively assessed based on the direct relevance of clinical pathways when constructing the knowledge graph. For example, if Path_Depth_E11.9 = (1.0... 3 + 1.2 3 + 1.5 2 + 1.3 3) / 11 = 1.27, and using the same calculation method, Path_Depth_I25.1 = 1.36, so the doctor's average Path_Depth = 1.315.

[0030] According to the formula For doctors specializing in E11.9 (diabetes): ∩ Path(E11.9) = {E11.9, I10} ∩{E11.9, diabetic nephropathy, retinopathy, neuropathy, hypertension management, dyslipidemia management, ...}, matching diseases: E11.9 (direct match), I10 (associated through "hypertension management"), with an intersection of 2.

[0031] For doctors specializing in I25.1 (coronary artery disease): ∩ Path(I25.1) = {E11.9, I10} ∩{I25.1, Hypertension Management, Diabetes Management, Lipid Management, Heart Failure, ...}, matching diseases: I10 (associated through "Hypertension Management"), E11.9 (associated through "Diabetes Management"), with an intersection of 2.

[0032] The intersection after merging is |{E11.9, I10}| = 2.

[0033] denominator = 2, Path_Depth = 1.315, = 0.76.

[0034] 2. Dynamic weight adaptive mechanism like The importance of the specific indicators, ranked from highest to lowest, is as follows: capability matching degree, spatiotemporal matching degree, and economic matching degree. like =3, then the importance ranking of the specific indicators is that the ability matching degree is higher than the economic matching degree and the time-space matching degree; like The importance of the specific indicators, ranked from highest to lowest, is as follows: economic matching degree, capability matching degree, and spatiotemporal matching degree. For example, in one embodiment, based on the patient's urgency level Automatically adjust matching dimension weights: like The weights of economic matching, capability matching, and spatiotemporal matching are as follows: ; like =3, and the weights of economic matching degree, capability matching degree and spatiotemporal matching degree are W=[0.3,0.4,0.3] respectively; like The weights of economic matching, capability matching, and spatiotemporal matching are as follows: .

[0035] Step 3: Multimodal matching degree calculation 1. Ability matching degree in, Rate the doctor's history, for example, a score of 4.8. (1+4.8)≈1.76, To determine the saturation level for order fulfillment, if the saturation level is 80%, then (1 / 1 + 0.8) ≈ 0.55.

[0036] 2. Spatiotemporal matching degree in, Calculate the Haversine distance (km) based on the latitude and longitude of the doctor's and patient's addresses. This is the distance attenuation factor (default is 0.02). This represents the expected response time. The average response time is expressed in hours (h). This represents the maximum allowable doctor response time, i.e., the maximum tolerable time difference. For non-emergency services, maxRT can be set to 2 hours; for emergency services, maxRT can be set to half an hour. For example: Ep=1, maxRT=2; Ep=2, maxRT=1.5; Ep=1, maxRT=1.0; Ep=1, maxRT=0.7; Ep=1, maxRT=0.5.

[0037] 3. Economic matching degree Among them, when the patient's budget Doctor's unit price is greater than or equal to When the budget is insufficient, the match score is 1. When the budget is insufficient, the match score is reduced proportionally and multiplied by a coefficient (0.5 + 0.5 × patient compliance score). This means that patients with high compliance can achieve a high degree of economic matching even if their budget is limited.

[0038] Step 4: Dynamic Comprehensive Scoring and Recommendation .

[0039] Step 5: Explainable Recommendation Output 1. According to Sort the list of doctors in descending order and recommend the top-ranked doctor to the patient.

[0040] 2. If there are multiple doctors If all doctors rank first, multiple doctors will be recommended for the patient to choose from.

[0041] As can be seen from the above embodiments, the present invention can dynamically assess the matching degree between patients and doctors, make full use of existing medical big data resources, make objective and accurate judgments, thereby helping patients efficiently find the most suitable family doctor, and has a very good application prospect.

Claims

1. An intelligent family doctor recommendation method, characterized in that: The dynamic comprehensive score represents the degree of matching between doctors and patients. The formula for calculating the dynamic comprehensive score is as follows: Among them, the As weight, For specific indicators, Specifically selected from the following three items: Capability Matching Degree Spatiotemporal matching degree Economic matching degree .

2. The intelligent family doctor recommendation method according to claim 1, characterized in that: The formula for calculating the capability matching degree is: in, Rate doctors' history To achieve order saturation, The degree of disease association is calculated based on a medical knowledge graph; The The calculation method is as follows: in, This indicates the collection of chronic diseases suffered by the patient. Indicates belonging to A specific disease in the context; This indicates the doctor's area of ​​expertise. Indicates belonging to A specific disease in the context; To associate diseases in medical knowledge graphs Related treatment pathways This indicates starting from the current disease node in the medical knowledge graph. The longest path length to the associated node.

3. The intelligent family doctor recommendation method according to claim 1, characterized in that: The specific disease types are represented based on ICD-10 codes.

4. The intelligent family doctor recommendation method according to claim 1, characterized in that: The formula for calculating the spatiotemporal matching degree is: in, The patient's place of residence (latitude and longitude) The latitude and longitude of the doctor's residence; The Haversine distance is calculated based on the latitude and longitude of the doctor's and patient's residences, in km. For distance attenuation factor, Expected response time; The average response time is expressed in hours (h). This represents the maximum response time allowed by the system for doctors.

5. The intelligent family doctor recommendation method according to claim 1, characterized in that: The formula for calculating the economic matching degree is: in, Budgeting for patients, Doctor's house call fees Assess patient compliance.

6. The intelligent family doctor recommendation method according to claim 1, characterized in that: The weights are dynamically adjusted, and the dynamic adjustment method is as follows: like The importance of the specific indicators, ranked from highest to lowest, is as follows: capability matching degree, spatiotemporal matching degree, and economic matching degree. like =3, then the importance ranking of the specific indicators is that the ability matching degree is higher than the economic matching degree and the time-space matching degree; like The importance of the specific indicators, ranked from highest to lowest, is as follows: economic matching degree, capability matching degree, and spatiotemporal matching degree. in, The level of urgency.

7. The intelligent family doctor recommendation method according to claim 6, characterized in that: The method for dynamically adjusting the weights is as follows: like The weights of economic matching, capability matching, and spatiotemporal matching are as follows: ; like =3, and the weights of economic matching degree, capability matching degree and spatiotemporal matching degree are W=[0.3,0.4,0.3] respectively; like The weights of economic matching, capability matching, and spatiotemporal matching are as follows: .

8. The intelligent family doctor recommendation method according to claim 1, characterized in that: according to Sort the list of doctors in descending order and recommend the top-ranked doctor to the patient; if there are multiple doctors... If all of them rank first, then all of them are recommended for the patient to choose from.

9. An intelligent family doctor recommendation system, characterized in that, The system integrates a module for implementing the intelligent family doctor recommendation method according to any one of claims 1-8, comprising: The data acquisition module is configured to collect data from patients and doctors and integrate it with medical knowledge graph data. The dynamic comprehensive score calculation module is configured to calculate the dynamic comprehensive score. The recommendation module is configured to recommend doctors to patients based on the dynamic comprehensive score.

10. A computer-readable storage medium, characterized in that, It stores a computer program for implementing the intelligent family doctor recommendation method according to any one of claims 1-8.

Images