Disease diagnosis method and device, equipment and storage medium

Abstract

The invention discloses a disease diagnosis method, device and equipment and a storage medium, and relates to the technical field of intelligent diagnosis, and the method provides a disease intelligent diagnosis model to assist doctors in improving the accuracy and efficiency of clinical diagnosis. The problem of insufficient disease knowledge in a general medical large model is solved, and the knowledge potential of the large model can be fully mined. The guiding model verifies the accuracy of the pre-diagnosis result according to the existing medical guideline, and the interpretability of the medical decision is ensured. The model aims to improve the accuracy and efficiency of complex disease diagnosis by integrating multi-scale knowledge enhancement, multi-agent debate optimization and self-correction diagnosis cooperation verification, and based on the scientificity of a medical guideline analysis conclusion, the accuracy and efficiency of complex disease diagnosis are improved by combining a leading-edge natural language processing technology and a clinical medical knowledge system. And a new path is developed for assisting clinical medical diagnosis of diseases.

Description

Technical Field

[0001] The present invention relates to the field of intelligent diagnosis technology, and in particular to a multi-source knowledge-driven intelligent disease diagnosis method, device, equipment and storage medium. Background Art

[0002] There are approximately 400 million patients with liver disease in China, accounting for 28% of the total population. The precise diagnosis and treatment of liver disease has greatly challenged the capabilities of the existing medical system. Due to the diversity of liver disease types and hidden early symptoms, the lack of structured knowledge and systematic quantitative standards can easily lead to misdiagnosis and missed diagnosis. In addition, liver disease has a long course and is often accompanied by multi-system lesions throughout the body. The diagnosis process requires comprehensive judgment of multidisciplinary cross-knowledge. These factors make the diagnosis of liver disease complex and changeable, especially requiring extremely high breadth and depth of knowledge of doctors. In addition, the uneven diagnosis and treatment levels among medical institutions of different levels further affect the accuracy and efficiency of decision-making for complex liver diseases.

[0003] Therefore, it is urgent to develop and apply intelligent diagnostic methods to improve the accuracy and efficiency of complex liver disease diagnosis and treatment. Considering the seriousness of medical diagnosis, the most important thing for this method is transparency and explainability, so that medical staff can understand and trust its diagnostic process and results, and thus apply it in clinical practice.

[0004] Therefore, the method of applying the intelligent liver disease diagnosis model to clinical liver disease analysis must meet the following conditions: 1. The method has rich knowledge of liver disease and can deeply analyze the complex pathogenic mechanism and identification methods of liver disease to ensure the authenticity and scientificity of the output content; 2. The method needs to analyze all possible liver diseases to the maximum extent and provide a basis for diagnosis to ensure that the results are highly interpretable and practical; 3. The liver disease diagnosis results are highly similar to the results of expert physicians' judgment to ensure the accuracy of the model output and consistency with the expert level. Summary of the invention

[0005] In view of the above problems, the present invention provides a disease diagnosis method, device, equipment and storage medium for overcoming the above problems or at least partially solving the above problems. It solves the problems of diagnostic result deviation and misleading caused by insufficient unstructured data analysis and lack of professional knowledge in practical applications, and is a new method for achieving accurate disease diagnosis.

[0006] The present invention provides the following scheme:

[0007] A disease diagnosis method, comprising:

[0008] Acquire the patient's electronic medical record data set, divide and count the electronic medical record data set to obtain an original summary report;

[0009] Abnormal medical indicators are obtained by analyzing the original summary report; the abnormal medical indicators and the names of multiple target diseases are used as entities to retrieve related triples in the disease-specific knowledge graph; predefined analysis instructions are used to guide the large language model to explore the potential relationship between the abnormal medical indicators and the multiple target diseases to generate corresponding diagnostic basis; the original summary report is integrated with the related triples and the diagnostic basis to obtain a target data set after knowledge integration;

[0010] Determine a number of intelligent agent roles with different tasks and progressive levels; use the lowest-level intelligent agent roles in combination with the target data set to generate a preliminary inference result; use the intermediate-level intelligent agent roles in combination with the target data set and the preliminary inference result to generate an intermediate inference result; use the highest-level intelligent agent roles in combination with the target data set, the preliminary inference result and the generated intermediate inference result to generate a final inference result; use the intelligent agent roles to conduct multiple rounds of voting on the final inference result, and after determining that the voting opinions are unified, use the final inference result as the final debate result;

[0011] Determine a guideline database and a consistency check agent including a plurality of the target diseases; use the consistency check agent to analyze the final debate result in combination with the guideline database and the original summary report, so as to verify the accuracy of the final debate result according to the requirements of the medical guidelines;

[0012] After determining that the final debate result is accurate, a comprehensive diagnosis and treatment decision is generated.

[0013] Preferably, the original summary report includes at least the patient's medical history information, chief complaint information, imaging report, physical examination information and laboratory test result information.

[0014] Preferably: after determining that the voting opinions are not unified, a modification suggestion is determined so that the highest-level intelligent agent roles adjust the final inference result according to the modification suggestion until the voting opinions are unified.

[0015] Preferably: the plurality of agent roles include 3 senior attending physician agents, 2 deputy chief physician agents and 1 chief physician agent in ascending order of level;

[0016] The three senior attending physician agents are used in combination with the target data set to generate preliminary inference results; the two deputy chief physician agents are used in combination with the target data set and the preliminary inference results to generate intermediate inference results; and the one chief physician agent is used in combination with the target data set, the preliminary inference results and the generated intermediate inference results to generate a final inference result.

[0017] Preferably: the three senior attending physician intelligent agents generate three diagnostic conclusions from medical history, imaging examination and biochemical examination and fuse them to obtain the preliminary inference result.

[0018] Preferably: determine to use the prompt word strategy to divide the two deputy chief physician agents into an imaging and medical history comprehensive analysis agent and an individual assessment agent;

[0019] The imaging and medical history comprehensive analysis agent is used to review the patient's medical history, pay attention to the timeline of the disease development and symptom changes, and compare the current imaging results with past records to analyze the specific characteristics of the lesion;

[0020] The individual assessment agent is used to consider the individual differences of patients and the impact of their lifestyle on the disease, and to evaluate the changes in biomarkers in biochemical examinations and analyze the changing trends of these indicators at different time points.

[0021] Preferably: the target disease includes liver disease, the abnormal medical indicators include liver function indicators and related biomarkers and specific manifestations, and the liver function indicators at least include alanine aminotransferase content, aspartate aminotransferase content, and alkaline phosphatase content;

[0022] The guideline database at least includes primary liver cancer, drug-induced liver injury, fatty liver, liver cyst, liver hemangioma, autoimmune hepatitis, and alcoholic liver disease;

[0023] The comprehensive diagnosis and treatment decision at least includes the liver disease diagnosis conclusion, diagnostic basis and recommended treatment method.

[0024] A disease diagnosis device, used to perform the above disease diagnosis method, the device comprising:

[0025] A data acquisition unit, used to acquire a patient's electronic medical record data set, and divide and count the electronic medical record data set to obtain an original summary report;

[0026] The knowledge enhancement unit is used to obtain abnormal medical indicators by analyzing the original summary report; retrieve the abnormal medical indicators and the names of multiple target diseases as entities in the disease-specific knowledge graph to obtain related triples; use predefined analysis instructions to guide the large language model to explore the potential relationship between the abnormal medical indicators and the multiple target diseases to generate corresponding diagnostic basis; fuse the original summary report with the related triples and the diagnostic basis to obtain a target data set after knowledge integration;

[0027] A multi-dimensional intelligent debate optimization unit is used to determine a number of intelligent agent roles with different tasks and progressive levels; use the lowest-level intelligent agent roles in combination with the target data set to generate a preliminary inference result; use the intermediate-level intelligent agent roles in combination with the target data set and the preliminary inference result to generate an intermediate inference result; use the highest-level intelligent agent roles in combination with the target data set, the preliminary inference result and the generated intermediate inference result to generate a final inference result; use the intelligent agent roles to conduct multiple rounds of voting on the final inference result, and after determining that the voting opinions are unified, use the final inference result as the final debate result;

[0028] A self-correcting diagnosis and treatment collaborative verification unit is used to determine a guideline database including a plurality of target diseases and a consistency verification agent; and to analyze the final debate result by using the consistency verification agent in combination with the guideline database and the original summary report, so as to verify the accuracy of the final debate result according to the requirements of the medical guideline;

[0029] A comprehensive diagnosis and treatment decision generating unit is used to generate a comprehensive diagnosis and treatment decision after determining that the final debate result is accurate.

[0030] A disease diagnosis device, comprising a processor and a memory:

[0031] The memory is used to store program code and transmit the program code to the processor;

[0032] The processor is used to execute the above-mentioned disease diagnosis method according to the instructions in the program code.

[0033] A computer-readable storage medium is used to store program codes, and the program codes are used to execute the above-mentioned disease diagnosis method.

[0034] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0035] The embodiments of the present application provide a disease diagnosis method, device, equipment and storage medium, which provides an intelligent disease diagnosis model to assist doctors in improving the accuracy and efficiency of clinical diagnosis. It solves the problem of insufficient disease knowledge in general medical big models and can fully tap the knowledge potential of big models. The model is guided to verify the accuracy of pre-diagnosis results according to current medical guidelines to ensure the interpretability of medical decisions. The model aims to improve the accuracy and efficiency of complex disease diagnosis by integrating multi-scale knowledge enhancement, multi-agent debate optimization and self-correcting diagnostic collaborative verification, and based on the scientific nature of the conclusions of medical guideline analysis, it combines cutting-edge natural language processing technology with clinical medical knowledge systems to open up new paths for assisting clinical medical diagnosis of diseases.

[0036] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] 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 are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 is a flow chart of a disease diagnosis method provided by an embodiment of the present invention;

[0039] Figure 2 is a flow chart of a liver disease diagnosis process provided by an embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of a disease diagnosis device provided by an embodiment of the present invention;

[0041] Figure 4 It is a schematic diagram of a disease diagnosis device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0043] See also Figure 1 , is a disease diagnosis method provided by an embodiment of the present invention, such as Figure 1 As shown, the method may include:

[0044] S101: Obtain the patient's electronic medical record data set, divide and count the electronic medical record data set to obtain an original summary report; the electronic medical record data set can be manually input by the doctor, and a related database can be pre-established to store the medical records of patients who need to be diagnosed with the corresponding disease in the hospital for subsequent diagnosis. The original summary may include some basic information. For example, in one implementation, the embodiment of the present application can provide that the original summary report at least includes the patient's medical history information, chief complaint information, imaging report, physical examination information, and laboratory test result information.

[0045] S102: Obtain abnormal medical indicators by analyzing the original summary report; retrieve the abnormal medical indicators and the names of multiple target diseases as entities in the disease-specific knowledge graph to obtain related triples; use predefined analysis instructions to guide the large language model to explore the potential relationship between the abnormal medical indicators and the multiple target diseases to generate corresponding diagnostic basis; fuse the original summary report with the related triples and the diagnostic basis to obtain a target data set after knowledge integration;

[0046] S103: Determine several intelligent agent roles with different tasks and progressive levels; use several of the intelligent agent roles at the lowest level in combination with the target data set to generate preliminary inference results; use several of the intelligent agent roles at the intermediate level in combination with the target data set and the preliminary inference results to generate intermediate inference results; use several of the intelligent agent roles at the highest level in combination with the target data set, the preliminary inference results and the generated intermediate inference results to generate final inference results; use several of the intelligent agent roles to conduct multiple rounds of voting on the final inference results, and after determining that the voting opinions are unified, use the final inference results as the final debate results; further, after determining that the voting opinions are not unified, determine modification suggestions, so that several of the intelligent agent roles at the highest level can adjust the final inference results according to the modification suggestions until the voting opinions are unified.

[0047] The method provided in the embodiment of the present application uses multiple rounds of debates by simulating multiple digital doctor agents with different expertise, and synthesizes the views of all parties to form a preliminary diagnosis. The number of agents and their role positioning can be set according to the needs of the actual diagnosis scenario. For example, in one implementation, the embodiment of the present application can also provide a number of agent roles including 3 senior attending physician agents, 2 deputy chief physician agents, and 1 chief physician agent, with levels from low to high;

[0048] The three senior attending physician agents are used in combination with the target data set to generate preliminary inference results; the two deputy chief physician agents are used in combination with the target data set and the preliminary inference results to generate intermediate inference results; and the one chief physician agent is used in combination with the target data set, the preliminary inference results and the generated intermediate inference results to generate a final inference result.

[0049] In specific implementation, the embodiment of the present application can also provide the three senior attending physician intelligent agents to generate three diagnostic conclusions from medical history, imaging examination and biochemical examination and integrate them to obtain the preliminary inference result.

[0050] In order to further ensure that the method can focus on the various causes of the patient's illness, the embodiment of the present application can also provide a method for determining the use of a prompt word strategy to divide the two deputy chief physician agents into an imaging and medical history comprehensive analysis agent and an individual assessment agent;

[0051] The imaging and medical history comprehensive analysis agent is used to review the patient's medical history, pay attention to the timeline of the disease development and symptom changes, and compare the current imaging results with past records to analyze the specific characteristics of the lesion;

[0052] The individual assessment agent is used to consider the individual differences of patients and the impact of their lifestyle on the disease, and to evaluate the changes in biomarkers in biochemical examinations and analyze the changing trends of these indicators at different time points.

[0053] S104: Determine a guideline database and a consistency check agent including a plurality of target diseases; use the consistency check agent to analyze the final debate result in combination with the guideline database and the original summary report, so as to verify the accuracy of the final debate result according to the requirements of the medical guideline;

[0054] S105: After determining that the final debate result is accurate, a comprehensive diagnosis and treatment decision is generated.

[0055] It is understandable that the method provided in the embodiment of the present application is applicable to diagnosing a variety of diseases. After determining the type of the target disease, the corresponding abnormal medical indicators, data guide database, and comprehensive diagnosis and treatment decision output type, etc. can be set. For example, in one implementation, the embodiment of the present application can provide that the target disease includes liver disease, the abnormal medical indicators include liver function indicators and related biomarkers and specific manifestations, and the liver function indicators include at least alanine aminotransferase content, aspartate aminotransferase content, and alkaline phosphatase content;

[0056] The guideline database at least includes primary liver cancer, drug-induced liver injury, fatty liver, liver cyst, liver hemangioma, autoimmune hepatitis, and alcoholic liver disease;

[0057] The comprehensive diagnosis and treatment decision at least includes the liver disease diagnosis conclusion, diagnostic basis and recommended treatment method.

[0058] The disease diagnosis method provided in the embodiment of the present application integrates knowledge graph retrieval and large model generation technology, adopts a multi-agent debate strategy and combines liver disease medical guidelines to improve the accuracy and reliability of diagnosis. Specifically, the method first uses multi-scale knowledge enhancement technology to analyze abnormal medical indicators; secondly, by simulating multiple virtual doctors with different expertise to conduct multiple rounds of debates, the views of all parties are integrated to form a preliminary diagnosis; finally, through a self-correcting diagnostic collaborative verification program, the diagnosis results are ensured to be consistent with the medical guidelines, thereby generating the final comprehensive diagnosis and treatment decision.

[0059] The following takes liver disease as an example to describe the disease diagnosis method provided in the present application in detail. Figure 2 .

[0060] The method provided in the embodiment of the present application integrates knowledge graph retrieval and large model generation technology, adopts a multi-agent debate strategy and combines liver disease medical guidelines to improve the accuracy and reliability of diagnosis. Specifically, the method first uses multi-scale knowledge enhancement technology to analyze abnormal medical indicators, and constructs relevant triples by retrieving the liver disease knowledge graph.

[0061] Secondly, by simulating multiple virtual doctors with different expertise to conduct multiple rounds of debate, the opinions of all parties are integrated to form a preliminary diagnosis;

[0062] Finally, a self-correcting diagnostic collaborative validation process ensures that the diagnostic results are consistent with medical guidelines, thereby generating the final comprehensive diagnosis and treatment decision.

[0063] The multi-source knowledge-driven intelligent liver disease diagnosis method includes the following steps:

[0064] Step 1: First, read in the electronic medical record data set containing the patient's medical history information, imaging examination, biochemical examination, physical examination information, etc. Divide and count this information for subsequent processing.

[0065] Given a patient's electronic medical record, clean and integrate the patient's medical history, chief complaint, imaging report, physical examination and laboratory test and other free text information to form a summary report S.

[0066] Step 2: Multi-scale knowledge enhancement. By analyzing abnormal medical indicators in the electronic health records of the electronic medical record dataset and retrieving related triple knowledge in combination with the liver disease knowledge graph, the understanding of the patient's liver disease condition can be enhanced. This stage also includes intelligent analysis generation, which guides large language models through predefined instructions to explore the potential association between abnormal medical indicators and various liver diseases and generate diagnostic evidence. Finally, this retrieved and generated knowledge is fused with the original input data to achieve multi-level knowledge integration.

[0067] By analyzing abnormal medical indicators in electronic medical records and retrieving relevant knowledge in combination with the liver disease knowledge graph, a comprehensive analysis report is generated. LLM (Large Language Model) is guided by specific prompts to analyze abnormal medical indicators (AMI) in medical texts. These indicators reflect the physiological state of an individual at a specific time point, including liver function indicators (such as alanine aminotransferase, aspartate aminotransferase, bilirubin, etc.) and other related biomarkers and specific manifestations. This process can be expressed as:

[0068] Gen AMI =LLM(S,prompt AMI )

[0069] Where: Gen AMI Indicates abnormal medical indicators, prompt AMI It means that it contains the role positioning and task prompts given to the large language model, and LLM stands for large language model.

[0070] In order to ensure the professionalism and depth of knowledge enhancement, abnormal medical indicators and various liver disease names are used as entities to retrieve relevant triples in the disease-specific knowledge graph. triples .

[0071] The disease-specific knowledge graph integrates clinical data on liver diseases, CM3KG, UMLS, and Wikidata5M, and contains about 140,000 nodes and relationships. The output format of the retrieval process can be expressed as:

[0072] Ret triples ={(HE i ,R i ,TE i )|i=1,…,n}

[0073] In the formula: HE i Represents the head entity, TE i Represents the tail entity, R i represents the relationship between them, and n is the number of triples retrieved.

[0074] In clinical practice, in order to fully understand the patient's liver disease status and make a scientific and reasonable diagnosis, we emphasize the importance of the breadth and diversity of medical information. By using predefined analysis instructions, the large language model can also be guided to explore the potential relationship between abnormal medical indicators AMI and various liver diseases, and generate corresponding diagnostic evidence. This process can be formalized as:

[0075] Gen analysis =LLM(AMI,prompt analysis )

[0076] Where: Gen analysisIndicates the basis for diagnosis, prompt analysis It stands for analysis instruction and AMI stands for abnormal medical index.

[0077] Then, we fuse the retrieved and generated knowledge with the original input data to achieve multi-level knowledge integration. This process can be formalized as:

[0078] K=Merge(S,Ret triples ,Gen analysis )

[0079] Where: K represents the target data set, Merge represents the merge sort algorithm.

[0080] Step 3: Multi-dimensional intelligent debate optimization. Construct multiple intelligent agent roles (such as senior attending physicians, deputy chief physicians, and chief physicians) to analyze patient data from different perspectives, reveal and correct different cognitive biases, and enhance the comprehensive understanding of complex liver diseases. In each round of discussion, the intelligent agent votes on the current decision result. If there is any objection, detailed modification suggestions are required, and then the chief physician intelligent agent will make adjustments until the opinions are unified and the final debate results are generated.

[0081] Construct intelligent agent roles for different tasks to simulate the expert consultation process, conduct multiple rounds of debate and optimization on the cases to achieve consistency in the diagnosis conclusions.

[0082] Considering the complexity of liver disease and the standardization of clinical diagnosis process, progressive medical roles are set for the intelligent agent. The roles are divided into three levels: 3 senior attending physicians, 2 deputy chief physicians and 1 chief physician. Among them, doctors at each level have different concerns when facing problems.

[0083] Specifically, j can be used to represent the different areas of expertise of the agent, including medical history analysis, imaging examination analysis, biochemical examination analysis, etc. The definition of the agent can be formalized as:

[0084] Agent j =LLM(prompt j )j∈(MA,IA,BA,…)

[0085] Where: prompt j Indicates the intelligent agent prompt word engineering with different focuses, MA represents medical history analysis, IA represents imaging analysis, and BA represents biochemical examination.

[0086] Using three senior attending physician agents to generate three diagnostic conclusions from medical history, imaging examination and biochemical examination and fusion to obtain preliminary inference results. Pre . This process can be expressed as:

[0087] AnsPre =Fusion j∈(MA,IA,BA) (f j (Agent j ,K))

[0088] In the formula, ∑ represents fusion, f j It means that each agent generates a diagnosis conclusion within its area of ​​expertise.

[0089] Similarly, using Agent j =LLM(prompt j ) Set different attention directions for the deputy chief physician agent through the prompt word strategy.

[0090] First, the imaging and medical history comprehensive analysis agent IM )The main task is to review the patient's medical history, pay attention to the timeline of disease development and symptom changes, compare current imaging results with past records, and analyze the specific characteristics of the lesions.

[0091] Secondly, biochemical examination and individual assessment agent BI ) focuses on the individual differences of patients and the impact of their lifestyle on the disease, while evaluating the changes in biomarkers in biochemical tests and analyzing the changing trends of these indicators at different time points.

[0092] Use 2 deputy chief physician agents to generate 2 comprehensive reports and combine them into an intermediate inference result. Mid . This process can be expressed as:

[0093] Ans Mid =Fusion j∈(IM,BI) (f j (Agent j ,K,Ans Pre ))

[0094] Chief Physician Agent ID ) focuses on integration and decision optimization. Its function is to integrate Ans Mid The analysis results of imaging, medical history, biochemical examinations and individual factors in the system are considered. At the same time, the weight and reliability of various information are considered to make a balanced judgment and avoid one-sided conclusions. We let it make high-level inferences and decisions based on comprehensive information and provide the final inference result Ans. This process can be expressed as:

[0095] Ans = f ID (Agent ID ,K,Ans Mid )

[0096] Where: f IDFunction representing the conclusion generated by the chief physician agent.

[0097] In each round of discussion, all agents will vote up to 5 times (agree / disagree) on the current final inference results. If you disagree with the report, you need to put forward detailed modification suggestions. revise , which can be expressed as:

[0098]

[0099] Where: Fusion represents an adaptive fusion algorithm, which is used to merge multi-source modification suggestions into the final modification plan.

[0100] Then, the chief physician agent adjusts the report based on these modification suggestions. adjust , this process can be expressed as:

[0101] Gen adjust =f ID (Agent ID ,K,Ans,Gen revise )

[0102] Until the opinions are unified and the final debate result D is generated n , this process can be expressed as:

[0103]

[0104] Where: Iterate(D n-1 ,Gen adjust ) indicates the result of the previous round of debate D n-1 Iterative process of adjustment.

[0105] Step 4: Self-correction diagnosis and treatment collaborative verification. In this stage, a guideline database containing a variety of liver diseases is used as the basis for the reliability of intelligent decision-making. If the debate result is inconsistent with the medical guidelines, the intelligent body will re-analyze the condition in combination with the medical records and guidelines.

[0106] Construct a guideline database Db covering various liver diseases such as primary liver cancer, drug-induced liver injury, and fatty liver Guide As an important basis for verifying the reliability of intelligent decision-making.

[0107] Through Agent j =LLM(prompt j )Build a consistency checking agent CVTo guide the large language model to analyze the results of multiple rounds of debates in combination with medical guidelines and S, and verify the accuracy of the debate results according to the requirements of medical guidelines. If the conclusions are inconsistent, the agent will re-analyze the condition in combination with the medical records and guidelines.

[0108] Step 5: Generate a comprehensive diagnosis and treatment decision including the diagnosis conclusion, diagnosis basis and recommended treatment methods of liver disease. Generate a comprehensive diagnosis and treatment decision C including the diagnosis conclusion, diagnosis basis and recommended treatment methods of liver disease as the output conclusion of this method. This process can be expressed as:

[0109] C = f CV (Agent CV ,K,D n ,Db Guide )

[0110] Where: f CV Represents the function of the consistency check agent to generate the conclusion, Db Guide Represents the guide database.

[0111] In summary, the disease diagnosis method provided in this application provides an intelligent disease diagnosis model to assist doctors in improving the accuracy and efficiency of clinical diagnosis. It solves the problem of insufficient disease knowledge in general medical large models and can fully tap the knowledge potential of large models. The model is guided to verify the accuracy of pre-diagnosis results according to current medical guidelines to ensure the interpretability of medical decisions. The model aims to improve the accuracy and efficiency of complex disease diagnosis by integrating multi-scale knowledge enhancement, multi-agent debate optimization, and self-correcting diagnostic collaborative verification, and based on the scientific nature of the conclusions of medical guideline analysis, it combines cutting-edge natural language processing technology with clinical medical knowledge systems to open up new paths for assisting clinical medical diagnosis of diseases.

[0112] See also Figure 3 , the present application embodiment may also provide a disease diagnosis device, such as Figure 3 As shown, for performing the above-mentioned disease diagnosis method, the device may include:

[0113] The data acquisition unit 301 is used to acquire the electronic medical record data set of the patient, divide and count the electronic medical record data set to obtain an original summary report;

[0114] The knowledge enhancement unit 302 is used to obtain abnormal medical indicators by analyzing the original summary report; retrieve the abnormal medical indicators and the names of multiple target diseases as entities in the disease-specific knowledge graph to obtain related triples; use predefined analysis instructions to guide the large language model to explore the potential relationship between the abnormal medical indicators and the multiple target diseases to generate corresponding diagnostic basis; fuse the original summary report with the related triples and the diagnostic basis to obtain a target data set after knowledge integration;

[0115] The multi-dimensional intelligent debate optimization unit 303 is used to determine a number of intelligent agent roles with different tasks and progressive levels; use the lowest-level intelligent agent roles in combination with the target data set to generate a preliminary inference result; use the intermediate-level intelligent agent roles in combination with the target data set and the preliminary inference result to generate an intermediate inference result; use the highest-level intelligent agent roles in combination with the target data set, the preliminary inference result and the generated intermediate inference result to generate a final inference result; use the intelligent agent roles to conduct multiple rounds of voting on the final inference result, and after determining that the voting opinions are unified, use the final inference result as the final debate result;

[0116] The self-correcting diagnosis and treatment collaborative verification unit 304 is used to determine a guideline database including a plurality of target diseases and a consistency verification agent; and analyze the final debate result by using the consistency verification agent in combination with the guideline database and the original summary report, so as to verify the accuracy of the final debate result according to the requirements of the medical guideline;

[0117] The comprehensive diagnosis and treatment decision generating unit 305 is used to generate a comprehensive diagnosis and treatment decision after determining that the final debate result is accurate.

[0118] The present application may also provide a disease diagnosis device, the device comprising a processor and a memory:

[0119] The memory is used to store program code and transmit the program code to the processor;

[0120] The processor is used to execute the steps of the above-mentioned disease diagnosis method according to the instructions in the program code.

[0121] like Figure 4 As shown, a disease diagnosis device provided in an embodiment of the present application may include: a processor 10, a memory 11, a communication interface 12 and a communication bus 13. The processor 10, the memory 11 and the communication interface 12 communicate with each other through the communication bus 13.

[0122] In the embodiment of the present application, the processor 10 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic devices.

[0123] The processor 10 may call a program stored in the memory 11. Specifically, the processor 10 may execute operations in an embodiment of the disease diagnosis method.

[0124] The memory 11 is used to store one or more programs, which may include program codes, and the program codes include computer operation instructions. In the embodiment of the present application, the memory 11 at least stores programs for implementing the following functions:

[0125] Acquire the patient's electronic medical record data set, divide and count the electronic medical record data set to obtain an original summary report;

[0126] Abnormal medical indicators are obtained by analyzing the original summary report; the abnormal medical indicators and the names of multiple target diseases are used as entities to retrieve related triples in the disease-specific knowledge graph; predefined analysis instructions are used to guide the large language model to explore the potential relationship between the abnormal medical indicators and the multiple target diseases to generate corresponding diagnostic basis; the original summary report is integrated with the related triples and the diagnostic basis to obtain a target data set after knowledge integration;

[0127] Determine a number of intelligent agent roles with different tasks and progressive levels; use the lowest-level intelligent agent roles in combination with the target data set to generate a preliminary inference result; use the intermediate-level intelligent agent roles in combination with the target data set and the preliminary inference result to generate an intermediate inference result; use the highest-level intelligent agent roles in combination with the target data set, the preliminary inference result and the generated intermediate inference result to generate a final inference result; use the intelligent agent roles to conduct multiple rounds of voting on the final inference result, and after determining that the voting opinions are unified, use the final inference result as the final debate result;

[0128] Determine a guideline database and a consistency check agent including a plurality of the target diseases; use the consistency check agent to analyze the final debate result in combination with the guideline database and the original summary report, so as to verify the accuracy of the final debate result according to the requirements of the medical guidelines;

[0129] After determining that the final debate result is accurate, a comprehensive diagnosis and treatment decision is generated.

[0130] In one possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required for at least one function (such as a file creation function, a data reading and writing function), etc.; the data storage area can store data created during use, such as initialization data, etc.

[0131] In addition, the memory 11 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0132] The communication interface 12 may be an interface of a communication module, and is used to connect to other devices or systems.

[0133] Of course, it should be noted that Figure 4 The structure shown does not constitute a limitation on the disease diagnosis device in the embodiment of the present application. In actual applications, the disease diagnosis device may include Figure 4 More or fewer components than shown, or combinations of certain components.

[0134] The embodiment of the present application may also provide a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute the steps of the above-mentioned disease diagnosis method.

[0135] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0136] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0137] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0138] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A disease diagnosis method, characterized in that: include: Acquire the patient's electronic medical record data set, divide and count the electronic medical record data set to obtain an original summary report; Obtaining abnormal medical indicators by analyzing the original summary report; The abnormal medical indicators and the names of multiple target diseases are used as entities to retrieve related triples in the disease-specific knowledge graph; predefined analysis instructions are used to guide the large language model to explore the potential relationship between the abnormal medical indicators and the multiple target diseases to generate corresponding diagnostic basis; the original summary report is integrated with the related triples and the diagnostic basis to obtain the target data set after knowledge integration; Determine a plurality of intelligent agent roles with different tasks and progressive levels; use the plurality of intelligent agent roles at the lowest level in combination with the target data set to generate a preliminary inference result; use the plurality of intelligent agent roles at the intermediate level in combination with the target data set and the preliminary inference result to generate an intermediate inference result; use the plurality of intelligent agent roles at the highest level in combination with the target data set, the preliminary inference result and the generated intermediate inference result to generate a final inference result; Using a plurality of the intelligent agent roles to conduct multiple rounds of voting on the final inference result, and after determining that the voting opinions are unified, the final inference result is used as the final debate result; Determining a guideline database including a plurality of target diseases and a consistency checking agent; Analyzing the final debate result using the consistency check agent in combination with the guideline database and the original summary report, so as to verify the accuracy of the final debate result according to the requirements of the medical guidelines; After determining that the final debate result is accurate, a comprehensive diagnosis and treatment decision is generated.

2. The disease diagnosis method according to claim 1, characterized in that: The original summary report includes at least the patient's medical history information, chief complaint information, imaging report, physical examination information and laboratory test result information.

3. The disease diagnosis method according to claim 1, characterized in that: After determining that the voting opinions are not unified, a modification suggestion is determined so that the highest-level intelligent agent roles adjust the final inference result according to the modification suggestion until the voting opinions are unified.

4. The disease diagnosis method according to claim 1, characterized in that: The plurality of agent roles include 3 senior attending physician agents, 2 deputy chief physician agents and 1 chief physician agent in order of level from low to high; Using the three senior attending physician agents combined with the target data set to generate preliminary inference results; Using the two deputy chief physician agents to combine the target data set and the preliminary inference results to generate an intermediate inference result; The chief physician agent is used to generate a final inference result by combining the target data set, the preliminary inference result and the generated intermediate inference result.

5. The disease diagnosis method according to claim 4, characterized in that: The three senior attending physician intelligent agents generated three diagnostic conclusions based on medical history, imaging examination and biochemical examination and integrated them to obtain the preliminary inference results.

6. The disease diagnosis method according to claim 4, characterized in that: Determine to use the prompt word strategy to divide the 2 deputy chief physician agents into an imaging and medical history comprehensive analysis agent and an individual assessment agent; The imaging and medical history comprehensive analysis agent is used to review the patient's medical history, pay attention to the timeline of the disease development and symptom changes, and compare the current imaging results with past records to analyze the specific characteristics of the lesion; The individual assessment agent is used to consider the individual differences of patients and the impact of their lifestyle on the disease, and to evaluate the changes in biomarkers in biochemical examinations and analyze the changing trends of these indicators at different time points.

7. The disease diagnosis method according to claim 1, characterized in that: The target disease includes liver disease, the abnormal medical indicators include liver function indicators and related biomarkers and specific manifestations, and the liver function indicators at least include alanine aminotransferase content, aspartate aminotransferase content, and alkaline phosphatase content; The guideline database at least includes primary liver cancer, drug-induced liver injury, fatty liver, liver cyst, liver hemangioma, autoimmune hepatitis, and alcoholic liver disease; The comprehensive diagnosis and treatment decision at least includes the liver disease diagnosis conclusion, diagnostic basis and recommended treatment method.

8. A disease diagnosis device, characterized in that: Used to perform the disease diagnosis method according to any one of claims 1 to 7, the device comprising: A data acquisition unit, used to acquire a patient's electronic medical record data set, and divide and count the electronic medical record data set to obtain an original summary report; The knowledge enhancement unit is used to obtain abnormal medical indicators by analyzing the original summary report; retrieve the abnormal medical indicators and the names of multiple target diseases as entities in the disease-specific knowledge graph to obtain related triples; use predefined analysis instructions to guide the large language model to explore the potential relationship between the abnormal medical indicators and the multiple target diseases to generate corresponding diagnostic basis; fuse the original summary report with the related triples and the diagnostic basis to obtain a target data set after knowledge integration; A multi-dimensional intelligent debate optimization unit is used to determine a number of intelligent agent roles with different tasks and progressive levels; use the lowest-level intelligent agent roles in combination with the target data set to generate a preliminary inference result; use the intermediate-level intelligent agent roles in combination with the target data set and the preliminary inference result to generate an intermediate inference result; use the highest-level intelligent agent roles in combination with the target data set, the preliminary inference result and the generated intermediate inference result to generate a final inference result; use the intelligent agent roles to conduct multiple rounds of voting on the final inference result, and after determining that the voting opinions are unified, use the final inference result as the final debate result; A self-correcting diagnosis and treatment collaborative verification unit is used to determine a guideline database including a plurality of target diseases and a consistency verification agent; and to analyze the final debate result by using the consistency verification agent in combination with the guideline database and the original summary report, so as to verify the accuracy of the final debate result according to the requirements of the medical guideline; A comprehensive diagnosis and treatment decision generating unit is used to generate a comprehensive diagnosis and treatment decision after determining that the final debate result is accurate.

9. A disease diagnosis device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the disease diagnosis method according to any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the disease diagnosis method according to any one of claims 1-7.

Images