Intelligent hospital outpatient service system

Through the intelligent hospital outpatient system, using AI intelligent algorithms and comprehensive tree networks, intelligent initial diagnosis, auxiliary examination recommendation and treatment effect evaluation are realized, solving the problems of low efficiency of outpatient procedures and poor resource utilization in the existing technology, and improving Patient visits and doctors’ work efficiency.

CN118942652APending Publication Date: 2024-11-12HOSPITAL OF STOMATOLOGY XIAN JIAOTONG UNIVERSITY
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410960359.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing hospital outpatient system is insufficient in terms of informationization, resulting in low efficiency in outpatient procedures, long visits to patients, inability to use medical resources efficiently, and lacks intelligent consultation, examination planning and doctor matching functions.

Method used

An intelligent hospital outpatient system was designed, using AI intelligent algorithms to automatically generate a list of pre-examination information, intelligently analyze through a comprehensive tree network of diseases, generate a list of auxiliary examination suggestions, and intelligently assign the examination sequence and doctors to realize online intelligence Recommended initial diagnosis, auxiliary examination and evaluation of treatment effect.

Benefits of technology

It improves the efficiency and satisfaction of patients' medical treatment, optimizes the utilization of medical resources, reduces low-level repetitive work of doctors, and realizes intelligent outpatient process management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942652A_ABST
    Figure CN118942652A_ABST
Patent Text Reader

Abstract

The intelligent hospital outpatient service system comprises a data processing center, and a pre-examination doctor client, an examination department client, an outpatient doctor client, a patient mobile client and a database which are in data interaction with the data processing center, the system has an intelligent inquiry function, and can complete pre-examination information acquisition, intelligent analysis and suspected disease set determination online, so that online intelligent preliminary diagnosis is realized; the intelligent examination function is achieved, auxiliary examination can be applied online, the optimal examination sequence can be intelligently recommended, the examination route can be planned, and the patient can be helped to quickly complete auxiliary examination; the intelligent doctor distribution function is achieved, doctors with professional matching and short waiting time are automatically recommended for the patients, and the doctor-seeing satisfaction degree of the patients is improved; the system has an intelligent treatment management function, reminds a patient to complete a corresponding treatment course on time, collects disease information of the patient, regularly evaluates the treatment effect of the patient, feeds back the treatment effect to a reception doctor, dynamically adjusts a treatment scheme, and achieves dynamic management of the treatment process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an intelligent hospital outpatient system. Background Art

[0002] In the past decade, hospital outpatient clinics have shown the characteristics of standardized outpatient procedures, cross-disciplinary collaboration, programmed consultation content, and diversified examination methods. The outpatient process is usually standard links such as registration, waiting, consultation, examination, diagnosis, and treatment. Under the condition of limited development of information technology, this outpatient process gives full play to the doctor's judgment of the patient's medical history, symptoms, signs and other information, and then verifies the diagnosis results in combination with the results of auxiliary examinations, which is very scientific. However, with the development of medical device technology, advanced medical devices can be used to detect diseases without symptoms in advance, and auxiliary examinations play an increasingly important role. The first consultation of patients presents programmed characteristics. Doctors only conduct programmed consultations, record medical records, and issue examination orders. It is difficult to achieve diagnosis by consultation, which consumes patients' waiting time and doctors' professional diagnosis time, and it is difficult to continue to improve the efficiency of outpatient clinics. Patients arrange the order of hospital examination and inspection departments by themselves, are unfamiliar with the route, and the planning is unreasonable. Some departments are crowded, some departments are empty, the treatment order is chaotic, and medical resources cannot be used efficiently. Inaccurate triage and mismatch of professional expertise of outpatient doctors lead to the circulation of patients between different departments, which not only wastes medical resources but also reduces the efficiency of outpatient clinics. There is no effective information technology for treatment management, and the evaluation of treatment effects and adjustment of treatment plans require patients to go to the hospital repeatedly for re-examinations and follow-up visits, further aggravating the tension in medical resources.

[0003] With the development of AI technology, it is possible to consider using AI information systems to complete some pre-examination triage and treatment management work. At present, outpatient systems that combine AI information technology are still rare. The patent application with publication number CN112466450A discloses a real-time and convenient remote cloud outpatient system, which has the functions of online consultation, medical consultation, appointment consultation, examination, and medication, realizing the convenience of patient consultation. However, the system only moves the doctor's offline consultation to the online function set, but does not have the intelligent level of intelligent consultation, examination planning, matching doctors and treatment management. Summary of the invention

[0004] In order to overcome the defects of the above-mentioned prior art, the purpose of the present invention is to provide an intelligent hospital outpatient system, which uses AI intelligent algorithms to replace part of the basic work of doctors, optimize the outpatient treatment process and medical resource allocation, improve the utilization efficiency of hospital outpatient resources, reduce patients' treatment time, and improve patients' satisfaction with treatment.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent hospital outpatient system, comprising a data processing center, a patient mobile client that interacts with the data processing center, a pre-examination doctor client, and a database;

[0007] The data processing center is used to automatically generate a pre-examination information list and collect patient medical history information; to intelligently analyze a set of suspected diseases of patients; and to generate a list of auxiliary examination suggestions; the pre-examination information list is automatically generated by using a comprehensive symptom tree network, starting from the main symptom site of the patient, and using a progressive tree method to continuously generate a patient pre-examination information collection table according to the collected patient symptom information until all possible symptom terminal information is collected; the comprehensive symptom tree network is a tree structure diagram of the relationship between various diseases of various disciplines and related symptoms using a tree network method, wherein the first-level nodes are the main disease categories determined by the International Classification of Diseases (ICD for short), the second-level nodes are subcategories of each main disease category, the third-level nodes are first-level symptoms, including common disease symptom classifications, the fourth-level nodes are specific manifestation symptoms, including the main symptoms and complications of the second-level node disease, and the fifth-level nodes are the degree of symptom manifestation; wherein the first-level node and the second-level node, the third-level node and the fourth-level node, and the fourth-level node and the fifth-level node are one-to-many relationships; the second-level node and the third-level node, the fourth-level node, and the fifth-level node are many-to-many relationships;

[0008] The patient mobile client is used for patients to conduct online intelligent consultations; for patients to apply for auxiliary examinations; and for patients to pay online;

[0009] The pre-examination doctor client is used to receive the patient's auxiliary examination application; to view the patient's basic information and medical history information; to view the intelligent analysis of the patient's suspected disease set; to view the system's auxiliary examination recommendation list based on the intelligent analysis of the suspected disease set; and to review the patient's auxiliary examination application;

[0010] The database is used to store data information, including various disease symptom information, patient basic information, patient medical record information, medical expense information, drug use information, and doctor information.

[0011] The online intelligent consultation of the patient's mobile client receives the patient pre-examination information list generated by the data processing center, collects and feedbacks the patient's symptom information, receives and displays the patient's suspected disease set and auxiliary examination recommendation list generated by the data processing center;

[0012] The intelligent analysis of the suspected disease set of the patient is based on the patient's own current main symptoms, and uses the comprehensive disease tree network to reversely determine the suspected disease set including the current main symptoms;

[0013] The generating of the auxiliary examination suggestion list is to conduct auxiliary examinations of relevant parts of each disease according to the set of suspected diseases of the patient, and to compile a list of auxiliary examination suggestions.

[0014] The described progressive tree method is used to continuously generate a patient pre-examination information collection table, specifically: first generate and collect third-level node (first-level symptom) information, exclude second-level node diseases that are not related to the third-level node (first-level symptom), then generate and collect fourth-level node (specific manifestation symptoms) information related to the third-level node (first-level symptom), exclude second-level node diseases that are not related to the fourth-level node (specific manifestation symptoms), then generate and collect fifth-level node (symptom manifestation degree) information related to the fourth-level node (specific manifestation symptoms), exclude second-level node diseases that are not related to the fifth-level node (symptom manifestation degree).

[0015] The intelligent hospital outpatient system also includes an examination department client interacting with the data processing center, and the examination department client is used to display the list of patients to be examined and the estimated time to be examined; to be used for the examination department doctor to call the number; to be used for collecting the patient's examination time; to be used for the examination department doctor to check the patient's medical record information; to be used for the examination department doctor to upload the examination results;

[0016] At this time, the data processing center needs to add the following functions: automatically generate the best examination sequence; guide patients to the examination according to the best examination sequence;

[0017] At this time, the patient mobile client needs to add a new function to display the best examination sequence and guide the patient to perform auxiliary examinations;

[0018] The automatic generation of the best inspection sequence is to collect the waiting conditions of each department, divide the inspection area into departments, and evaluate the area Ar i Time required for inspection i , area Ar i Departments i,j Waiting time i,j , based on the Ar i Average waiting time per month for examination i 、RegionAr i Departments i,j Average waiting time per month for examination i,j As a standard, the calculation area Ar i Check congestion Cr i =t i / T i , area Ar i Departments i,j Check congestion Cr i,j =t i,j / T i,j , Cr i Sort by size, and determine the order of area inspection [Ar1, Ar2, ..., Ar i ], and similarly determine the area Ari Departments i,j Check the order, and form the best inspection order 1,1 ,Of 1,2 ,...,Of 1,j ],[Of 2,1 ,Of 2,2 ,...,Of 2,j ],...,[Of i,1 ,Of i,2 ,...,Of i,j ],].

[0019] The intelligent hospital outpatient system also includes an outpatient doctor client that interacts with the data processing center; the outpatient doctor client is used for doctor calling; for collecting patient waiting time; for checking the medical records of patients; for recording patient medical diagnosis information; for filling in patient treatment plans; and for applying for expert consultation.

[0020] At this time, the data processing center needs to add a new function that can intelligently assign doctors to patients based on doctor specialties, patient satisfaction, and patient waiting time.

[0021] At this time, the new function that the patient mobile client needs to add is to determine the doctor selection mode.

[0022] The intelligent allocation of receiving doctors first evaluates the professional matching degree of the receiving doctors to form a professional matching doctor set, and comprehensively evaluates the expertise, patient satisfaction, and patient waiting time of the doctors in the set, and gives priority to recommending doctors with high evaluation values. The specific algorithm is as follows: Assume that the doctor information set U i =[A i ,B i ,C i ,D i ,E i ,F i ]; among them, A i is the name of doctor i, B i For doctors in department i, C i For doctors i professional, D i For doctors i specialty, E i is the patient satisfaction of doctor i, F i is the waiting time of the patient for doctor i. For the patient with suspected disease I, the set of professional matching doctors L is obtained by screening. x ,B x ,C x ,D x ,E x ,F x ,G x ],I∈B x ,I∈Cx ,Evaluation value G x =P1D x +P2E x +P3F x , P1, P2, P3 are D x 、E x 、F x The weight value of

[0023] The data processing center can also regularly push treatment reminder information to the patient client according to the patient's treatment plan; can evaluate the patient's treatment effect; and can feedback the treatment effect evaluation results to the outpatient doctor and the patient;

[0024] The evaluation of the patient's treatment effect is to quantitatively analyze each symptom index i when the patient is diagnosed, and obtain the evaluation value Q of the symptom index i,a and the symptom index evaluation value Q of the previous treatment stage i,b Compare and combine the weights of each symptom V i , perform weighted calculation to obtain the comprehensive evaluation value K of the treatment effect i ; The specific algorithm is as follows:

[0025]

[0026] Where n is the number of symptom indicators, a is the current assessment stage, and b is the previous assessment stage.

[0027] The functions of the patient mobile client also include reminding the patient to complete the treatment task on time; and regularly collecting treatment execution information and treatment effect information.

[0028] Compared with the prior art, the present invention has at least the following beneficial effects:

[0029] 1. The present invention relies on the tree network of comprehensive symptoms and uses the progressive tree method to realize the comprehensive collection of patient pre-examination information in online interaction with patients, preliminarily determine the set of suspected diseases, and realize online intelligent initial diagnosis;

[0030] 2. The present invention intelligently generates auxiliary examination suggestions. Patients can apply for auxiliary examinations online. After the pre-examination doctor completes the review, the auxiliary examination phase will be entered during the first visit, which improves the efficiency of the patient's initial diagnosis;

[0031] 3. The present invention intelligently recommends the best inspection sequence and plans the inspection route according to the congestion of each inspection area and inspection department, which can help patients complete auxiliary inspections quickly;

[0032] 4. The present invention automatically recommends doctors with high professional expertise matching and short waiting time to patients based on the suspected disease set, doctor professional matching degree and queue congestion, thus achieving efficient and accurate triage;

[0033] 5. According to the treatment plan, the present invention reminds the patient to complete the corresponding course of treatment on time, collects the patient's symptom information, regularly evaluates the patient's treatment effect, and feeds back to the attending doctor, dynamically adjusts the treatment plan, and realizes dynamic management of the treatment process.

[0034] In summary, the present invention realizes the online and intelligent links of intelligent initial diagnosis, auxiliary examination recommendation, treatment effect evaluation and treatment management through intelligent algorithms, which not only reduces the offline consultation links of patients, but also reduces the low-level repetitive workload of doctors, and improves the efficiency of patients' visits and hospital work. The functions realized by the present invention, such as intelligent recommendation of the best examination sequence and intelligent matching of the best doctor, can make patients worry less, walk less and spend less time. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The figure is a schematic diagram of the structure of an intelligent hospital outpatient system of the present invention.

[0036] Figure 2 This is a functional module diagram of an embodiment of a patient mobile client of an intelligent hospital outpatient system of the present invention.

[0037] Figure 3 This is a schematic diagram of functional modules of an embodiment of a data processing center of an intelligent hospital outpatient system of the present invention.

[0038] Figure 4 This is a functional module diagram of an embodiment of a pre-examination doctor client of an intelligent hospital outpatient system of the present invention.

[0039] Figure 5 This is a schematic diagram of functional modules of an embodiment of an examination department client of an intelligent hospital outpatient system of the present invention.

[0040] Figure 6 This is a functional module diagram of an embodiment of an outpatient doctor client of an intelligent hospital outpatient system of the present invention.

[0041] Figure 7 This is a schematic diagram of functional modules of an embodiment of a database of an intelligent hospital outpatient system of the present invention. DETAILED DESCRIPTION

[0042] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] Embodiment 1

[0044] like Figure 1As shown, the present invention discloses an intelligent hospital outpatient system, which specifically includes a data processing center, multiple pre-examination doctor clients that interact with the data processing center, multiple patient mobile clients that interact with the data processing center, and a database that interacts with the data processing center.

[0045] like Figure 2 As shown, the patient mobile client is a client software for patients to use, which is used for patients to conduct online intelligent consultations; to apply for auxiliary examinations; and to pay online; it mainly has four functional modules: basic information, online pre-examination consultation, application for auxiliary examinations, and online payment.

[0046] The basic information module is used for patients to fill in their basic information, including personal information of patients, such as name, age, gender, contact information, etc.; medical history information, such as past disease records, allergy history, surgical history, family disease history, etc.; physical examination information, such as height, weight, blood pressure, blood sugar and other data.

[0047] The online pre-examination consultation module is used for patients to conduct online intelligent consultation. By interacting with the patient and collecting the patient's main symptoms, the data processing center automatically generates a patient pre-examination information list and completes the collection of all symptom information, and receives and displays the patient's suspected disease set and auxiliary examination recommendation list formed by the data processing center's analysis.

[0048] The auxiliary examination application module is used for patients to upload existing relevant out-of-hospital examination reports according to the auxiliary examination recommendation list, and submit auxiliary examination applications online according to their own circumstances.

[0049] The online payment module is used by patients to pay for registration, auxiliary examinations, doctor's consultations, pharmacy medication, etc., thereby saving patients' payment time.

[0050] like Figure 3 As shown, the data processing center is a software that collects information from each client software, processes data, and pushes relevant information to the corresponding client. It is used to generate a pre-examination information list based on an automatic generation algorithm for patient pre-examination information, collect patient medical records; analyze a patient's suspected disease set based on a comprehensive symptom tree network algorithm; and generate a list of examination recommendations based on a patient's suspected disease set. It mainly has three functional modules: intelligent consultation, intelligent analysis, and auxiliary examination recommendations.

[0051] The intelligent consultation module mainly includes two steps:

[0052] Step 1: Construct a tree network of complex symptoms. Use the tree network method to construct a tree structure diagram of the relationship between various diseases and related symptoms in various disciplines. The first-level nodes are the main disease categories determined by the International Classification of Diseases (ICD for short), the second-level nodes are the subcategories of each major disease category, the third-level nodes are the first-level symptoms, which are common disease symptom classifications, the fourth-level nodes are specific manifestation symptoms, mainly the main symptoms and complications of the second-level node diseases, and the fifth-level nodes are the degree of symptom manifestation. Among them, the first-level node and the second-level node, the third-level node and the fourth-level node, and the fourth-level node and the fifth-level node are one-to-many relationships. The second-level node and the third-level node, the fourth-level node, and the fifth-level node are many-to-many relationships.

[0053] Step 2: Automatically generate a pre-examination information list and collect patient symptom information. Using a comprehensive symptom tree network, starting from the main symptom site of the patient, based on the collected patient symptom information, a progressive tree method is used to continuously generate a patient pre-examination information collection table until all possible symptom terminal information is collected. The algorithm for continuously generating a patient pre-examination information collection table using the progressive tree method is as follows: First, generate and collect third-level node (first-level symptom) information, excluding second-level node diseases that are not related to the third-level node (first-level symptom), then generate and collect fourth-level node (specific manifestation symptoms) information that is related to the third-level node (first-level symptom), excluding second-level node diseases that are not related to the fourth-level node (specific manifestation symptoms), then generate and collect fifth-level node (symptom manifestation degree) information that is related to the fourth-level node (specific manifestation symptoms), excluding second-level node diseases that are not related to the fifth-level node (symptom manifestation degree).

[0054] The intelligent analysis module is used to intelligently analyze the suspected disease set of the patient, and reversely determine the suspected disease set including the current main symptoms by using the comprehensive symptom tree network according to the patient's own current main symptoms.

[0055] The auxiliary examination suggestion module is used to generate an auxiliary examination suggestion list. According to the patient's suspected disease set, auxiliary examinations of relevant parts are performed on each disease one by one, and the auxiliary examination suggestion list is summarized.

[0056] like Figure 4 As shown in the figure, the pre-examination doctor client is used to receive the patient's auxiliary examination application; to check the patient's basic information and medical record information; to check the intelligent analysis of the patient's suspected disease set; to check the system's auxiliary examination suggestion list based on the intelligent analysis of the suspected disease set; and to review the patient's auxiliary examination application. There are mainly four functional modules: checking the patient's medical record information, checking the intelligent analysis situation, checking the auxiliary examination suggestion, and reviewing the auxiliary examination application.

[0057] The module for reviewing patient medical record information is used for the pre-examination doctor to review the patient's basic information and main symptom information, as well as the relevant auxiliary examination reports uploaded by the patient.

[0058] The intelligent analysis situation review module is used for the pre-examination doctor to review the system's analysis report on various symptom information of the patient and possible disease collection information.

[0059] The module for reviewing auxiliary examination suggestions is used for the pre-examination doctor to review the auxiliary examination suggestion list obtained by the system in combination with the set information of possible diseases of the patient.

[0060] The auxiliary examination application review module is used for the pre-examination doctor to review the auxiliary examination application submitted by the patient and conduct review.

[0061] like Figure 7 As shown, the database is used to store various types of system data, mainly including various disease symptom information databases, patient basic information databases, patient medical record information databases, medical expense information databases, drug use information databases, doctor information databases, etc. There are mainly 6 functional modules: symptom information database, patient information database, medical expense information database, drug use information database, and doctor information database.

[0062] The disease information database is a database used to store the main disease categories and subcategories defined in the International Classification of Diseases, common disease symptom classifications, specific symptoms and symptom severity, as well as their interrelationships.

[0063] The patient basic information database is a database used to store the basic information of registered patients, medical history information, suspected disease collection, auxiliary examination recommendation list, auxiliary examination information, doctor diagnosis information, and treatment process information.

[0064] The medical expense information database is mainly used to store information such as patient registration, outpatient visits, auxiliary examinations, treatments, drug purchases, and hospital outpatient-related expenditure information.

[0065] The drug usage information database is mainly used to store information such as drug shipment, replenishment, and patient medication.

[0066] The doctor information database module is mainly used to store databases such as basic information, professional information, clinical information, and scientific research information of doctors of various specialties.

[0067] Embodiment 2

[0068] like Figure 1 As shown, the present invention discloses an intelligent hospital outpatient system, which specifically includes a data processing center, multiple pre-examination doctor clients that interact with the data processing center for data, multiple patient mobile clients that interact with the data processing center for data, and a database that interacts with the data processing center. Compared with the first embodiment, multiple examination department clients that interact with the data processing center for data and multiple outpatient doctor clients that interact with the data processing center for data are added.

[0069] like Figure 5As shown, the examination department client is a client software used by doctors in the examination department, which is used to display the list of patients to be examined and the estimated time for examination outside the department; to be used by doctors in the examination department to call the number and update the patient's examination evaluation time at the same time; to be used by doctors in the examination department to check the patient's medical records; to be used by doctors in the examination department to upload examination results. There are mainly four functional modules: patients to be examined, doctors calling the number, patient information, and examination results.

[0070] The patient waiting module is used for doctors in the examination department to check the list of patients to be examined and the waiting time. At the same time, the list of patients to be examined and the waiting time are displayed on the screen outside the examination department. The waiting time is calculated by accumulating the examination parts and examination methods of each patient in the queue and the average examination time of the same auxiliary examination in the past;

[0071] The doctor calling module is used to check whether the doctor in the department calls the number of the patient and whether the screen outside the department synchronously displays the serial number and name of the patient being treated. The system synchronously collects the actual treatment time of the last patient and includes it in the waiting time database;

[0072] The patient information module is used for doctors in the examination department to check the basic information and related medical records of the patients;

[0073] The examination result module is used for doctors in the examination department to view the auxiliary examination results and upload the auxiliary examination conclusions and suggestions.

[0074] like Figure 6 As shown, the outpatient doctor client is a client software used by outpatient department doctors, which is used for doctor calling; for checking the medical records of patients; for recording the medical diagnosis information of patients; for filling in the patient treatment plan; for applying for expert consultation. It mainly has 6 functional modules: waiting patients, doctor calling, patient information, medical diagnosis, treatment plan, and expert consultation.

[0075] The waiting patient module is used by outpatient doctors to check the waiting patient list and waiting evaluation time, and the waiting patient list, waiting evaluation time and other information are displayed on the screen outside the outpatient department. The patient waiting evaluation time is calculated by accumulating the suspected disease of each patient in the queue and the average outpatient time of similar suspected diseases in the past.

[0076] The doctor calling module is used for outpatient doctors to call the patients, and the screen outside the outpatient department will synchronously display the serial number and name of the patient being treated. The system will synchronously collect the actual time of the last patient's visit and include it in the waiting time database.

[0077] The patient information module is used by outpatient doctors to review the basic information and relevant medical records of the patients, as well as the examination results, conclusions and suggestions of the auxiliary examination departments.

[0078] The medical diagnosis module is used by outpatient doctors to fill in the diagnosis conclusions of the patients.

[0079] The treatment plan module is used for outpatient doctors to fill in treatment plans and push them to the data processing center for treatment process management and to the patient's mobile client for patients to review; it is used to revise the treatment plan based on the treatment effect evaluation results of the treatment process management and push them to the data processing center and the patient's mobile client.

[0080] The expert consultation module is used for outpatient doctors to apply for online consultation with relevant experts; for pushing basic patient information, relevant medical record information, and auxiliary examination related information to the outpatient doctor client of relevant experts; and for viewing expert consultation opinions.

[0081] like Figure 2 As shown, in this embodiment, when the system expands the examination department client and the outpatient doctor client, the patient mobile client adds three functional modules: guiding auxiliary examinations, assigning attending doctors, and managing treatment processes.

[0082] The guided auxiliary examination module receives and displays the best examination sequence and planned route generated by the data processing center based on the auxiliary examination application reviewed by the pre-examination doctor, and guides the patient to complete the auxiliary examination quickly; after the auxiliary examination report comes out, the patient can check the auxiliary examination report by himself.

[0083] The module for assigning doctors to see patients is used to receive and display a set of professional matching doctors. Patients can choose their own doctors or choose the doctor with the highest evaluation value recommended by the system.

[0084] The treatment process management module is used to remind patients to complete the corresponding treatment on time according to the outpatient doctor's treatment plan; regularly remind patients to evaluate the treatment effect, collect patient symptom information, send it to the data processing center for treatment effect evaluation, and receive and display the treatment effect evaluation results.

[0085] like Figure 3 As shown, in this embodiment, when the system expands the examination department client and the outpatient doctor client, the data processing center needs to add new functions, such as being able to automatically generate the best examination sequence; being able to guide patients to the examination according to the best examination sequence; being able to intelligently assign doctors according to the doctor's specialty, patient satisfaction, and patient waiting time; being able to push reminder information to the corresponding patients on time according to the patient's treatment plan, regularly evaluate the treatment effect, provide feedback to patients and doctor clients, and implement dynamic treatment management. Four new functional modules are added: examination sequence planning, guided examination, intelligent doctor assignment, and intelligent treatment management.

[0086] The inspection sequence planning module is used to generate the best inspection sequence and inspection planning route. i Time required for inspection i , area Ar i Departments i,j Waiting time i,j , based on the Ar i Average waiting time per month for examination i 、RegionAr i Departments i,j Average waiting time per month for examination i,j As a standard, the calculation area Ar i Check congestion Cr i =t i / T i , area Ar i Departments i,j Check congestion Cr i,j =t i,j / T i,j , Cr i Sort by size, and determine the order of area inspection [Ar1, Ar2, ..., Ar i ], and similarly determine the area Ar i Departments i,j Check the order, and form the best inspection order 1,1 ,Of 1,2 ,...,Of 1,j ],[Of 2,1 ,Of 2,2 ,...,Of 2,j ],...,[Of i,1 ,Of i,2 ,...,Of i,j ]].

[0087] The guided examination module actively generates a planned route for the patient to go to the examination department according to the patient's current location, and feeds it back to the patient's mobile client, and also feeds back the waiting evaluation time of the examination department to the patient's mobile client.

[0088] The intelligent doctor allocation module first evaluates the professional matching degree of the attending doctors to form a professional matching doctor set, and then comprehensively evaluates the expertise, patient satisfaction, and patient waiting time of the doctors in the set, and gives priority to recommending doctors with high evaluation values. The specific algorithm is as follows: Assume that the doctor information set U i =[A i ,B i ,C i ,D i ,Ei ,F i ]. Among them, A i is the name of doctor i, B i For doctors in department i, C i For doctors i professional, D i For doctors i specialty, E i is the patient satisfaction of doctor i, F i is the waiting time for the patient to see doctor i. For the patient with suspected disease I, the set of professional matching doctors L is obtained by screening. x ,B x ,C x ,D x ,E x ,F x ,G x ],I∈B x ,I∈C x ,Evaluation value G x =P1D x +P2E x +P3F x , P1, P2, P3 are D x 、E x 、F x The weight value of

[0089] The intelligent treatment management module is used to send reminder information to the corresponding patient mobile client on time according to the outpatient doctor's treatment plan, or send text messages to the patient's registered mobile phone number to remind the patient to complete the corresponding treatment, collect symptom information through the patient's mobile client, and regularly evaluate the patient's treatment effect. To evaluate the patient's treatment effect, each symptom indicator i is quantitatively analyzed when the patient is diagnosed, and the evaluation value Q of the symptom indicator is obtained. i,a and the symptom index evaluation value Q of the previous treatment stage i,b Compare and combine the weights of each symptom V i , perform weighted calculation to obtain the comprehensive evaluation value K of the treatment effect i , and feedback is sent to the patient's mobile client and the outpatient doctor's client. If the treatment effect does not meet the expected effect, the outpatient doctor will dynamically adjust the treatment plan. The specific algorithm is as follows:

[0090]

[0091] Where n is the number of symptom indicators, a is the current assessment stage, and b is the previous assessment stage.

[0092] The patient mobile client can also remind the patient to complete treatment tasks on time and regularly collect treatment execution information and treatment effect information.

[0093] In summary, the present invention relies on a comprehensive symptom tree network and uses a progressive tree method to realize comprehensive collection of patient pre-examination information in online interaction with patients, preliminarily determine a set of suspected diseases, and realize online intelligent initial diagnosis; intelligently generate a list of auxiliary examination suggestions, and patients apply for auxiliary examinations online. After the pre-examination doctor completes the review, the first visit will enter the auxiliary examination link, which improves the efficiency of the patient's initial diagnosis; according to the congestion of each inspection area and inspection department, the best inspection sequence is intelligently recommended, and the inspection route is planned, which can help patients complete auxiliary examinations quickly; the present invention automatically recommends doctors with high professional expertise matching and short waiting time to patients based on the doctor's professional matching, patient satisfaction and queue congestion, to achieve efficient and accurate triage; according to the treatment plan, the patient is reminded to complete the corresponding course of treatment on time, the patient's symptom information is collected, the patient's treatment effect is regularly evaluated, and the feedback is given to the attending doctor, the treatment plan is dynamically adjusted, and dynamic management of the treatment process is achieved.

[0094] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. An intelligent hospital outpatient system, characterized in that: It includes a data processing center, a patient mobile client, a pre-examination doctor client and a database that interact with the data of the data processing center; The data processing center is used to automatically generate a pre-examination information list and collect patient medical record information; Used for intelligent analysis of a patient's suspected disease set; used for generating a list of auxiliary examination recommendations; the automatic generation of the pre-examination information list is to use a comprehensive symptom tree network, starting from the patient's main symptom site, and based on the collected patient symptom information, to continuously generate a patient pre-examination information collection table using a progressive tree method until all possible symptom terminal information is collected; the comprehensive symptom tree network is a tree structure diagram that uses a tree network method to construct a connection between various disciplines and various diseases and related symptoms, the first-level node is the main disease category determined by the International Classification of Diseases (ICD for short), the second-level node is the subcategory of each main disease category, the third-level node is the first-level symptom, including common disease symptom classifications, the fourth-level node is the specific manifestation symptoms, including the main symptoms and complications of the second-level node disease, and the fifth-level node is the degree of symptom manifestation; among them, the first-level node and the second-level node, the third-level node and the fourth-level node, and the fourth-level node and the fifth-level node are one-to-many relationships; the second-level node and the third-level node, the fourth-level node, and the fifth-level node are many-to-many relationships; The patient mobile client is used for patients to conduct online intelligent consultations; for patients to apply for auxiliary examinations; and for patients to pay online; The pre-examination doctor client is used to receive the patient's auxiliary examination application and to check the patient's basic information and medical record information; Used to check the suspected disease set of patients analyzed by intelligent analysis; used to check the auxiliary examination recommendation list based on the system's suspected disease set analyzed by intelligent analysis; used to review the patient's auxiliary examination application; The database is used to store data information, including various disease symptom information, patient basic information, patient medical record information, medical expense information, drug use information, and doctor information.

2. The intelligent hospital outpatient system according to claim 1, characterized in that: The online intelligent consultation of the patient's mobile client receives the patient pre-examination information list generated by the data processing center, collects and feedbacks the patient's symptom information, receives and displays the patient's suspected disease set and auxiliary examination recommendation list generated by the data processing center; The intelligent analysis of the suspected disease set of the patient is based on the patient's own current main symptoms, and uses the comprehensive disease tree network to reversely determine the suspected disease set including the current main symptoms; The generating of the auxiliary examination suggestion list is to conduct auxiliary examinations of relevant parts of each disease according to the set of suspected diseases of the patient, and to compile the auxiliary examination suggestion list.

3. The intelligent hospital outpatient system according to claim 1, characterized in that: The described progressive tree method is used to continuously generate a patient pre-examination information collection table, specifically: first, generate and collect third-level node, i.e., first-level symptom information, and exclude second-level node diseases that are not related to the third-level node, i.e., first-level symptoms; then generate and collect fourth-level node, i.e., specific manifestation symptom information, which is related to the third-level node, and exclude second-level node diseases that are not related to the fourth-level node, i.e., specific manifestation symptom information; then generate and collect fifth-level node, i.e., symptom manifestation degree information, which is related to the fourth-level node, i.e., specific manifestation symptom information, and exclude second-level node diseases that are not related to the fifth-level node, i.e., symptom manifestation degree information.

4. The intelligent hospital outpatient system according to claim 1, characterized in that: The intelligent hospital outpatient system also includes an examination department client that interacts with the data processing center. The examination department client is used to display a list of patients to be examined and an estimated time for examination; and is used to call the examination department doctor; Used to collect the patient's waiting time for examination; It is used by doctors in the examination department to check the patient's medical records; it is used by doctors in the examination department to upload the examination results; At this time, the data processing center needs to add the following functions: automatically generate the best examination sequence; guide patients to the examination according to the best examination sequence; At this time, the patient mobile client needs to add a new function to display the best examination sequence and guide the patient to perform auxiliary examinations.

5. The intelligent hospital outpatient system according to claim 4, characterized in that: The automatic generation of the best inspection sequence is to collect the waiting conditions of each department, divide the inspection area into departments, and evaluate the area Ar i Time required for inspection i , area Ar i Departments i,j Waiting time i,j , based on the Ar i Average waiting time per month for examination i 、RegionAr i Departments i,j Average waiting time per month for examination i,j As a standard, the calculation area Ar i Check congestion Cr i =t i / T i , area Ar i Departments i,j Check congestion Cr i,j =t i,j / T i,j , Cr i Sort by area from small to large and determine the area inspection order [Ar1, Ar2, ..., Ar i ], and similarly determine the area Ar i Departments i,j Inspection sequence, forming the best inspection sequence [[Of 1,1 ,Of 1,2 ,…,Of 1,j ],[Of 2,1 ,Of 2,2 ,…,Of 2,j ],…,[Of i,1 ,Of i,2 ,…,Of i,j ]]。 6. The intelligent hospital outpatient system according to claim 4, characterized in that: The intelligent hospital outpatient system also includes an outpatient doctor client that interacts with the data processing center. The outpatient doctor client is used to call doctors, collect patient waiting time, check medical records of patients, record patient medical diagnosis information, fill in patient treatment plans, and apply for expert consultation. At this time, the data processing center needs to add a new function that can intelligently assign doctors to patients based on doctor specialties, patient satisfaction, and patient waiting time. At this time, the new function that the patient mobile client needs to add is to determine the doctor selection mode.

7. The intelligent hospital outpatient system according to claim 6, characterized in that: The intelligent allocation of receiving doctors first evaluates the professional matching degree of the receiving doctors to form a professional matching doctor set, and comprehensively evaluates the expertise, patient satisfaction, and patient waiting time of the doctors in the set, and gives priority to recommending doctors with high evaluation values. The specific algorithm is as follows: Assume that the doctor information set U i =[A i , B i , C i , D i , E i , F i ]; among them, A i is the name of doctor i, B i For doctors in department i, C i For doctors i professional, D i For doctors i specialty, E i is the patient satisfaction of doctor i, F i is the waiting time of the patient for doctor i. For the patient with suspected disease I, the set of professional matching doctors L is obtained by screening. x , B x , C x , D x , E x , F x , G x ],I∈B x , I∈C x , the evaluation value G x =P1D x +P2E x +P3F x , P1, P2, P3 are D x 、E x 、F x The weight value of 8. The intelligent hospital outpatient system according to claim 6, characterized in that: The data processing center can push treatment reminder information to the patient's mobile client on time according to the patient's treatment plan; can regularly evaluate the patient's treatment effect; and can feed back the treatment effect evaluation results to the outpatient doctor's client and the patient's mobile client.

9. The intelligent hospital outpatient system according to claim 8, characterized in that: The evaluation of the patient's treatment effect is to quantitatively analyze each symptom index i when the patient is diagnosed, and obtain the evaluation value Q of the symptom index i,a and the symptom index evaluation value Q of the previous treatment stage i,b Compare and combine the weights of each symptom V i , perform weighted calculation to obtain the comprehensive evaluation value K of the treatment effect i ; The specific algorithm is as follows: Where n is the number of symptom indicators, a is the current assessment stage, and b is the previous assessment stage.

10. The intelligent hospital outpatient system according to claim 9, characterized in that: The patient mobile client can also remind the patient to complete the treatment task on time and is used to regularly collect treatment execution information and treatment effect information.

Citation Information

Cited By

  • Medical service pushing method and pushing system based on big data analysis

    CN119360493A

  • Intelligent treatment method, system and equipment for AI virtual human accompanying diagnosis and medium

    CN119626483A