Extended diagnosis and treatment service system for Parkinson's disease patient

Abstract

The invention provides an extended diagnosis and treatment service system for a Parkinson's disease patient, which comprises a patient mobile terminal, a medical care mobile terminal and an application server, and is characterized in that the patient mobile terminal and the medical care mobile terminal are both connected with the application server; a patient and medical care binding unit, a patient scale filling unit and a doctor-patient interaction unit are arranged in the patient mobile terminal, the patient and medical care binding unit, the doctor-patient interaction unit, a doctor scale filling unit and an illness state description unit are arranged in the medical care mobile terminal, and the doctor-patient interaction unit of the medical care mobile terminal is connected with the illness state description unit. The illness state description unit is connected with the doctor filling scale unit; the patient and medical care binding unit, the patient scale filling unit, the doctor-patient interaction unit, the illness state description unit and the doctor scale filling unit are all connected with the application server. According to the method, the treatment effect is evaluated through weight iteration, the treatment scheme is corrected in time, and decision support is provided for optimizing the next treatment scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of Parkinson's disease tracking treatment records, and in particular to an extended diagnosis and treatment service system for Parkinson's disease patients, which completes the follow-up service for Parkinson's disease patients in a data-driven manner by establishing a data treatment scenario. Background Art

[0002] Parkinson's disease is a chronic disease, and the treatment process is long and changeable. my country has not yet established a complete Parkinson's disease tracking and treatment system. The treatment process mainly relies on manual investigation, summary, and reporting. The procedures are complicated, the workload is huge, the data is prone to errors, and it cannot be stored and processed uniformly, resulting in poor data quality and low utilization. At present, the use of new-generation information technology means through mobile WeChat applets or APPs and other clients facilitates patients to obtain disease information in a timely manner or communicate conveniently, but there are deficiencies in personalized patient disease monitoring. It only collects disease data without accurate evaluation and feedback, and cannot provide intelligent disease decision support.

[0003] The hospital's electronic medical records are general information, with a complex document organization structure, cross-system data integration, complicated query operations, and frequent jump interfaces. This is not conducive to doctors' rapid retrieval of specific Parkinson's disease patients' electronic medical record information and is not suitable for specialized treatment of specialized diseases.

[0004] The health records carried by the Health Pass APP can be viewed in real time, and the medical records are fully uploaded to the cloud server. Patients can query their own imaging data through indexes, including: medical records, test and examination data, and imaging data, which can be called at any time, carried with you, used at any time, and convenient for patients to use and query. Disadvantages: ① There is only a patient client, but no doctor client, and it cannot provide one-on-one in-depth tracking treatment and diagnosis between doctors and patients; ② It can only record the patient's health records, and cannot provide timely feedback and evaluation of the treatment effect to the patient client, and cannot correct the treatment plan in time, nor can it provide decision support for the next treatment plan. And it cannot provide extended diagnosis for the treatment of Parkinson's disease.

[0005] WeChat public accounts are suitable for popularizing medical knowledge, and are convenient for patients to make appointments with experts, register for outpatient clinics, and seek medical advice. Disadvantages: ① The content of public accounts is diverse, forming a service platform for miscellaneous discussions, which makes it difficult to provide a one-to-one doctor-patient treatment service model and lacks the coordination of online and offline communication; ② No personalized health records are built, which cannot support the historical record tracing of chronic diseases (such as Parkinson's disease) and it is difficult to deeply track patients to provide long-term treatment services and medication guidance.

[0006] The "Application Demonstration of Personalized Active Health Comprehensive Intervention Model" project undertaken by the Chronic Disease Center of the Chinese Center for Disease Control and Prevention aims to build a set of personalized active health comprehensive intervention technology systems covering the entire life cycle of children and adolescents, young and middle-aged professional groups, and the elderly (including patients with chronic diseases), including health education, information collection and personalized assessment, compliance assessment and other health intervention dimensions, covering nutrition, exercise, diet, behavior, sleep and other aspects. Insufficient points: ① The focus of the project is to establish a comprehensive personalized active health comprehensive intervention model, lack of in-depth participation of doctors, and reduce the urgency of chronic disease patients; ② Lack of timely feedback on the treatment effect of chronic disease patients and correction methods and means.

[0007] The National Key R&D Program "Construction of a Big Data Platform for Epidemiological Monitoring of Major Chronic Diseases and Research on Key Technologies" project builds a big data interconnection system for chronic diseases at the provincial, municipal and county levels to promote the in-depth use of chronic disease monitoring data. Insufficient points: ① The constructed big data platform for epidemiological monitoring of chronic diseases lacks convenient methods and means for chronic patients; ② The big data for chronic diseases is monitored from the government and medical organization level, but lacks the big data for chronic diseases from the level of chronic disease patients.

[0008] The invention patent with application number 202111430825.3 discloses a Parkinson's disease follow-up system, including a patient side, a doctor side and a server side, and the patient side and the doctor side are connected to the server side; the patient side includes a patient scale module, which pushes the corresponding patient scale to the patient according to the patient's current stage of treatment, obtains the patient scale content filled in by the patient, and uploads it to the server side, and the server side sends the patient scale content to the doctor side; the doctor side includes a doctor scale module, which receives the patient scale content and pushes the doctor scale to the doctor, and obtains the doctor scale content filled in by the doctor and uploads it to the server side; the server side calculates the patient's disease stage according to the patient scale content and the doctor scale content, and sends the disease stage to the patient side and the doctor side. The above invention solves the technical problems of low informatization in the existing Parkinson's disease follow-up management and low efficiency in obtaining medical research big data information. However, this invention only collects the condition data of Parkinson's patients and improves the efficiency of obtaining big data for medical research. It does not effectively manage, deeply mine and apply these medical data, lacks intelligent diagnosis and decision-making services, and cannot support the development of smart healthcare. Summary of the invention

[0009] In response to the technical problem that the existing follow-up system cannot accurately monitor the condition of Parkinson's disease, the present invention proposes an extended diagnosis and treatment service system for Parkinson's disease patients. Patients and medical staff can evaluate the effect of symptom treatment through follow-up. The collected disease data are extracted and processed, and a data scenario model for personalized treatment of patients is established in combination with intelligent algorithms to predict and decide future treatment plans, thereby realizing extended diagnosis of Parkinson's disease treatment. At the same time, a knowledge graph of Parkinson's disease is established in collaboration with the cloud to assist doctors in providing personalized intelligent diagnosis and decision-making services for patients.

[0010] In order to achieve the above-mentioned purpose, the technical solution of the present invention is implemented as follows: an extended diagnosis and treatment service system for Parkinson's disease patients, including a patient mobile terminal, a medical mobile terminal and an application server, wherein the patient mobile terminal and the medical mobile terminal are both connected to the application server; the patient mobile terminal is provided with a patient-medical binding unit, a patient scale filling unit and a doctor-patient interaction unit, the medical mobile terminal is provided with a patient-medical binding unit, a doctor-patient interaction unit, a condition description unit and a doctor scale filling unit, the doctor-patient interaction unit of the medical mobile terminal is connected to the condition description unit, and the condition description unit is connected to the doctor scale filling unit; the patient-medical binding unit, the patient scale filling unit, the doctor-patient interaction unit, the condition description unit and the doctor scale filling unit are all connected to the application server;

[0011] The patient's mobile terminal uses the patient and medical binding unit to complete the data entry of the patient's basic information, basic symptoms, and medication details. The patient fills in the scale unit to fill in the data of the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale. The doctor-patient interaction unit is used to collect data information about the patient's condition using text, sound, pictures, and videos in the doctor-patient interaction interface;

[0012] The medical and nursing mobile terminal uses the patient and medical binding unit to complete the filling of the doctor's basic information data, uses the doctor-patient interaction unit to collect data information of the doctor's consultation text, sound, picture, and video in the doctor-patient interaction interface, and uses the doctor's scale filling unit to allow the doctor to fill in the scale; the medical and nursing mobile terminal completes the filling of the condition through the condition description unit and the condition label recognized by the application server, and fills in the scale according to the patient's condition description.

[0013] Preferably, the application server is provided with a data storage and processing module, which includes a data storage module, a data processing module and a data evaluation module which are connected in sequence, and the patient and medical care binding unit, the patient filling out scale unit, the doctor-patient interaction unit, the condition description unit and the doctor filling out scale unit are all connected to the data storage module; the data processing module is connected to the condition description unit.

[0014] Preferably, the data storage module includes a source database and a target database; the patient-medical care binding unit, the patient-filling scale unit, the doctor-patient interaction unit, and the doctor-filling scale unit are all connected to the source database, the condition description unit is connected to the target database, and the source database and the target database are both connected to the data processing module;

[0015] The data processing module includes a scale data extraction unit, a scale data calculation unit and an interactive data processing unit, the source database is connected to the scale data extraction unit, the scale data extraction unit is connected to the scale data calculation unit, the scale data calculation unit and the interactive data processing are both connected to the target database, and the scale data calculation unit is connected to the data evaluation module;

[0016] The data evaluation module includes a patient and doctor evaluation calculation unit and an extended diagnosis tracking treatment plan generation unit connected in sequence, the scale data calculation unit is connected to the doctor evaluation calculation unit, the patient and doctor evaluation calculation unit is connected to the target database, the extended diagnosis tracking treatment plan generation unit is connected to the target database, and the patient and doctor evaluation calculation unit is connected to the extended diagnosis tracking treatment plan generation unit.

[0017] Preferably, the patient's basic information, basic symptoms, medication details and doctor's basic information collected by the patient and medical care binding unit are input into the source database; the scale data collected by the patient filling scale unit and the doctor filling scale unit are input into the source database, and the doctor-patient interaction text, sound, picture and video data collected by the doctor-patient interaction unit are stored in the source database; the scale data extraction unit extracts the scale data, and the scale data calculation unit performs a custom score quantitative conversion on the extracted scale data, and the calculated scale final value is stored in the target database; the interactive data processing unit extracts keywords from the interactive data collected by the doctor-patient interaction unit to generate a disease label and stores it in the target database. Target database; the condition description unit completes the condition filling through the condition label in the target database, and the doctor fills in the scale according to the patient's condition description; the patient and doctor evaluation calculation unit respectively quantifies the doctor's and patient's evaluations on the degree of symptom relief, medication efficacy, and treatment effect by scoring, and at the same time forms an evaluation report based on the treatment effect in the time domain. The comprehensive diagnosis result is obtained based on the score quantification calculation of the patient and doctor evaluation calculation unit and the scale final value of the scale data calculation unit. The extended tracking treatment plan generation unit generates a treatment plan based on the comprehensive diagnosis result for the patient's medication, daily precautions, and follow-up interval information, and sends it to the patient's mobile terminal;

[0018] During the file creation period, the patient's basic information, basic symptoms, and medication details are entered through the patient and medical staff binding unit, and the medical staff is bound, the timestamp is set, the follow-up interval and the extended diagnosis process are determined, and the basic data are quantified by standards to establish a historical diagnosis and treatment data scenario model; during the follow-up period, the patient fills in the options for the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale through the patient filling in scale unit. At the same time, the doctor-patient interaction unit extracts the interactive data of text, voice, photos, and videos of the follow-up interaction. The doctor uses the doctor filling in scale unit to fill in the condition description according to the interactive data and the generated condition label. The scale data extraction unit assigns scores to the scale data for individual items, sub-items, and total items. The scale data calculation unit is enhanced The patient's symptom data is calculated by weight, and the timestamp is added to establish a follow-up data scenario model through scale data and interaction data; the patient and doctor evaluation calculation unit uses the weight iterative optimization method to analyze the diagnosis and treatment effect evaluation of patients and medical staff, generate an extended diagnosis and tracking treatment plan, and establish an extended diagnosis and treatment data scenario model based on the evaluation data; according to the timestamp, the follow-up data scenario model is changed to the historical data diagnosis and treatment scenario at the next diagnosis; with the timestamp as the clue, the follow-up data scenario model, the historical diagnosis and treatment data scenario model, and the extended diagnosis and treatment data scenario model are combined and arranged in time series to establish a patient personalized treatment data scenario model; the data of the patient personalized treatment data scenario model is uploaded to the cloud as metadata to provide data support for the Parkinson's disease knowledge graph.

[0019] The steps of its operation method are:

[0020] Step 1: Parkinson's disease patients establish basic data including basic patient information, basic symptoms, and medication details through the patient and medical staff binding unit, and bind medical staff at the same time. Medical staff fill in basic information through the patient and medical staff binding unit, set timestamps, determine follow-up time and extend diagnostic procedures;

[0021] Step 2: The medical and nursing mobile terminals and the patient mobile terminals collect the scale data and upload them to the application server, perform quantitative calculations on the single item scores, sub-item scores, and total item scores of the scale data, and perform enhanced weight calculations on the scale data to obtain the final value of the scale;

[0022] Step 3: The doctor fills in the comprehensive diagnosis result based on the scale score, interaction data, condition label, and treatment effect evaluation and feeds it back to the patient. The patient and medical staff evaluate the treatment effect of the follow-up visit based on the comprehensive diagnosis result. At the same time, the patient and medical staff respectively evaluate the effect of the treatment process in the time period between the current follow-up visit and the previous diagnosis in real time. The application server performs evaluation and calculation through the cross-weight calculation method and determines the extended diagnosis plan.

[0023] Preferably, the method for quantitatively calculating the single item score, sub-item score and total item score of the scale data is:

[0024] Any scale in the scale data is quantized into scale M = {m 0 =0,m 1 =1,...,m i =i},m i Indicates the options in the scale, each option represents the severity of a certain disease;

[0025] Quantify the options for each question, including quantifying the single item score according to [0...n]; quantify the two answers to each question separately, quantify item A according to [0...n], quantify item B according to [0...n], and the sub-item score is A*B; the total score is the sum of the score of each tensor table item and the sub-item score Among them, SUM is the total score, X s is the score of the sth item in the scale, Y t is the t-th sub-item score in the scale, n is the number of single-item scores in the scale, and m is the number of sub-item scores in the scale;

[0026] The patient's basic information, basic symptoms, medication details, and basic information of medical personnel are stored in the database with the corresponding field data type; the timestamp is stored in the database according to the time data type, and the two parties confirm the binding with a semaphore S, which is composed of the doctor's ID number and the patient's ID number. The semaphores S of doctors and patients who are not bound are all set to 0; if the doctor's release semaphore is equal to the patient's release semaphore and the doctor's and patient's semaphores are not 0, the doctor and the patient are in a follow-up relationship;

[0027] The method of performing enhanced weight calculation on the scale data to obtain the final value of the scale is: assuming that the patient's scale data is X={x 1 ,x 2 ,…,x q}, the medical care scale data is Y = {y 1 ,y 2 ,…,y q}, the weight is w, when the x of the p-th tensor table p =y p When p =2, when x p ≠y p , w p =1, the final value of the scale is:

[0028]

[0029] Among them, the patient's condition is judged according to the final value of each scale; the follow-up diagnosis result can be judged according to the final value of all scales. The doctor fills in the comprehensive diagnosis result according to the final value of the scale, description of the condition, and evaluation of the treatment process, and chooses the hospital for the patient to visit or continue follow-up.

[0030] Preferably, the doctor and the patient upload the scoring records of the symptom relief degree, medication efficacy, and treatment effect to the application server, and the medical mobile terminal selects the labels of the patient's symptoms, severity of the disease, and medication effect according to the interactive data, completes the description of the disease of this follow-up visit, and uploads it to the application server;

[0031] The doctor fills out the treatment plan based on the comprehensive diagnosis results, including the next follow-up time, treatment methods, medication precautions, and nursing precautions;

[0032] Patient and physician evaluations included follow-up symptom scores, follow-up treatment scores, follow-up medication scores, and standard scale scores.

[0033] Preferably, the patient and doctor's evaluation score range for the treatment effect is set to L = {0, 1, 2, 3, 4, 5}, and the patient evaluation score is Among them, n represents the total number of evaluation items, x i is the score of the patient’s i-th evaluation item, and the input vector is represented by X1={x 0 ,x 1 ,x 2 ,x 3};

[0034] The range of the patient's score for the i-th evaluation item is x i ∈{0,1,2,3,4,5}, the weight is represented by W ik ={w 0k ,w 1k ,w 2k ,w 3k}, the first follow-up initialization assignment weights w 0k =1,w 1k =1,w 2k =1,w 3k =1; the weight of each follow-up patient is iteratively optimized: Among them, xi k represents the score of the i-th evaluation item of the patient's k-th follow-up, W ik is the weight of the i-th evaluation item in the k-th follow-up, W i(k-1) is the weight of the i-th evaluation item in the k-1-th follow-up, and the correction value is calculated by the correction function:

[0035] Doctors' evaluation score is Among them, y j represents the score of the jth evaluation item, and the input vector is represented as Y1={y 0 ,y 1 ,y 2 ,y 3}, the doctor weight is Wjk ={w 0k ,w 1k ,w 2k ,w 3k}, the first follow-up initialization assignment weights w 0k =1,w 1k =1,w 2k =1,w 3k =1, and then each follow-up weight is optimized iteratively: W jk represents the weight of the jth evaluation item in the kth follow-up, W j(k-1) is the weight of the jth evaluation item in the k-1th follow-up, and the correction value is calculated by the correction function:

[0036] Preferably, the calculation model for the comprehensive evaluation of the effect of the treatment process by the patient and the doctor is Among them, h w (x, y) represents the weighted comprehensive evaluation results of patients and doctors, g k (x) represents the comprehensive evaluation score of the patient at the kth follow-up, g k (y) represents the comprehensive evaluation score of the doctor's kth follow-up visit, represents the evaluation weight of the patient's kth follow-up, represents the evaluation weight of the doctor's kth follow-up visit; the weight is optimized iteratively and in, represents the evaluation weight of the patient's k-1th follow-up, represents the evaluation weight of the doctor's k-1th follow-up. When evaluating the treatment effect at the first follow-up, the patient and the doctor are calculated with the same weight according to the average principle. After that, the evaluation weight of each follow-up is calculated by adding a correction value to the evaluation weight of the previous follow-up. The correction value is calculated by the correction function, and the correction function of the patient evaluation is: The correction function of the doctor's evaluation is

[0037] Preferably, the calculation process of the application server performing evaluation calculation by a cross-weight calculation method to obtain the evaluation score is:

[0038] The first step is to convert the scores of the evaluation items of the treatment process of Parkinson's disease patients into i As input, the patient weight W ik Perform iterative optimization calculations and use the patient evaluation score g(x i ) formula to calculate the patient evaluation score;

[0039] The second step is to calculate the score y of the evaluation item of the doctor's treatment process. j As input, the doctor weight Wjk Perform iterative optimization calculations based on the doctor's evaluation score g(y j ) formula to calculate the doctor evaluation score;

[0040] In the third step, the patient evaluation scores and doctor evaluation scores during the patient treatment process are used as the input of the comprehensive evaluation calculation model, and the evaluation weights are adjusted by iterative optimization. and Iterative calculation is performed, and the weighted comprehensive evaluation result obtained is the comprehensive evaluation result.

[0041] Compared with the prior art, the present invention has the following beneficial effects: Parkinson's disease patients can have their Parkinson's disease severity clinically diagnosed by the hospital, and start tracking the treatment process with medical staff through the Hongmeng Yuan Service application on their mobile phones;

[0042] During the follow-up treatment process, Parkinson's patients and doctors use their mobile phones to promptly record disease symptoms, follow-up interactions, examination documents, treatment methods, and treatment effects, thereby improving the traceability of health management for patients with chronic diseases. The follow-up electronic health records, such as text, voice, photos, and videos of interactions between patients and doctors, are stored in their own accounts, reflecting the convenience of fully utilizing mobile phones to collect data.

[0043] Through the scale scores of patients and medical staff, combined with follow-up text, voice, photos, and videos for data processing and extraction, a personalized treatment scenario model is established for each patient. The model is transmitted to the cloud to construct a knowledge graph of Parkinson's disease risk factors. A collaborative mechanism is established between the patient's mobile personalized treatment data scenario model and the cloud knowledge graph. The mobile terminal establishes a personal data model to provide data support for the cloud, and the cloud knowledge graph can provide decision support for the mobile terminal.

[0044] The Parkinson's disease diagnosis is integrated with the weight iteration algorithm to comprehensively evaluate the treatment effect, provide scientific data basis for correcting the treatment plan, and provide decision support for optimizing the next treatment plan. It intelligently extends the time and space domains of treatment and ensures the tracking treatment effect of Parkinson's disease. Through the evaluation of the treatment effect by intelligent algorithms, the treatment plan can be corrected in time and the next treatment plan can be optimized to provide decision support. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0046] Figure 1 It is a flow chart of the present invention.

[0047] Figure 2 It is a system principle block diagram of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] like Figure 2As shown, an extended diagnosis and treatment service system for Parkinson's patients includes a mobile terminal used by Parkinson's patients and medical staff, the mobile terminal is a mobile phone, the mobile terminal is connected to an application server, the mobile terminal includes a medical client and a patient client, and the application server is connected to the cloud. The mobile terminal realizes the collection of patient and medical data, and is divided into a Parkinson's patient module and a medical module. Among them, it includes a patient and medical binding unit S11, a patient filling scale unit S12, a doctor-patient interaction unit S13, a condition description unit S14, and a doctor filling scale unit S15. The Parkinson's patient module includes a patient and medical binding unit S11, a patient filling scale unit S12, and a doctor-patient interaction unit S13. The medical module includes a patient and medical binding unit S11, a doctor-patient interaction unit S13, a condition description unit S14, and a doctor filling scale unit S15. The Parkinson's disease patient module completes the data filling of the patient's basic information and basic symptoms (which can be completed by the patient or the patient's family, guardian, or medical staff) and medication details (completed by medical staff) in the patient-medical staff binding unit S11, as well as the data filling of the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale in the patient-filled scale unit S12 (completed by the patient or the patient's family or guardian), and the collection of data information such as the patient's condition in text, sound, picture, video, etc. in the medical-patient interaction interface in the doctor-patient interaction unit S13; the medical staff module completes the data filling of the doctor's basic information in the patient-medical staff binding unit S11, as well as the collection of data information such as the doctor's consultation text, sound, picture, video, etc. in the medical-patient interaction interface in the doctor-patient interaction unit S13, as well as the filling of the condition in the condition description unit S14, and the filling of the scale by the doctor in the doctor-filled scale unit S15. The application server realizes the storage and processing of medical data. The application server is equipped with a data storage module, a data processing module and a data evaluation module. The patient-medical binding unit S11, the patient-filling scale unit S12, the doctor-patient interaction unit S13, the condition description unit S14 and the doctor-filling scale unit S15 are all connected to the data storage module. Among them, the data storage module includes a source database D0 and a target database D1; the patient-medical binding unit S11, the patient-filling scale unit S12, the doctor-patient interaction unit S13, and the doctor-filling scale unit S15 are all connected to the source database D0, and the condition description unit S14 is connected to the target database D1. The data processing module includes a scale data extraction unit S21, a scale data calculation unit S22, and an interactive data processing S23. The scale data extraction unit S21 is connected to the scale data calculation unit S22, and the scale data calculation unit S22 and the interactive data processing S23 are both connected to the target database D1; the data evaluation module includes a patient and doctor evaluation calculation unit S31 and an extended diagnosis tracking treatment plan generation unit S32 which are connected in sequence. The patient and doctor evaluation calculation unit S31 and the extended diagnosis tracking treatment plan generation unit S32 are connected to the target database D1.The patient's basic information, basic symptoms, medication details and doctor's basic information collected by the mobile terminal are input into the source database D0; the scale data collected by the mobile terminal are input into the source database D0, and the scale data extraction unit S21 extracts the scale data, and the scale data calculation unit S22 performs a custom score quantitative conversion on the extracted scale data, and the calculated final scale value is stored in the target database D1; the doctor-patient interaction text, sound, picture and video data collected by the mobile terminal are stored in the source database D0, and the interaction data processing unit S23 generates a disease label library by extracting keywords from the interaction data of the doctor's mobile terminal and stores it in the target database D1; the disease description unit S14 is a target database. The condition label in D1 is used to complete the filling of the condition, and the doctor fills in the scale according to the patient's condition description; the doctor and the patient's evaluation of the degree of symptom relief, medication efficacy, and treatment effect are quantified and calculated through the patient and doctor evaluation calculation unit S31. At the same time, an evaluation report is formed based on the treatment effect in the time domain (including from the most recent follow-up or outpatient clinic to this follow-up). A comprehensive diagnosis result is obtained based on the score quantification calculation of the patient and doctor evaluation calculation unit S31 and the scale final value of the scale data calculation unit S22. The extended tracking treatment plan generation unit S32 generates a treatment plan for the patient's medication, daily precautions, follow-up intervals and other information based on the comprehensive diagnosis result, and sends it to the patient's mobile terminal.

[0050] During the file creation period, the patient's basic information, basic symptoms, and medication details are entered, and medical staff are bound, timestamps are set, and follow-up intervals and extended diagnosis processes are determined. Here, the basic data is quantified by standardization to establish the initial data scenario model for historical diagnosis and treatment. During the follow-up period, the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale are filled in, and the text, voice, photos, videos, and other records of follow-up interactions are saved. According to the interactive data, the doctor uses tags to fill in the description of the condition. The scale data is scored by single items, sub-items, and total items. The patient's symptom data is enhanced by weight calculation, and the timestamp is added to establish the follow-up data scenario model. The weight iteration optimization method is used to analyze the evaluation of the diagnosis and treatment effects of patients and medical staff, and an extended diagnosis and tracking treatment plan is generated. The extended diagnosis and treatment data scenario model is established. Patients and medical staff can also negotiate to end the extended diagnosis process based on the diagnosis data. The patient's personalized treatment data scenario model is established with the timestamp as the clue and combined with the three data scenario models of follow-up, historical diagnosis and treatment, and extended diagnosis and treatment; the data of the patient's personalized treatment data scenario model is uploaded to the cloud. The extended diagnosis and treatment service system for Parkinson's disease patients of the present invention performs quantitative processing on source data while collecting data, thereby improving data processing efficiency in a big data environment. When processing unstructured data, a method of converting the data into text data and extracting keywords to define tags is adopted, so that the data stored in the application database can be directly used as metadata to provide data support for the Parkinson's disease knowledge graph in the cloud server. At the same time, the Parkinson's disease knowledge graph does not belong to the scope of the present invention, but the present invention can provide high-quality data services for the cloud Parkinson's disease knowledge graph through a network data interface.

[0051] like Figure 1 As shown, a service method of an extended diagnosis and treatment service system for Parkinson's disease patients includes the following steps:

[0052] Step 1: Parkinson's disease patients undergo clinical diagnosis and treatment in the hospital to determine their symptoms and establish an electronic patient file, including basic information, basic symptoms, and medication details. At the same time, the medical staff is bound, a timestamp is set, and the follow-up time and extended diagnosis process are determined.

[0053] Parkinson's patients and medical staff use mobile terminals to enter data and complete system data collection. The HarmonyOS environment is used to develop the Parkinson's disease follow-up meta-service application, using the DevEco Studio development environment, ArkTS language and ArkUI framework. After the patient's diagnosis is confirmed in the hospital, he or she consults with the doctor for follow-up diagnosis and treatment. The APP is mainly used to register and log in patients and medical staff. Patients fill in basic information, basic symptoms, and medication details. Medical staff fill in basic information and set the follow-up treatment timeline. Both parties confirm the binding and start the follow-up process. Remote data collection through mobile phones is convenient and not restricted by location. After the doctor and patient are bound, it is convenient for the later follow-up process. The doctor is familiar with the patient's historical condition, which is conducive to long-term condition tracking and treatment.

[0054] Step 2: The medical and nursing mobile terminals and the patient mobile terminals collect the scale data and upload them to the application server. The scale data includes comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale. The single score, sub-score, and total score of the scale data are quantified and calculated, recorded, and saved in the patient's electronic health record.

[0055] During the follow-up, fill in the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale. The data are quantified using M = {m 0 =0,m 1 =1,...,m i =i}, where M represents any scale, m i Represents the options in the scale, each option represents the severity of a certain disease.

[0056] During the follow-up process, the patient or his / her family members assist in filling out the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale. The medical staff fill out the above scales based on the text, sound, picture, video and other information interacting with the patient. The fields of each scale include the patient's ID number, date of filling, person filling in, and multiple question descriptions. The answers to each question are quantified, including the single-item score X, which is quantified according to [0...n]. For example, the evaluation items of anxiety mood in the Hamilton Anxiety Rating Scale are divided into five levels [none, mild, mild, moderate, severe], and the quantitative score is [0,1,2,3,4]. The sub-item score means that each question has two answers, which are quantified separately. Item A is quantified according to [0...n], and item B is quantified according to [0...n]. For example, the evaluation items of whether the patient has periarticular pain in the Parkinson's Disease Pain Scale include severity [none, mild, moderate, severe] and frequency [never, rarely, often, frequently, often]. The quantitative score is A = [0,1,2,3], B = [0,1,2,3,4], and the sub-item score is Y = A*B. The total score is the sum of the score of each scale item and the sub-item score. Here SUM is the total score, X s is the score of the sth item in the scale, Y t is the t-th sub-item score in the scale. n is the number of single-item scores in the scale, and m is the number of sub-item scores in the scale.

[0057] The application server is mainly responsible for data processing and calculation. Records such as patient basic information, basic symptoms, medication details, and basic information of medical personnel are stored in the database with the corresponding field data type. The timestamp is stored in the database according to the time data type. Both parties confirm the binding with a semaphore S. The semaphore S is composed of the doctor ID number and the patient ID number. For example, if the doctor ID is 100001 and the patient ID is 110001, then the semaphore S = 100001110001. The unbound doctors and patients S are all 0. Let the doctor semaphore be S and the patient semaphore be S'. When S = S' and S≠0, S'≠0, the doctor and the patient are in a follow-up relationship. The above data information establishes a patient historical diagnosis and treatment data scenario model.

[0058] The interactive data between doctors and patients during the follow-up process includes text, sound, image, and video. The doctor selects labels for the patient's symptoms, severity, and medication effect based on the interactive data, completes the description of the follow-up condition, and fills in the scale data. The patient scale data and the doctor scale data are enhanced and weighted to obtain the final value of the scale. Suppose the patient scale data is X = {x 1 ,x 2 ,…,x q}, the medical care scale data is Y = {y 1 ,y 2 ,…,y q}, q represents the qth tensor table, p represents the pth tensor table, and the weight is w. When using x p =y p When p =2, when x p ≠y p , w p =1, then the final value matrix of the scale is:

[0059]

[0060] Among them, the patient's condition is judged according to the final value of each scale. For example, the total score of the sleepiness scale is 24 points. Among the 24 points, a score greater than 6 points indicates sleepiness, greater than 11 points indicates excessive sleepiness, and greater than 16 points indicates dangerous sleepiness. The follow-up diagnosis results can be determined according to the scores of all scales. The doctor fills in the comprehensive diagnosis results based on the scale scores, condition description, and treatment process evaluation, and chooses the patient to go to the hospital for treatment or continue follow-up. The above data information establishes a follow-up data scenario model. Patients and medical staff respectively evaluate the treatment effect within the time period of this follow-up and the last diagnosis in real time. The cross-weight calculation method of the treatment effect of patients and doctors is used to timely evaluate the treatment effect of this stage and predict the next treatment method. It can timely discover deficiencies and deviations in the treatment process, and doctors provide extended diagnosis services for Parkinson's patients.

[0061] Step 3: The medical client and the patient client collect follow-up interaction data, extract, process and upload them to the application server, including original records such as text, voice, photos, and videos, which are saved in the electronic health record.

[0062] Follow-up interaction data is text, voice, photos or videos of communication between doctors and patients through dialog boxes. Doctors select labels for patient symptoms, severity of the disease and medication effects based on the interaction data, complete the description of the follow-up condition and submit it to the application server. For example, labels for pain symptoms include: musculoskeletal, chronic pain, movement pain, night pain, oral-facial pain, abnormal skin color, and radicular pain. Labels for pain severity include: none, mild, moderate, and severe. Labels for pain frequency include: never, rarely, often, frequently, and often. Labels for medication effects include: symptom improvement, symptom relief, and no change in symptoms. This method can select labels for rapid quantification as needed, realizes direct quantification of data during data collection, and improves data processing efficiency.

[0063] Step 4: The medical client and the patient client upload the treatment effect score to the application server. The doctor and the patient's score records on the degree of symptom relief, medication efficacy, and treatment effect are submitted to the application server. The application server calculates the user evaluation and determines the extended diagnosis plan based on this data.

[0064] The doctor fills in the comprehensive diagnosis results based on the scale score, condition description, and treatment effect evaluation and feeds back to the patient. The patient and medical staff evaluate the follow-up effect (satisfactory, general, unsatisfactory) based on the results and determine the next diagnosis method (follow-up, hospital outpatient clinic). Those with satisfactory or general follow-up effects are defined as those who meet the standard and can continue to determine the time for the next follow-up. The doctor fills in the treatment plan based on the comprehensive diagnosis results, including the next follow-up time, treatment method, medication precautions, and nursing precautions. Those with unsatisfactory follow-up effects are defined as those who do not meet the standard and need to undergo outpatient diagnosis in the hospital, and the follow-up process is suspended.

[0065] The range of the patient and doctor's evaluation scores for the treatment effect is set to L = {0, 1, 2, 3, 4, 5}, and the patient evaluation score is calculated as follows: Where n represents n evaluation items, i represents the i-th evaluation item, and x i is the patient's i-th evaluation score, then the input vector is represented as X = {x 0 ,x 1 ,x 2 ,x 3}(Formula 2), the patient and doctor's evaluations included follow-up symptom scores, follow-up treatment scores, follow-up medication scores, and standard scale scores.

[0066] The range of values ​​corresponding to the 4 input values ​​of formula 1 is x i ={0,1,2,3,4,5}, weight is denoted by W ik ={w 0k ,w 1k ,w 2k ,w 3k}(Formula 3), the weights w after the initial assignment of the first follow-up visit 0k =1,w 1k =1,w 2k =1,w 3k =1; each subsequent follow-up weight is optimized iteratively, i.e. Among them, i represents the patient's i-th evaluation item, k represents the k-th follow-up, and xi k represents the score of the ith evaluation item of the patient's kth follow-up. The meaning of formula 4 is that the weight of the ith evaluation item of the kth follow-up is the weight of the ith evaluation item of the k-1th follow-up plus the correction value, and the correction value is calculated by the correction function, that is,

[0067] Calculation of doctor evaluation scores Among them, j represents the jth evaluation item of the doctor, y j represents the jth evaluation item score, and k represents the kth follow-up visit. The input vector is represented as Y = {y 0 ,y 1 ,y 2 ,y 3}(Formula 6), the corresponding value range is the same as Formula 2, and the weight is expressed as W jk ={w 0k ,w 1k ,w 2k ,w 3k}(Formula 7), the corresponding initialization assignment is the same as Formula 3, and then each follow-up weight is iteratively optimized, that is, Formula 8 means that the weight of the jth evaluation item at the kth follow-up is the weight of the jth evaluation item at the k-1th follow-up plus the correction value, which is calculated by the correction function, that is,

[0068] The calculation model used for the comprehensive evaluation of treatment effect by patients and doctors is Among them, h w (x, y) represents the weighted comprehensive evaluation results of patients and doctors, g i (x) represents the patient's comprehensive evaluation score at the i-th follow-up visit, g i (y) represents the comprehensive evaluation score of the doctor’s ith follow-up visit, represents the patient's ith follow-up evaluation weight, represents the evaluation weight of the doctor’s ith follow-up visit. The weight is optimized iteratively, i.e. in, represents the evaluation score of the patient's i-1th follow-up visit, represents the evaluation score of the doctor's i-1th follow-up visit, with an initial value of w x =0.5, w y =0.5. When evaluating the treatment effect at the first follow-up visit, according to the principle of averageness, the patient and the doctor are calculated with the same weight. After that, the weight of the doctor and the patient in each follow-up visit is calculated by adding the weight of the previous follow-up visit to the correction value. The correction value is calculated by the correction function. The correction function for patient evaluation is: The correction function of the doctor's evaluation is The correction value reflects the impact of the doctor's and patient's respective evaluations on the overall evaluation, increasing the accuracy of the next evaluation.

[0069] According to the above description, the evaluation score calculation process is divided into three steps:

[0070] In the first step, the treatment process evaluation score of Parkinson's disease patients is used as the input of the algorithm, and the weights are iteratively calculated according to Formula 3 and Formula 4. The output result of Formula 1 is the patient evaluation score. This process is calculated on the patient side and serves as a reference for patients to receive extended diagnosis and continue to follow up on treatment plans.

[0071] In the second step, the doctor's treatment process evaluation score is used as the input of the algorithm, and the weights are iteratively calculated according to Formula 7 and Formula 8. The output result is the doctor's evaluation score according to Formula 5. This process is calculated on the doctor's side and serves as a reference for the doctor to provide extended diagnosis and continue to track the treatment plan.

[0072] In the third step, the patient's evaluation score on the effectiveness of the treatment process and the doctor's evaluation score on the effectiveness of the treatment process are used as inputs of Formula 9, and weighted iterative calculations are performed. The output result of Formula 9 is a comprehensive evaluation result, which serves as a reference for doctors to fill in the comprehensive diagnosis results and determine the extended diagnosis and continuous follow-up treatment plan.

[0073] Algorithm implementation:

[0074] The first step is to implement the patient evaluation algorithm

[0075] Patient(x){

[0076] Folat W; / / define weight

[0077] Float X, g(x); / / Define input vector, output function

[0078] While(i==1){ / / ith follow-up visit

[0079] W={1,1,…,1}; / / initial value of weight

[0080] g i (x);} / / Calculate output

[0081] While(i>=2){

[0082]

[0083] g i (x);} / / Calculate output

[0084] }

[0085] The second step is to implement the algorithm for doctor evaluation

[0086] Doctor(y){

[0087] Folat W; / / define weight

[0088] Float X, g(y); / / Define input vector, output function

[0089] While(i==1){ / / i records the number of follow-up visits

[0090] W={1,1,…,1}; / / initial value of weight

[0091] g i (y);} / / Calculate output

[0092] While(i>=2){

[0093]

[0094] g i (y);} / / Calculate output

[0095] }

[0096] The third step is to implement the algorithm of comprehensive evaluation

[0097] Total(x){

[0098] Folat w x ,w y , g(x), g(y); / / Define weight vector matrix, input vector

[0099] Float h w (x,y); / / define the output result

[0100] while(i=1){

[0101] w x =0.5, w y =0.5;

[0102] h w (x,y)=(w x ·g i (x)+w y ·g i (y)) / 2;

[0103] }

[0104] While(i>=2){

[0105]

[0106] h w (x,y)=(w x ·g i (x)+w y ·g i (y)) / 2;

[0107] }

[0108] }

[0109] The application server securely stores basic data, scale data, interactive data, and evaluation data. Scale data and interactive data are defined as follow-up data scenario models, basic data are defined as historical diagnosis and treatment data scenarios, and evaluation data are defined as extended diagnosis and treatment data scenarios. Doctors and patients can choose to view different scenarios based on timestamps. Basic data is displayed in the form of a data table, total scale score data is displayed in the form of a bar chart, interactive data is displayed in the form of a word cloud chart, evaluation data is displayed in the form of a pie chart, and the patient follow-up process is displayed in the form of a time series according to the timestamp. The scale data and interaction data are used to establish a follow-up data scenario model, the basic data is used to establish a historical diagnosis and treatment data scenario model, and the evaluation data is used to establish an extended diagnosis and treatment scenario model. According to the timestamp, the follow-up data scenario model is changed to the historical data diagnosis and treatment scenario at the next diagnosis. Based on this, the treatment data scenario arranged in time series is defined as a patient-personalized treatment data scenario model. Each data scenario model has relatively professional medical data, which can be pushed to the cloud application server through the network interface, providing more detailed data support for the construction of the Parkinson's disease knowledge graph. The present invention does not involve the construction of the Parkinson's disease knowledge graph.

[0110] Either the medical client or the patient client can initiate the termination of the extended diagnostic service. Either party can fill out the termination application on the mobile terminal and submit it. The other party confirms and submits the extended diagnostic service opinion, and the termination is timestamped at the same time.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An extended diagnosis and treatment service system for Parkinson's disease patients, characterized in that: The invention comprises a patient mobile terminal, a medical mobile terminal and an application server, wherein the patient mobile terminal and the medical mobile terminal are both connected to the application server; the patient mobile terminal is provided with a patient-medical binding unit (S11), a patient scale filling unit (S12) and a doctor-patient interaction unit (S13); the medical mobile terminal is provided with a patient-medical binding unit (S11), a doctor-patient interaction unit (S13), a condition description unit (S14) and a doctor scale filling unit (S15); the doctor-patient interaction unit (S13) of the medical mobile terminal is connected to the condition description unit (S14), and the condition description unit (S14) is connected to the doctor scale filling unit (S15); the patient-medical binding unit (S11), the patient scale filling unit (S12), the doctor-patient interaction unit (S13), the condition description unit (S14) and the doctor scale filling unit (S15) are all connected to the application server; The patient's mobile terminal uses the patient and medical binding unit (S11) to complete the data filling of the patient's basic information, basic symptoms, and medication details. The patient fills in the scale unit (S12) to fill in the data of the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale. The doctor-patient interaction unit (S13) is used to collect data information of the patient's description of the condition using text, sound, picture, and video in the doctor-patient interaction interface; The medical care mobile terminal uses the patient and medical care binding unit (S11) to complete the filling of the doctor's basic information data, uses the doctor-patient interaction unit (S13) to collect data information of the doctor's consultation text, sound, picture, and video in the doctor-patient interaction interface, and uses the doctor filling scale unit (S15) to let the doctor fill in the scale; the medical care mobile terminal completes the filling of the condition through the condition description unit (S14) and the condition label recognized by the application server, and fills in the scale according to the patient's condition description.

2. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 1, characterized in that: The application server is provided with a data storage module, a data processing module and a data evaluation module which are connected in sequence; the patient and medical care binding unit (S11), the patient filling out scale unit (S12), the doctor-patient interaction unit (S13), the condition description unit (S14) and the doctor filling out scale unit (S15) are all connected to the data storage module; the data processing module is connected to the condition description unit (S14).

3. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 2, characterized in that: The data storage module includes a source database (D0) and a target database (D1); the patient and medical care binding unit (S11), the patient filling out a scale unit (S12), the doctor-patient interaction unit (S13), and the doctor filling out a scale unit (S15) are all connected to the source database (D0), the condition description unit (S14) is connected to the target database (D1), and the source database (D0) and the target database (D1) are both connected to the data processing module; The data processing module includes a scale data extraction unit (S21), a scale data calculation unit (S22) and an interactive data processing (S23), the source database (D0) is connected to the scale data extraction unit (S21), the scale data extraction unit (S21) is connected to the scale data calculation unit (S22), the scale data calculation unit (S22) and the interactive data processing (S23) are both connected to the target database (D1), and the scale data calculation unit (S22) is connected to the data evaluation module; The data evaluation module includes a patient and doctor evaluation calculation unit (S31) and an extended diagnosis tracking treatment plan generation unit (S32) which are connected in sequence, the scale data calculation unit (S22) is connected to the doctor evaluation calculation unit (S31), the patient and doctor evaluation calculation unit (S31) is connected to the target database (D1), the extended diagnosis tracking treatment plan generation unit (S32) is connected to the target database (D1), and the patient and doctor evaluation calculation unit (S31) is connected to the extended diagnosis tracking treatment plan generation unit (S32).

4. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 3, characterized in that: The patient's basic information, basic symptoms, medication details and doctor's basic information collected by the patient and medical care binding unit (S11) are input into the source database (D0); the scale data collected by the patient filling scale unit (S12) and the doctor filling scale unit (S15) are input into the source database (D0), and the doctor-patient interaction text, sound, picture and video data collected by the doctor-patient interaction unit (S13) are stored in the source database (D0); the scale data extraction unit (S21) extracts the scale data, and the scale data calculation unit (S22) performs a custom score quantitative conversion on the extracted scale data, and the calculated scale final value is stored in the target database (D1); the interactive data processing unit (S23) performs keyword analysis on the interactive data collected by the doctor-patient interaction unit (S13); Extract and generate disease labels and store them in the target database (D1); the disease description unit (S14) completes the disease filling through the disease labels in the target database (D1), and the doctor fills in the scale according to the patient's disease description; the patient and doctor evaluation calculation unit (S31) respectively quantifies the doctor's and patient's evaluations of the degree of symptom relief, medication efficacy, and treatment effect by scoring, and at the same time forms an evaluation report based on the treatment effect in the time domain, and obtains a comprehensive diagnosis result based on the score quantification calculation of the patient and doctor evaluation calculation unit (S31) and the scale final value of the scale data calculation unit (S22); the extended tracking treatment plan generation unit (S32) generates a treatment plan based on the comprehensive diagnosis result for the patient's medication, daily precautions, and follow-up interval information, and sends it to the patient's mobile terminal; During the file creation period, the patient's basic information, basic symptoms, and medication details are entered through the patient and medical staff binding unit (S11), and the medical staff is bound, the timestamp is set, the follow-up interval and the extended diagnosis process are determined, and the basic data are quantified by standards to establish a historical diagnosis and treatment data scenario model; during the follow-up period, the patient fills in the options for the comprehensive scale, pain scale, mental scale, anxiety scale, depression scale, and sleepiness scale through the patient filling in the scale unit (S12). At the same time, the doctor-patient interaction unit (S13) extracts the interactive data of text, voice, photos, and videos of the follow-up interaction. The doctor uses the doctor filling in the scale unit (S15) to fill in the condition description according to the interactive data and the generated condition label. The scale data extraction unit (S21) assigns scores to the scale data for individual items, sub-items, and total items. The scale data is calculated. The calculation unit (S22) calculates the patient's symptom data by enhancing the weights, adds timestamps, and establishes a follow-up data scenario model through scale data and interaction data; the patient and doctor evaluation calculation unit (S31) uses the weight iteration optimization method to analyze the evaluation of the diagnosis and treatment effects of patients and medical staff, generates an extended diagnosis and tracking treatment plan, and establishes an extended diagnosis and treatment data scenario model based on the evaluation data; according to the timestamp, the follow-up data scenario model is changed to the historical data diagnosis and treatment scenario at the next diagnosis; with the timestamp as a clue, the follow-up data scenario model, the historical diagnosis and treatment data scenario model, and the extended diagnosis and treatment data scenario model are combined and arranged in time series to establish a patient personalized treatment data scenario model; the data of the patient personalized treatment data scenario model is uploaded to the cloud as metadata to provide data support for the Parkinson's disease knowledge graph.

5. The extended diagnosis and treatment service system for Parkinson's disease patients according to any one of claims 1 to 4, characterized in that: The steps of its operation method are: Step 1: Parkinson's disease patients establish basic data including basic patient information, basic symptoms, and medication details through the patient and medical binding unit (S11), and bind medical staff at the same time. Medical staff fill in basic information, set timestamps, determine follow-up time, and extend diagnostic procedures through the patient and medical binding unit (S11); Step 2: The medical and nursing mobile terminals and the patient mobile terminals collect the scale data and upload them to the application server, perform quantitative calculations on the single item scores, sub-item scores, and total item scores of the scale data, and perform enhanced weight calculations on the scale data to obtain the final value of the scale; Step 3: The doctor fills in the comprehensive diagnosis result based on the scale score, interaction data, condition label, and treatment effect evaluation and feeds it back to the patient. The patient and medical staff evaluate the treatment effect of the follow-up visit based on the comprehensive diagnosis result. At the same time, the patient and medical staff respectively evaluate the effect of the treatment process in the time period between the current follow-up visit and the previous diagnosis in real time. The application server performs evaluation and calculation through the cross-weight calculation method and determines the extended diagnosis plan.

6. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 5, characterized in that: The method for quantitatively calculating the single item score, sub-item score, and total item score of the scale data is: Any scale in the scale data is quantized into a scale M = {m0 = 0, m1 = 1, ..., m i =i},m i Indicates the options in the scale, each option represents the severity of a certain disease; Quantify the options for each question, including quantifying the individual score according to [0...n]; The two answers to each question are quantified separately. Item A is quantified as [0...n], and item B is quantified as [0...n]. The sub-item score is A*B; the total score is the sum of the score of each tensor table item and the sub-item score. Among them, SUM is the total score, X s is the score of the sth item in the scale, Y t is the t-th sub-item score in the scale, n is the number of single-item scores in the scale, and m is the number of sub-item scores in the scale; The patient's basic information, basic symptoms, medication details, and basic information of medical personnel are stored in the database with the corresponding field data type; the timestamp is stored in the database according to the time data type, and the two parties confirm the binding with a semaphore S, which is composed of the doctor's ID number and the patient's ID number. The semaphores S of doctors and patients who are not bound are all set to 0; if the doctor's release semaphore is equal to the patient's release semaphore and the doctor's and patient's semaphores are not 0, the doctor and the patient are in a follow-up relationship; The method for performing enhanced weight calculation on the scale data to obtain the final value of the scale is: assuming that the patient's scale data is X = {x1, x2, ..., x q }, the medical care scale data is Y = {y1,y2,…,y q }, the weight is w, when the x of the p-th tensor table p =y p When p =2, when x p ≠y p , w p =1, the final value of the scale is: Among them, the patient's condition is judged according to the final value of each scale; the follow-up diagnosis result can be judged according to the final value of all scales. The doctor fills in the comprehensive diagnosis result according to the final value of the scale, description of the condition, and evaluation of the treatment process, and chooses the hospital for the patient to visit or continue follow-up.

7. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 6, characterized in that: The doctor and the patient upload their ratings of symptom relief, medication efficacy, and treatment effect to the application server. The medical mobile terminal selects labels for the patient's symptoms, severity, and medication effect based on the interactive data, completes the description of the condition of this follow-up visit, and uploads it to the application server. The doctor fills out the treatment plan based on the comprehensive diagnosis results, including the next follow-up time, treatment methods, medication precautions, and nursing precautions; Patient and physician evaluations included follow-up symptom scores, follow-up treatment scores, follow-up medication scores, and standard scale scores.

8. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 6 or 7, characterized in that: The range of patient and doctor evaluation scores for treatment effects is set to L = {0, 1, 2, 3, 4, 5}, and the patient evaluation score is Among them, n represents the total number of evaluation items, x i is the score of the patient’s i-th evaluation item, and the input vector is represented as X1 = {x0, x1, x2, x3}; The range of the patient's score for the i-th evaluation item is x i ∈{0,1,2,3,4,5}, the weight is represented by W ik ={w 0k ,w 1k ,w 2k ,w 3k }, the first follow-up initialization assignment weights w 0k =1,w 1k =1,w 2k =1,w 3k =1; the weight of each follow-up patient is iteratively optimized: Among them, xi k represents the score of the i-th evaluation item of the patient's k-th follow-up, W ik is the weight of the i-th evaluation item in the k-th follow-up, W i(k-1) is the weight of the i-th evaluation item in the k-1-th follow-up, and the correction value is calculated by the correction function: Doctors' evaluation score is Among them, y j represents the score of the jth evaluation item, the input vector is represented by Y1={y0,y1,y2,y3}, and the doctor weight is W jk ={w 0k ,w 1k ,w 2k ,w 3k }, the first follow-up initialization assignment weights w 0k =1,w 1k =1,w 2k =1,w 3k =1, and then each follow-up weight is optimized iteratively: W jk represents the weight of the jth evaluation item in the kth follow-up, W j(k-1) is the weight of the jth evaluation item in the k-1th follow-up, and the correction value is calculated by the correction function:

9. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 7, characterized in that: The calculation model for the comprehensive evaluation of the effect of the treatment process by patients and doctors is Among them, h w (x, y) represents the weighted comprehensive evaluation results of patients and doctors, g k (x) represents the comprehensive evaluation score of the patient at the kth follow-up, g k (y) represents the comprehensive evaluation score of the doctor's kth follow-up visit, represents the evaluation weight of the patient's kth follow-up, represents the evaluation weight of the doctor's kth follow-up visit; the weight is optimized iteratively and in, represents the evaluation weight of the patient's k-1th follow-up, represents the evaluation weight of the doctor's k-1th follow-up. When evaluating the treatment effect at the first follow-up, the patient and the doctor are calculated with the same weight according to the average principle. After that, the evaluation weight of each follow-up is calculated by adding a correction value to the evaluation weight of the previous follow-up. The correction value is calculated by the correction function, and the correction function of the patient evaluation is: The correction function of the doctor's evaluation is 10. The extended diagnosis and treatment service system for Parkinson's disease patients according to claim 8, characterized in that: The calculation process of the evaluation score obtained by the application server through the cross-weight calculation method is as follows: The first step is to convert the scores of the evaluation items of the treatment process of Parkinson's disease patients into i As input, the patient weight W ik Perform iterative optimization calculations and use the patient evaluation score g(x i ) formula to calculate the patient evaluation score; The second step is to calculate the score y of the evaluation item of the doctor's treatment process. j As input, the doctor weight W jk Perform iterative optimization calculations based on the doctor's evaluation score g(y j ) formula to calculate the doctor evaluation score; In the third step, the patient evaluation scores and doctor evaluation scores during the patient treatment process are used as the input of the comprehensive evaluation calculation model, and the evaluation weights are adjusted by iterative optimization. and Iterative calculation is performed, and the weighted comprehensive evaluation result obtained is the comprehensive evaluation result.

Images