Medical auxiliary diagnosis method, device and equipment and storage medium
By combining machine learning models and medical knowledge bases, the generation and evaluation of medical diagnostic results are solved, and the shortcomings of insufficient model generalization capabilities and credibility assessment of diagnostic results in the prior art are achieved, and more accurate and efficient medical-assisted diagnosis is achieved, reducing the risk of The burden of doctors and improves the quality of medical services.
Patent Information
- Application Number
- CN202411307899.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-19
- Publication Date
- 2025-01-07
AI Technical Summary
When faced with the diversity and complexity of medical data, the model's generalization ability and robustness are insufficient, and the lack of effective credibility assessment mechanism for diagnostic results, resulting in misdiagnosis and missed diagnosis, which increases doctors The burden.
Using machine learning models (including decision trees, support vector machines, neural networks and deep learning models) combined with medical knowledge base, analyzing the basic information and clinical data of patients, generate preliminary diagnostic results, and based on confidence and medical knowledge base The correlation score provides multiple diagnostic options and treatment recommendations, which are finally confirmed and optimized by the doctor.
It improves the accuracy and efficiency of medical diagnosis, reduces the burden on doctors, provides more reliable diagnostic results, and provides early warning and response strategies for future disease development through predictive models, improving the quality of medical services.
Smart Images
Figure CN119274776A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to medical auxiliary diagnosis methods, devices, equipment and storage media. Background Art
[0002] With the rapid development of medical technology and the continuous advancement of information technology, the amount and complexity of data in the medical diagnosis process have increased significantly. Traditional medical diagnosis mainly relies on the doctor's experience and subjective judgment, which is not only time-consuming and labor-intensive, but also difficult to guarantee the accuracy and efficiency of diagnosis when facing complex cases. Especially in the case of tight medical resources, the burden on doctors is increased, which can easily lead to misdiagnosis and missed diagnosis, thus affecting the treatment effect of patients.
[0003] In this context, medical auxiliary diagnosis methods based on artificial intelligence and big data technologies have emerged. These technologies use machine learning and deep learning models to automatically identify and analyze patients' conditions and provide preliminary diagnosis results and treatment recommendations through learning and training of large amounts of medical data. This can not only improve the accuracy and efficiency of diagnosis, but also reduce the burden on doctors and improve the quality of medical services.
[0004] Although the existing medical auxiliary diagnosis methods have solved the above problems to a certain extent, they still have some shortcomings. First, the diversity and complexity of medical data place high demands on the diagnostic model, and the generalization ability and robustness of the existing model need to be improved. Secondly, the updating and maintenance of the medical knowledge base is a heavy task, and how to incorporate the latest medical research results into the diagnostic system in a timely manner is an important challenge. In addition, the credibility and reliability evaluation of the diagnostic results are also weak links in the existing technology, and the lack of an effective evaluation mechanism may lead to misjudgment of the diagnostic results.
[0005] In order to meet these challenges, the present invention provides an innovative medical auxiliary diagnosis method, device, equipment and storage medium. Summary of the invention
[0006] The purpose of the present invention is to solve the technical problems raised in the above background technology.
[0007] The present invention adopts the following technical solutions: a medical auxiliary diagnosis method, device, equipment and storage medium, the method comprising:
[0008] Obtaining medical data to be diagnosed, the medical data including basic information and clinical data of the patient, the basic information including the patient's name, gender, age, past medical history, family medical history, lifestyle and allergy history, etc., and the clinical data including symptom description, physical examination results, laboratory test results and imaging examination results, etc.;
[0009] Based on the medical data, a preliminary diagnosis result is generated using a machine learning model, wherein the machine learning model includes a decision tree, a support vector machine, a neural network, and a deep learning model, and the model is trained with a large amount of annotated data and can accurately identify and analyze the symptoms and signs of various diseases;
[0010] Matching the preliminary diagnosis result with a preset medical knowledge base to generate multiple possible diagnosis options, wherein the medical knowledge base includes diagnostic criteria for common diseases, clinical characteristics of uncommon diseases, and the latest medical research results;
[0011] Ranking each diagnosis option and giving a corresponding credibility score, wherein the ranking is based on the confidence of the diagnosis model and the relevance score of the medical knowledge base;
[0012] Select the best diagnosis result according to the credibility score and preset medical rules, and generate corresponding treatment suggestions, including drug treatment plans, non-drug treatment plans, lifestyle adjustment suggestions and further examination suggestions;
[0013] The diagnosis results and treatment recommendations are fed back to the doctor for reference and further confirmation. The doctor can adjust and optimize the diagnosis results and treatment recommendations based on his or her own clinical experience and the actual situation of the patient.
[0014] In one embodiment, the step of obtaining the medical data to be diagnosed includes:
[0015] Obtaining the patient's electronic health record (EHR) data, including the patient's medical history, past medical records, inspection and quarantine records, and drug use records;
[0016] Obtain patients' real-time monitoring data, including physiological indicators such as blood pressure, heart rate, blood sugar, body temperature and oxygen saturation. These data are collected and transmitted in real time through wearable devices or hospital monitoring equipment;
[0017] Obtain the patient's laboratory test data, including blood tests, urine tests, imaging tests (such as X-ray, CT, MRI, etc.) and other special examination results for specific diseases. These data are provided by the hospital's laboratory or imaging department.
[0018] In one embodiment, the machine learning model is a deep neural network model, which is pre-trained with a large amount of labeled data to improve diagnostic accuracy;
[0019] The training data includes patient data of different age groups, genders and races, covering a variety of common and rare diseases, to ensure the wide applicability and robustness of the model.
[0020] In one embodiment, the medical knowledge base includes the following:
[0021] The diagnostic criteria for common diseases are formulated based on the International Classification of Diseases (ICD) and medical guidelines of various countries;
[0022] Symptoms and characteristics of different diseases, including causes, pathological mechanisms, clinical manifestations, complications and prognosis;
[0023] Treatment plans and drug use guidelines for different diseases, including standard treatment plans, individualized treatment plans, and drug indications, contraindications, dosage, and adverse reactions;
[0024] The latest medical research results and clinical trial data, including the latest published research papers, clinical trial results and discussion results of medical conferences, in order to timely update and supplement the content of the medical knowledge base.
[0025] In one embodiment, the credibility score is calculated based on the following factors:
[0026] The confidence level of the machine learning model’s diagnostic results, which indicates the model’s confidence in a certain diagnostic result;
[0027] Statistical data of similar cases in the medical knowledge base, including the diagnosis results and treatment effects of similar cases, are inferred based on historical data;
[0028] Individual patient characteristics and medical history, including age, gender, medical history, family history, lifestyle, etc., to consider the impact of individual differences on disease diagnosis;
[0029] Environmental and epidemiological factors, including seasonal epidemics, regional disease distribution, etc., modify and supplement the diagnostic results.
[0030] In one embodiment, the generated diagnostic result is judged and predicted, and the specific steps include:
[0031] After obtaining the preliminary diagnosis results, compare and analyze them with historical diagnosis data to evaluate their accuracy and reliability;
[0032] Combine current medical data with historical data to use predictive models to predict possible disease progression and treatment effects;
[0033] Assess the credibility of the prediction results and adjust the diagnosis and treatment plans based on the evaluation results;
[0034] Provides detailed advice on the likelihood of future disease progression and coping strategies to help doctors conduct prevention and early intervention.
[0035] A medical auxiliary diagnosis device, comprising:
[0036] A data acquisition module is used to obtain basic information and clinical data of patients. The data acquisition module is connected to data sources such as hospital information system (HIS), laboratory information system (LIS) and wearable devices to realize automatic data collection and transmission;
[0037] A diagnostic model module, used to generate preliminary diagnostic results based on the medical data, wherein the diagnostic model module integrates a variety of machine learning and deep learning algorithms and performs diagnostic analysis by calling trained models;
[0038] A matching module, used to match the preliminary diagnosis result with the medical knowledge base to generate multiple possible diagnosis options, wherein the matching module screens out possible diagnosis results by comparing the output of the diagnosis model with the standards in the knowledge base;
[0039] A ranking module is used to rank the various diagnostic options and give corresponding credibility scores, wherein the ranking module comprehensively considers the confidence of the model and the relevance score of the knowledge base to generate a comprehensive score;
[0040] A selection module is used to select the best diagnosis result according to the credibility score and the preset medical rules, and generate corresponding treatment suggestions. The selection module automatically selects and generates the best diagnosis and treatment plan according to the score and the preset rules;
[0041] The feedback module is used to feed back the diagnosis results and treatment suggestions to the doctor, and push them to the doctor through the doctor's workstation, mobile terminal or email for reference and further confirmation.
[0042] A medical auxiliary diagnosis device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program;
[0043] The memory includes a storage area for storing patient data, diagnostic models, medical knowledge base and diagnostic results. When the processor executes the computer program, it calls the data and models in the memory to complete data processing, diagnostic analysis and result feedback.
[0044] A computer storage medium having a computer program stored thereon, wherein the steps of the above method are implemented when the computer program is executed by a processor, wherein the computer storage medium comprises a hard disk, a solid-state drive, a flash memory, an optical disk or a magnetic disk, and the computer program comprises instructions and algorithms for implementing data collection, model training, diagnostic analysis, result matching, sorting and feedback.
[0045] A computer system for a method for medical auxiliary diagnosis, comprising:
[0046] processor;
[0047] A memory storing a computer program, wherein when the computer program is executed by the processor, the processor executes the steps of the above method, and the computer system is connected to data sources such as a hospital information system, a laboratory information system, and a wearable device through a network interface to achieve real-time data collection, processing, and feedback;
[0048] The user interface module is used for the interaction between doctors and the system, displays diagnostic results and treatment recommendations, and provides feedback and adjustment functions. The user interface module can be a graphical user interface (GUI), command line interface (CLI) or voice interaction interface (VUI) to facilitate doctors' operation and use.
[0049] Compared with the prior art, the advantages and positive effects of the present invention are:
[0050] The present invention aims to improve the intelligence level and practicality of the medical auxiliary diagnosis system, improve the quality of medical services, reduce the pressure on medical resources, and provide patients with better quality and more efficient medical services through scientific methods and technical means. By comprehensively utilizing the patient's basic information, clinical data and laboratory test results, combined with advanced machine learning and deep learning technologies, accurate and reliable diagnosis results are generated. At the same time, based on the preset medical knowledge base and historical diagnostic data, the diagnosis results are matched and evaluated, and a multi-dimensional credibility score is provided to help doctors make more accurate diagnostic decisions. In addition, the present invention also includes the prediction and judgment of the diagnosis results, which can provide effective early warning and response strategies for future disease development. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 A flow chart of a medical auxiliary diagnosis method is proposed for the present invention;
[0052] Figure 2 The present invention provides a structural block diagram of a medical auxiliary diagnosis device;
[0053] Figure 3 A system diagram of a medical auxiliary diagnosis system is provided for the present invention;
[0054] Figure 4 A training flow chart of a medical auxiliary diagnosis model is proposed for the present invention;
[0055] Figure 5 A flow chart for matching the medical auxiliary diagnosis model with the medical knowledge base is proposed for the present invention;
[0056] Figure 6 A flowchart for sorting and scoring medical auxiliary diagnosis results is proposed for the present invention;
[0057] Figure 7 A flow chart for judging and predicting diagnostic results is proposed for the present invention. DETAILED DESCRIPTION
[0058] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described below in conjunction with the accompanying drawings and embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments of the following disclosure.
[0060] Example
[0061] like Figure 1 As shown, the present invention provides a medical auxiliary diagnosis method, comprising the following steps:
[0062] Step 1: Obtain the medical data to be diagnosed;
[0063] Obtain the patient's basic information, including name, gender, age, past medical history, family medical history, living habits and allergy history, etc. This information can be automatically extracted through the hospital information system (HIS) or manually entered by the doctor.
[0064] Obtain the patient's clinical data, including symptom descriptions (such as cough, fever, headache, etc.), physical examination results (such as blood pressure, heart rate, body temperature, etc.), laboratory test results (such as blood tests, urine tests, imaging tests such as X-rays, CT, MRI, etc.). These data can be automatically extracted through the laboratory information system (LIS) and the imaging system (PACS).
[0065] Step 2: Generate preliminary diagnosis results using machine learning models;
[0066] Select an appropriate machine learning model, such as a deep neural network model (DNN), and pre-train the model with training data covering patient data of different age groups, genders, and races, including case data of various common and rare diseases.
[0067] The acquired medical data is input into the model, and the model automatically generates preliminary diagnosis results based on the learned features. The model can be implemented using deep learning frameworks such as TensorFlow or PyTorch.
[0068] Step 3: Match the preset medical knowledge base and generate diagnosis options;
[0069] After the initial diagnosis is generated, it is matched with the preset medical knowledge base, which stores a large number of disease diagnostic criteria, symptoms, treatment plans and the latest medical research results.
[0070] Through the matching process, the system generates multiple possible diagnosis options, each based on data from the medical knowledge base.
[0071] Step 4: Sort and score the diagnostic options;
[0072] The diagnostic options are ranked according to the confidence of the diagnostic model and the relevance score of the medical knowledge base. The confidence score indicates the confidence of the model in a certain diagnosis result, and the relevance score is calculated based on similar case data in the knowledge base.
[0073] A composite confidence score was generated reflecting the reliability and accuracy of each diagnostic option.
[0074] Step 5: Select the best diagnosis and generate treatment recommendations;
[0075] The optimal diagnosis is selected based on the comprehensive credibility score and preset medical rules, which may include treatment priorities, individual patient differences, and existing medical guidelines.
[0076] Generate corresponding treatment recommendations, including drug treatment plans (such as drug name, dosage, usage, etc.), non-drug treatment plans (such as physical therapy, psychotherapy, etc.), lifestyle adjustment recommendations (such as diet, exercise, smoking cessation, etc.) and further examination recommendations (such as re-examination of blood, imaging examinations, etc.).
[0077] Step 6: Feedback on diagnosis results and treatment recommendations;
[0078] The diagnosis results and treatment suggestions are fed back to the doctor through the doctor's workstation, mobile terminal or email. The system will generate a detailed diagnosis report for the doctor's reference and further confirmation.
[0079] Doctors can adjust and optimize the diagnostic results and recommendations based on their own clinical experience and the patient's actual situation, and ultimately determine the treatment plan.
[0080] Step 7: Judge and predict the diagnosis results;
[0081] After obtaining the preliminary diagnosis results, they are compared and analyzed with historical diagnosis data to evaluate their accuracy and reliability. Historical data can include the patient's previous diagnosis records and diagnosis data of other similar cases.
[0082] Combining current medical data with historical data, use predictive models (such as time series prediction models or Bayesian networks) to predict possible disease progression and treatment effects.
[0083] The credibility of the prediction results is evaluated, and the diagnosis and treatment plans are adjusted based on the evaluation results, providing detailed suggestions on the possibility of future disease development and response strategies.
[0084] In one embodiment, Figure 2 As shown, a medical auxiliary diagnosis device is provided, comprising the following modules:
[0085] Data acquisition module: used to obtain basic information and clinical data of patients. The data acquisition module connects with data sources such as hospital information system (HIS), laboratory information system (LIS) and wearable devices to realize automatic data collection and transmission. This module can exchange data with various systems through API interface to ensure the real-time and accuracy of data.
[0086] Diagnostic model module: Integrates multiple machine learning and deep learning algorithms to perform diagnostic analysis by calling trained models. The diagnostic model module can use deep neural network models based on TensorFlow or PyTorch to analyze input medical data and generate preliminary diagnostic results.
[0087] Matching module: used to match the preliminary diagnosis results with the medical knowledge base to generate multiple possible diagnosis options. The matching module screens out possible diagnosis results by comparing the output of the diagnosis model with the standards in the knowledge base. This module can use natural language processing (NLP) technology to match the diagnosis results with the text data in the knowledge base.
[0088] Sorting module: used to sort the various diagnostic options and give the corresponding credibility scores. The sorting module comprehensively considers the confidence of the model and the relevance score of the knowledge base to generate a comprehensive score. This module can use a weighted scoring algorithm to weight different scoring factors to generate the final credibility score.
[0089] Selection module: used to select the best diagnosis results based on the credibility score and preset medical rules, and generate corresponding treatment recommendations. The selection module automatically selects and generates the best diagnosis and treatment plan based on the score and preset rules. This module can use a rule engine (such as Drools) to implement the application and execution of medical rules.
[0090] Feedback module: used to provide feedback on diagnosis results and treatment suggestions to doctors. Diagnosis results and treatment suggestions are pushed to doctors through doctor workstations, mobile terminals or emails for their reference and further confirmation. The feedback module can also provide doctors with the function of providing feedback and adjusting diagnosis results and suggestions, and record the doctor's modifications and final confirmation results.
[0091] In one embodiment, Figure 3 As shown, a medical auxiliary diagnosis device is provided, including a memory and a processor, as follows:
[0092] Memory: The memory stores computer programs, which include instructions and algorithms for data collection, model training, diagnostic analysis, result matching, sorting and feedback. The memory also includes storage areas for storing patient data, diagnostic models, medical knowledge bases and diagnostic results to ensure data integrity and security.
[0093] Processor: The processor executes the computer program in the memory to complete data processing, diagnostic analysis and result feedback. The processor calls the data and models in the memory to perform real-time diagnostic analysis and processing to ensure the efficiency and accuracy of the diagnostic process.
[0094] In one embodiment, a computer storage medium is provided, on which a computer program is stored, specifically as follows:
[0095] Computer program: This program includes instructions and algorithms for data collection, model training, diagnostic analysis, result matching, sorting and feedback. When the program is executed by the processor, it can implement the steps of the above method to ensure the automation and intelligence of the diagnostic process.
[0096] Storage media: Computer storage media include hard disks, solid-state drives, flash memory, optical disks or magnetic disks. Storage media can store computer programs and related data for a long time, ensuring the security and availability of data.
[0097] In one embodiment, Figure 4 As shown, a computer system is provided, comprising:
[0098] processor:
[0099] It is used to execute computer programs in the memory to realize data processing, diagnostic analysis and result feedback. The processor completes real-time analysis and diagnosis of patient data by calling the data and models in the memory.
[0100] Memory:
[0101] The computer program is stored, and when the program is executed by the processor, the steps of the above method are implemented. The memory is also used to store patient data, diagnostic models, medical knowledge base and diagnostic results to ensure the integrity and security of the data.
[0102] User Interface Module:
[0103] It is used for the interaction between doctors and the system, displays diagnosis results and treatment recommendations, and provides feedback and adjustment functions. The user interface module can be a graphical user interface (GUI), command line interface (CLI) or voice interaction interface (VUI) to facilitate the operation and use of doctors. The interface design focuses on user experience to ensure that doctors can easily and quickly obtain diagnostic information and perform operations.
[0104] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A medical auxiliary diagnosis method, characterized in that: The method comprises: Obtaining medical data to be diagnosed, the medical data including basic information and clinical data of the patient, the basic information including the patient's name, gender, age, past medical history, family medical history, lifestyle and allergy history, etc., and the clinical data including symptom description, physical examination results, laboratory test results and imaging examination results, etc.; Based on the medical data, a preliminary diagnosis result is generated using a machine learning model, wherein the machine learning model includes a decision tree, a support vector machine, a neural network, and a deep learning model, and the model is trained with a large amount of annotated data and can accurately identify and analyze the symptoms and signs of various diseases; Matching the preliminary diagnosis result with a preset medical knowledge base to generate multiple possible diagnosis options, wherein the medical knowledge base includes diagnostic criteria for common diseases, clinical characteristics of uncommon diseases, and the latest medical research results; Ranking each diagnosis option and giving a corresponding credibility score, wherein the ranking is based on the confidence of the diagnosis model and the relevance score of the medical knowledge base; Select the best diagnosis result according to the credibility score and preset medical rules, and generate corresponding treatment suggestions, including drug treatment plans, non-drug treatment plans, lifestyle adjustment suggestions and further examination suggestions; The diagnosis results and treatment recommendations are fed back to the doctor for reference and further confirmation. The doctor can adjust and optimize the diagnosis results and treatment recommendations based on his or her own clinical experience and the actual situation of the patient.
2. The medical auxiliary diagnosis method according to claim 1, characterized in that: The step of obtaining the medical data to be diagnosed includes: Obtaining the patient's electronic health record (EHR) data, including the patient's medical history, past medical records, inspection and quarantine records, and drug use records; Obtain patients' real-time monitoring data, including physiological indicators such as blood pressure, heart rate, blood sugar, body temperature and oxygen saturation. These data are collected and transmitted in real time through wearable devices or hospital monitoring equipment; Obtain the patient's laboratory test data, including blood tests, urine tests, imaging tests (such as X-ray, CT, MRI, etc.) and other special examination results for specific diseases. These data are provided by the hospital's laboratory or imaging department.
3. The medical auxiliary diagnosis method according to claim 1, characterized in that: The machine learning model is a deep neural network model, which is pre-trained with a large amount of labeled data to improve diagnostic accuracy; The training data includes patient data of different age groups, genders and races, covering a variety of common and rare diseases, to ensure the wide applicability and robustness of the model.
4. The medical auxiliary diagnosis method according to claim 1, characterized in that: The medical knowledge base includes the following: The diagnostic criteria for common diseases are formulated based on the International Classification of Diseases (ICD) and medical guidelines of various countries; Symptoms and characteristics of different diseases, including causes, pathological mechanisms, clinical manifestations, complications and prognosis; Treatment plans and drug use guidelines for different diseases, including standard treatment plans, individualized treatment plans, and drug indications, contraindications, dosage, and adverse reactions; The latest medical research results and clinical trial data, including the latest published research papers, clinical trial results and discussion results of medical conferences, in order to timely update and supplement the content of the medical knowledge base.
5. The medical auxiliary diagnosis method according to claim 1, characterized in that: The credibility score is calculated based on the following factors: The confidence level of the machine learning model’s diagnostic results, which indicates the model’s confidence in a certain diagnostic result; Statistical data of similar cases in the medical knowledge base, including the diagnosis results and treatment effects of similar cases, are inferred based on historical data; Individual patient characteristics and medical history, including age, gender, medical history, family history, lifestyle, etc., to consider the impact of individual differences on disease diagnosis; Environmental and epidemiological factors, including seasonal epidemics, regional disease distribution, etc., modify and supplement the diagnostic results.
6. The medical auxiliary diagnosis method according to any one of claims 1 to 5, characterized in that: The generated diagnostic results are judged and predicted. The specific steps include: After obtaining the preliminary diagnosis results, compare and analyze them with historical diagnosis data to evaluate their accuracy and reliability; Combine current medical data with historical data to use predictive models to predict possible disease progression and treatment effects; Assess the credibility of the prediction results and adjust the diagnosis and treatment plans based on the evaluation results; Provides detailed advice on the likelihood of future disease progression and coping strategies to help doctors conduct prevention and early intervention.
7. A medical auxiliary diagnosis device, characterized in that: include: A data acquisition module is used to obtain basic information and clinical data of patients. The data acquisition module is connected to data sources such as hospital information system (HIS), laboratory information system (LIS) and wearable devices to realize automatic data collection and transmission; A diagnostic model module, used to generate preliminary diagnostic results based on the medical data, wherein the diagnostic model module integrates a variety of machine learning and deep learning algorithms and performs diagnostic analysis by calling trained models; A matching module, used to match the preliminary diagnosis result with the medical knowledge base to generate multiple possible diagnosis options, wherein the matching module screens out possible diagnosis results by comparing the output of the diagnosis model with the standards in the knowledge base; A ranking module is used to rank the various diagnostic options and give corresponding credibility scores, wherein the ranking module comprehensively considers the confidence of the model and the relevance score of the knowledge base to generate a comprehensive score; A selection module is used to select the best diagnosis result according to the credibility score and the preset medical rules, and generate corresponding treatment suggestions. The selection module automatically selects and generates the best diagnosis and treatment plan according to the score and the preset rules; The feedback module is used to feed back the diagnosis results and treatment suggestions to the doctor, and push them to the doctor through the doctor's workstation, mobile terminal or email for reference and further confirmation.
8. A medical auxiliary diagnosis device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented; The memory includes a storage area for storing patient data, diagnostic models, medical knowledge base and diagnostic results. When the processor executes the computer program, it calls the data and models in the memory to complete data processing, diagnostic analysis and result feedback.
9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented, the computer storage medium includes a hard disk, a solid-state drive, a flash memory, an optical disk or a magnetic disk, and the computer program includes instructions and algorithms for implementing data collection, model training, diagnostic analysis, result matching, sorting and feedback.