Clinical auxiliary diagnosis method and system, computing device and readable storage medium

Abstract

The invention provides a clinical auxiliary diagnosis method and system, computing equipment and a readable storage medium. The method comprises the following steps: acquiring an inquiry information result and medical record information of a target object; inputting the inquiry information result and the medical record information into a trained inquiry model to obtain an auxiliary diagnosis result; wherein the inquiry information result is obtained by the following steps: inputting the chief complaint information of the target object into a trained inquiry model to obtain inquiry information; and the target object answers the inquiry information to obtain an inquiry information result. The method can improve the diagnosis accuracy of doctors, reduce missed diagnosis and misdiagnosis, relieve the workload of the doctors and improve the medical efficiency. Meanwhile, a personalized treatment scheme is provided for the patient, patient management is optimized, and the treatment effect is improved. In addition, regional restrictions are broken through, high-quality medical resource sharing is achieved, and patients in remote areas can enjoy the same medical service as urban patients.

Description

Technical Field

[0001] The present application relates to the field of medical auxiliary diagnosis technology, and in particular to clinical auxiliary diagnosis methods, systems, computing devices and readable storage media. Background Art

[0002] Traditional diagnosis and treatment methods often require patients to go through multiple tedious steps including registration, medical treatment, examination and follow-up. The entire diagnosis and treatment process is lengthy and time-consuming. Doctors need to manually review medical records and examination results during the diagnosis and treatment process. In addition, it is difficult for patients to smoothly connect their medical information between different medical institutions, which leads to discontinuity and repeated examinations in the diagnosis and treatment process. At the same time, when facing complex diseases, rare diseases or interdisciplinary diseases, traditional diagnosis and treatment methods often cannot provide comprehensive and effective solutions.

[0003] Therefore, the existing diagnosis and treatment methods still need to be improved. Summary of the invention

[0004] This application aims to solve at least one of the existing problems. To this end, this application proposes a clinical auxiliary diagnosis method, which uses a large language model combined with a medical knowledge graph to analyze and process multivariate data from the target object through a human-computer interaction mode, effectively improving the efficiency and accuracy of diagnosis and reducing the risk of misdiagnosis and missed diagnosis.

[0005] Specifically, this application provides the following technical solutions:

[0006] In the first aspect of the present application, the present application proposes a clinical auxiliary diagnosis method. According to an embodiment of the present application, the method includes: obtaining the inquiry information results and medical history information of the target object; inputting the inquiry information results and medical history information into a trained inquiry model to obtain an auxiliary diagnosis result; wherein the inquiry information result is obtained in the following manner: inputting the chief complaint information of the target object into the trained inquiry model to obtain the inquiry information; the target object answers the inquiry information to obtain the inquiry information result.

[0007] In some examples of the present application, clear and comprehensive knowledge support can be obtained based on the aforementioned method, which helps to improve the accuracy of doctors' diagnosis and greatly reduce the risk of missed diagnosis and misdiagnosis; it can effectively reduce the workload of doctors and improve medical efficiency; provide patients with personalized treatment plans, and selectively collect disease-related information based on the patient's condition before the patient sees the doctor, implement patient management strategies that are tailored to each patient, and improve treatment effects; it can also break through geographical restrictions and realize the sharing and popularization of high-quality medical resources, so that patients in remote areas can also enjoy the same level of medical services as urban patients.

[0008] In the second aspect of the present application, the present application proposes a clinical auxiliary diagnosis system. According to an embodiment of the present application, the system includes: an information acquisition module for obtaining the inquiry information results and medical history information of the target object; a diagnostic reasoning module for inputting the inquiry information results and medical history information into a trained inquiry model to obtain an auxiliary diagnosis result; wherein the inquiry information result is obtained in the following manner: inputting the chief complaint information of the target object into the trained inquiry model to obtain the inquiry information; the target object answers the inquiry information to obtain the inquiry information result.

[0009] In some examples of the present application, the aforementioned system can efficiently and automatically analyze and integrate multivariate data from patients, provide doctors with clear and comprehensive knowledge support, help improve the accuracy of doctors' diagnosis, and reduce the risk of misdiagnosis and missed diagnosis; it can effectively reduce the workload of doctors and improve medical efficiency; provide patients with personalized treatment plans, and selectively collect disease-related information based on the patient's condition before the patient sees a doctor, implement patient management strategies that are tailored to each patient, and improve treatment outcomes; it can also break through geographical restrictions and realize the sharing and popularization of high-quality medical resources, so that patients in remote areas can also enjoy the same level of medical services as urban patients.

[0010] In the third aspect of the present application, the present application proposes a computer program product. According to an embodiment of the present application, the computer program product includes: computer instructions; when part or all of the computer instructions are run on a computer, the clinical auxiliary diagnosis method as described in the first aspect is executed.

[0011] In a fourth aspect of the present application, the present application proposes a computing device. According to an embodiment of the present application, the computing device comprises: a processor and a memory; the memory is used to store a computer program; the processor is used to execute the computer program to implement the clinical auxiliary diagnosis method as described in the first aspect.

[0012] In a fifth aspect of the present application, the present application proposes a computer-readable storage medium. According to an embodiment of the present application, the computer-readable storage medium stores computer instructions or programs, and when the computer instructions or programs are run on a computer, the clinical auxiliary diagnosis method as described in the first aspect is executed.

[0013] In some examples of this application, the aforementioned computer program products, computing devices, and computer-readable storage media automatically execute the aforementioned clinical auxiliary diagnosis methods through computer instructions, thereby achieving efficient and automated clinical auxiliary diagnosis, improving treatment effects, and reducing the risk of misdiagnosis and missed diagnosis; they can also break through geographical restrictions, achieve sharing of high-quality medical resources, and enable patients in remote areas to enjoy the same medical services as urban patients. In addition, the characteristics based on instructions make the above methods highly consistent and reliable in different application scenarios.

[0014] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A schematic diagram of a clinical auxiliary diagnosis method flow chart provided for a specific embodiment of the present application;

[0017] Figure 2 A schematic diagram of a clinical auxiliary diagnosis system provided for a specific embodiment of the present application;

[0018] Figure 3 A schematic diagram of an electronic device provided for a specific implementation of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In the present application, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In the description of the present application, unless otherwise specified, "multiple" refers to two or more than two.

[0021] In this application, unless otherwise specified, the term "medical knowledge graph (KG)" is a highly structured knowledge representation method, which is based on a graph model and systematically organizes and displays complex knowledge networks in the medical field in the form of nodes (representing entities, such as diseases, symptoms, drugs, etc.) and edges (representing relationships, such as causal relationships, therapeutic relationships, etc.), and greatly enhances the availability and practicality of knowledge through association analysis, intelligent reasoning and other means.

[0022] In the consultation model of this application, the medical knowledge graph builds a comprehensive, authoritative, and dynamically updated medical knowledge base by integrating a large amount of medical literature, clinical guidelines, expert experience and other data sources. This knowledge base covers the clinical manifestations, diagnostic criteria, treatment plans and other aspects of the disease, providing a knowledge basis for the consultation model.

[0023] Secondly, the medical knowledge graph supports the consultation model to achieve accurate diagnosis through its powerful association analysis and intelligent reasoning capabilities. The model can retrieve relevant disease entities and diagnostic rules in the knowledge graph based on the symptoms, signs and other information entered by the patient, and generate preliminary diagnostic suggestions through logical reasoning and probability calculation. At the same time, the model can also make personalized adjustments to the diagnostic suggestions based on the individual differences and disease characteristics of the patient, thereby improving the accuracy and pertinence of the diagnosis.

[0024] In this application, unless otherwise specified, the term "large language model (LLM)" is a type of deep learning model with a large number of parameters, which learns language patterns, grammar and semantics by processing massive amounts of text data in the field of natural language processing (NLP), so that it can understand and generate human language. The architecture contains a self-attention mechanism that can handle long-distance dependencies and improve the contextual understanding ability of the model. At the same time, the architecture can be fine-tuned on task-specific data sets to adapt to different application scenarios. In some examples of this application, a large language model is used as part of the architecture of the consultation model, as an intelligent question-and-answer system or consulting system, to provide patients or medical staff with medical knowledge answers, medication consultation, health advice and other services.

[0025] Aiming at the technical problems existing in the prior art, such as insufficient accuracy, low efficiency, and the risk of misdiagnosis and missed diagnosis, the inventor has proposed a clinical auxiliary diagnosis method, a clinical auxiliary diagnosis system, a computer program product, a computing device, and a computer storage medium after in-depth research. The following are detailed descriptions of each of them:

[0026] Clinical auxiliary diagnosis method

[0027] On the one hand, this application proposes a clinical auxiliary diagnosis method, referring to Figure 1 , the method comprising:

[0028] S10, obtaining the target object's inquiry information results and medical record information; wherein the inquiry information results are obtained in the following manner: inputting the target object's chief complaint information into the trained inquiry model to obtain the inquiry information; the target object answers the inquiry information to obtain the inquiry information results.

[0029] In some examples of the present application, the aforementioned target subjects are selected from the gastrointestinal discomfort group, including various groups of people with stomach discomfort (such as pain, acid reflux, belching, etc.), those who have been diagnosed with stomach diseases (chronic gastritis, gastric ulcer, duodenal ulcer, etc.), those with a family history of gastric cancer who need early screening, and those who need evaluation or review before and after gastric surgery.

[0030] The target subject's main complaint information (main symptoms) is input into the trained medical consultation model, and the model will output a medical consultation information, which includes a list of medical consultations around the main symptoms, such as the time of symptom occurrence, frequency of occurrence, whether there is persistent pain, type of pain, and whether family members have the same symptoms, etc. After the target subject answers the medical consultation information, it is the medical consultation information result.

[0031] While obtaining the results of the medical consultation information, it is also necessary to obtain the medical history information of the target object. The aforementioned case information includes at least: gastric imaging examination results (such as X-ray angiography, CT scan, MRI (magnetic resonance imaging), ultrasound examination or images obtained based on capsule gastroscopy technology, etc.), and may also include the target object's personal information, family medical history, medication history, physical examination information (such as abdominal palpation, etc.), laboratory test results (such as blood tests, biochemical indicators, etc.), etc.

[0032] S20, inputting the medical inquiry information results and medical record information into a trained medical inquiry model to obtain auxiliary diagnosis results.

[0033] The medical inquiry model involved in steps S10 and S20 is the same model, including: a first sub-model, used to obtain medical entity information and medical entity attribute information associated with the chief complaint information; and a second sub-model, used to generate auxiliary diagnosis results based on the entity information and the medical entity attribute information; wherein, the first sub-model is selected from the medical knowledge graph; and the second sub-model is selected from the large language model.

[0034] The relationship between entity information and entity attribute information is obtained based on the first sub-model. For example, if the medical entity information is a patient, the medical entity attribute information may include age, gender, medical history, etc.; for another example, if the medical entity information is a disease, the medical entity attribute information may include name, classification, symptoms, etc.; for another example, if the medical entity information is a drug, the medical entity attribute information may include name, usage, efficacy, etc.

[0035] In some examples of the present application, the aforementioned first sub-model is obtained by training in the following manner: obtaining a first medical training set, such as one or more of medical literature, clinical data, and case reports; further using a deep learning model to perform entity recognition on the first medical training set to obtain medical entity information and medical entity attribute information; based on preset triple rules, constructing a medical knowledge graph of the medical entity information and medical entity attribute information.

[0036] The aforementioned "preset triple rules" are structured specifications for connecting different entities through relationships in the knowledge graph. Each triple consists of three basic elements, namely entity 1 (subject), relationship (predicate), and entity 2 (object). These rules clearly define the types of relationships allowed between entities and how they are connected, so as to form a structured data representation in the knowledge graph. For example, gastritis manifests as stomach pain; omeprazole treats gastric ulcers; gastroscopy is used to diagnose gastric cancer, etc.

[0037] The second sub-model is used to output the medical auxiliary diagnosis result based on the relationship of the first sub-model. In some examples of the present application, the aforementioned second sub-model is obtained by training in the following manner: obtaining a second medical training set, such as a test report, etc.; based on a low-rank adaptation method, using the second medical training set to fine-tune the large language model.

[0038] The aforementioned “Low-Rank Adaptation (LoRA)” is a fine-tuning technique for optimizing large-scale pre-trained models. The core idea is to insert low-rank matrices for fine-tuning while keeping the original parameters of large language models (such as GPT, GLM, etc.) unchanged, so that the model can quickly adapt to data in specific fields without updating all parameters. This method effectively reduces the computational and storage overhead during fine-tuning, while improving the performance of the model in specific tasks. In the present application scheme, first, by adding low-rank matrices as adapters to the basic large language model, the knowledge of the medical field is used to initialize and update the parameters of these matrices, while keeping the basic model unchanged, so as to quickly adapt to the characteristics of medical text information.

[0039] In some examples of the present application, the aforementioned large language model is selected from at least one of GLM, GPT and LLaMA. In a specific example of the present application, the aforementioned large language model is selected from GLM-4.

[0040] In some examples of the present application, the method further includes: using the auxiliary diagnosis results to train the medical inquiry model. By obtaining the clinical auxiliary diagnosis results of the target object to expand the medical inquiry model (such as the medical knowledge graph part), the accuracy of the model diagnosis can be effectively improved.

[0041] The consultation model of this application adopts a medical knowledge graph-large language model collaborative reasoning architecture, in which the large language model is responsible for accurately understanding natural language, while the medical knowledge graph serves as a knowledge base to provide rich factual information. This fusion reasoning mechanism combines a dual encoder design: on the one hand, the LLM is deeply fine-tuned through massive data in the medical field, so that it can accurately capture the patient's intention to seek medical treatment, and automatically generate a detailed consultation list based on this, guiding the patient to complete the information filling. On the other hand, after the doctor's consultation and confirmation of additional examination results, the model further processes the text content and converts unstructured examination results into structured information for subsequent analysis.

[0042] Subsequently, the patient's core complaint and all examination results are used as input and integrated into the constructed medical KG. The powerful association ability of the graph is used to quickly retrieve and extract key entity information such as disease types, potential disease factors, and appropriate medication types that are closely related to the complaint. This process not only improves the efficiency of information processing, but also ensures the comprehensiveness and accuracy of the diagnostic basis.

[0043] Finally, the entity information extracted from KG is fed back to the LLM, which is aimed at ordinary people and focuses on the medical field. It automatically generates a comprehensive diagnosis report including disease introduction, disease cause analysis, personalized treatment plan, recommended medication list and detailed precautions in accordance with the standardized clinical report format. This innovative integration not only strengthens the depth and breadth of knowledge representation, but also greatly improves the intelligence level of clinical decision-making and patient experience, and jointly builds an efficient, accurate and humanized medical auxiliary reasoning system.

[0044] Clinical auxiliary diagnosis system

[0045] On the other hand, the present application proposes a clinical auxiliary diagnosis system, referring to Figure 2 The device includes: an information collection module 100 and a diagnosis and reasoning module 200.

[0046] Module 100 is used to obtain the medical inquiry information results and medical record information of the target object; wherein the medical inquiry information results are obtained in the following manner: the chief complaint information of the target object is input into the trained medical inquiry model to obtain medical inquiry information; the target object answers the medical inquiry information to obtain the medical inquiry information results.

[0047] In some examples of the present application, the target subject is selected from a group suffering from gastrointestinal discomfort.

[0048] In some examples of the present application, the medical record information includes at least: gastric imaging examination results.

[0049] Module 200 is used to input the medical inquiry information results and medical record information into the trained medical inquiry model to obtain auxiliary diagnosis results;

[0050] In some examples of the present application, the consultation model includes: a first sub-model, used to obtain medical entity information and medical entity attribute information associated with the chief complaint information; and a second sub-model, used to generate an auxiliary diagnosis result based on the entity information and the medical entity attribute information; wherein, the first sub-model is selected from a medical knowledge graph; and the second sub-model is selected from a large language model.

[0051] In some examples of the present application, the large language model is selected from at least one of GLM, GPT, and LLaMA.

[0052] In some examples of the present application, the first sub-model is obtained by training in the following manner: obtaining a first medical training set; performing entity recognition on the first medical training set using a deep learning model to obtain medical entity information and medical entity attribute information; and constructing a medical knowledge graph of the medical entity information and medical entity attribute information based on preset triple rules.

[0053] In some examples of the present application, the second sub-model is trained in the following manner: obtaining a second medical training set; and fine-tuning the large language model using the second medical training set based on a low-rank adaptation method.

[0054] In some examples of the present application, it further includes: using the auxiliary diagnosis results to train the consultation model.

[0055] This system can significantly reduce the patient's medical treatment process; improve the accuracy of clinical diagnosis by conducting comprehensive analysis of multivariate data from patients; provide personalized treatment plans based on the patient population to improve treatment outcomes; and transcend geographical restrictions to achieve the sharing and popularization of high-quality medical resources, so that patients in remote areas can also enjoy the same level of medical services as urban patients.

[0056] It should be understood that the above system embodiment and the clinical auxiliary diagnosis method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Figure 2 The system shown can execute the above-mentioned embodiment of the clinical auxiliary diagnosis method, and the operations and / or functions performed by each module in the system correspond to the method embodiment, which will not be described in detail here for the sake of brevity.

[0057] The system of the embodiment of the present application is described above from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or a combination of hardware and software modules in the decoding processor to perform. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.

[0058] Computer program product, computing device, and computer readable storage medium

[0059] In another aspect, the present application proposes a computer program product, a computing device, and a computer-readable storage medium. Based on the aforementioned computer program product, computing device, or computer-readable storage medium, the aforementioned clinical auxiliary diagnosis method is executed.

[0060] This embodiment takes electronic equipment as an example for detailed description.

[0061] The so-called electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Computing devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are intended to be examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0062] like Figure 3 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 502 or a computer program loaded from a storage unit 508 to a RAM (Random Access Memory) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An I / O (Input / Output) interface 505 is also connected to the bus 504.

[0063] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0064] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as a clinical auxiliary diagnosis method. For example, in some embodiments, the clinical auxiliary diagnosis method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the aforementioned clinical auxiliary diagnosis method in any other appropriate manner (eg, by means of firmware).

[0065] In the present application, the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program may be printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or processing in other suitable ways as necessary, and then stored in a computer memory. The various computer-readable storage media described herein may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0066] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0067] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0068] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0069] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0070] Embodiments of the present invention will be described in more detail below, examples of which are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0071] Example 1 Clinical auxiliary diagnosis application example

[0072] This embodiment uses the patient A (target subject) whose main complaint is diarrhea as an example to verify the feasibility of the clinical auxiliary diagnosis method or system of the present application.

[0073] 1) Chief complaint information: diarrhea;

[0074] 2) Input the chief complaint information into the questionnaire model, and the model generates a questionnaire list, including: time of occurrence, frequency of diarrhea (daily, less than 3 times, 3-10 times, 10-20 times), stool characteristics (soft stool, watery, mucous, bloody stool), whether it is persistent pain and pain type (colic, dull pain, stabbing pain, bloating, burning pain), whether family members have the same situation?, whether the following behaviors occurred before the onset of the disease (expired food, drinking, overeating, strenuous exercise, spicy food, overwork), historical medical history, especially related to the intestines, family medical history, allergy history;

[0075] 3) Patient A responds based on the consultation information, as follows:

[0076] Time of occurrence: after meals (before or after meals);

[0077] Frequency of diarrhea (per day): less than 3 times (less than 3 times, 3-10 times, 10-20 times);

[0078] Stool characteristics: watery (soft stool, watery stool, mucous stool, bloody stool);

[0079] Whether it is persistent pain and the type of pain: dull pain (colic, dull pain, stabbing pain, distending pain, burning pain);

[0080] Do any family members have the same situation? No;

[0081] Whether the following behaviors occurred before the onset of the disease: drinking (expired food, drinking, overeating, strenuous exercise, spicy food, overwork)

[0082] Medical history, especially related to the bowel: None

[0083] Family history: None

[0084] Allergy history: None

[0085] 4) Patient A's imaging examination results showed gastric erosion. Laboratory test results were blood routine: elevated white blood cell count; urine and stool routine: both normal; fecal occult blood test: negative.

[0086] The inquiry information results obtained in step 3), as well as the above-mentioned imaging examination results and laboratory examination results are input into the inquiry model, wherein:

[0087] The output results of the first sub-model include: the disease type is acute gastroenteritis, and the appropriate medication types are antidiarrheal drugs (montmorillonite powder), gastric mucosal protective agents (sulfoaluminum sugar), probiotics (Bifidobacterium), and antispasmodic drugs (Belladonna tablets);

[0088] The second sub-model generates the following auxiliary diagnosis report based on the output results of the first sub-model:

[0089] Patient Information:

[0090] Basic information such as specific name and age was not provided.

[0091] Chief complaint:

[0092] Diarrhea, watery stools, less than 3 times a day; diarrhea symptoms occur after drinking, accompanied by abdominal pain.

[0093] History of present illness:

[0094] The patient had diarrhea symptoms in the past week, with watery stools and less than 3 bowel movements per day. He often drank alcohol before diarrhea, which was suspected to be the cause. After examination, it was found that the patient had a gastric ulcer.

[0095] Past history:

[0096] The patient had no history of major surgery, no family history of genetic diseases, and no history of allergies.

[0097] Auxiliary examination results:

[0098] Examination results showed that the patient had a gastric ulcer.

[0099] diagnosis:

[0100] Gastric ulcer: Gastroscopy confirmed that the patient had gastric ulcer, which was the main cause of abdominal pain and indigestion.

[0101] Alcoholic diarrhea: Considering that the patient's diarrhea symptoms are closely related to drinking and the stool is watery, the initial diagnosis is alcoholic diarrhea. The increase in white blood cell count may be related to the inflammatory response caused by gastric ulcers, or it may be related to intestinal infections caused by diarrhea.

[0102] Treatment recommendations:

[0103] For gastric ulcers: it is recommended to use proton pump inhibitors (such as omeprazole) for acid suppression treatment, and at the same time give gastric mucosal protective agents (such as sucralfate) to promote ulcer healing. Patients should quit drinking and smoking, maintain regular eating habits, and avoid eating irritating foods.

[0104] For diarrhea: antidiarrheal drugs (such as montmorillonite powder) and drugs that regulate intestinal flora (such as probiotics) are recommended for treatment. At the same time, patients should supplement with sufficient water and electrolytes to prevent dehydration and electrolyte imbalance.

[0105] Anti-infection treatment: In view of the elevated white blood cell count, antibiotics may be considered for anti-infection treatment, but the specific medication should be determined based on the results of drug sensitivity tests.

[0106] 5) The doctor reviews the diagnostic report information and will refer to the auxiliary diagnostic report to treat the patient after confirming that it is correct. After the treatment is completed, the diagnostic report will be used as new data to supplement the knowledge graph and language model respectively.

[0107] Example 2: Clinical auxiliary diagnosis application example

[0108] This embodiment uses the patient B (target subject) whose main complaint is abdominal pain as an example to verify the feasibility of the clinical auxiliary diagnosis method or system of the present application.

[0109] 1) Chief complaint information: abdominal pain;

[0110] 2) Input the chief complaint information into the medical consultation model, and the model generates a medical consultation list, including: type of pain, whether it is getting worse, whether it is tolerable, whether there is vomiting, bowel movement, whether family members have the same situation?, urine color, whether there is fever, whether there are the following behaviors before the onset of the disease (expired food, drinking, overeating, strenuous exercise, spicy food, overwork), whether there has been a recent visit to the doctor, medication, historical medical history, especially gastrointestinal diseases, family medical history;

[0111] 3) Patient B responds based on the consultation information as follows:

[0112] Pain type: persistent pain, cramping

[0113] Is it getting worse, is it tolerable?: Getting worse, can be tolerated

[0114] Vomiting: No

[0115] Stool condition: normal.

[0116] Does anyone in your family have the same situation?: No

[0117] Urine color: yellow

[0118] Fever: Yes

[0119] Did you have the following behaviors before the onset of the disease: No (expired food, drinking, overeating, strenuous exercise, spicy food, overwork)

[0120] Have you seen a doctor recently, and taken any medications: No

[0121] Medical history, especially gastrointestinal disorders; none

[0122] Family history: None

[0123] 4) Patient A's imaging results showed gastric erosion. Laboratory test results showed that blood routine test: elevated white blood cell count; urine and stool routine test: normal; fecal occult blood test: negative.

[0124] The inquiry information results obtained in step 3), as well as the above-mentioned imaging examination results and laboratory examination results are input into the inquiry model, wherein:

[0125] The output results of the first sub-model include: the disease type is acute gastroenteritis, and the appropriate medication types are antidiarrheal drugs (montmorillonite powder), gastric mucosal protective agents (sulfoaluminum sugar), probiotics (Bifidobacterium), and antispasmodic drugs (Belladonna tablets);

[0126] The second sub-model generates the following auxiliary diagnosis report based on the output results of the first sub-model:

[0127] Patient Information:

[0128] Basic information such as specific name and age was not provided.

[0129] Chief complaint:

[0130] Diarrhea, watery stools, less than 3 times a day.

[0131] Diarrhea symptoms occur after drinking, accompanied by abdominal pain.

[0132] History of present illness:

[0133] The patient reported persistent colic, which gradually worsened but was still tolerable. He did not vomit, had normal bowel movements, yellow urine, and had a fever.

[0134] Past history:

[0135] The patient had no history of major surgery, no family history of genetic diseases, and no history of allergies.

[0136] Auxiliary examination results:

[0137] Examination results showed that the patient had intestinal erosion.

[0138] Initial diagnosis:

[0139] Intestinal erosion.

[0140] Fever to be investigated (may be related to infection or inflammation caused by intestinal erosion)

[0141] Acute enteritis: Although the patient's bowel movements are normal, intestinal erosion may be caused by acute enteritis and needs to be further excluded.

[0142] Treatment recommendations:

[0143] Further examination: It is recommended that patients undergo special examinations such as abdominal CT or MRI.

[0144] Anti-infection treatment: In view of the elevated white blood cell count, antibiotics may be considered for anti-infection treatment, but the specific medication should be determined based on the results of drug sensitivity tests.

[0145] Symptomatic treatment: Before diagnosis, avoid self-use of painkillers to avoid masking the condition. A professional doctor will formulate a treatment plan based on the hospital examination results.

[0146] 5) The doctor reviews the diagnostic report information and will refer to the auxiliary diagnostic report to treat the patient after confirming that it is correct. After the treatment is completed, the diagnostic report will be used as new data to supplement the knowledge graph and language model respectively.

[0147] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0148] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention without departing from the principles and intent of the present invention.

Claims

1. A clinical auxiliary diagnosis method, characterized in that: include: Obtain the target object's medical consultation information results and medical record information; Inputting the medical inquiry information results and medical record information into a trained medical inquiry model to obtain auxiliary diagnosis results; in, The medical consultation information result is obtained in the following manner: Inputting the chief complaint information of the target subject into the trained medical inquiry model to obtain medical inquiry information; The target object answers the medical inquiry information to obtain the medical inquiry information result.

2. The method according to claim 1, characterized in that The target subjects are selected from the group suffering from gastrointestinal discomfort.

3. The method according to claim 2, characterized in that The medical record information at least includes: gastric imaging examination results.

4. The method according to claim 1, characterized in that: The inquiry model includes: A first sub-model is used to obtain medical entity information and medical entity attribute information associated with the chief complaint information; and A second sub-model generates an auxiliary diagnosis result based on the entity information and the medical entity attribute information; Wherein, the first sub-model is selected from the medical knowledge graph; the second sub-model is selected from the large language model; Optionally, the large language model is selected from at least one of GLM, GPT and LLaMA.

5. The method according to claim 4, characterized in that The first sub-model is obtained by training in the following way: Obtain the first medical training set; Using a deep learning model to perform entity recognition on the first medical training set to obtain medical entity information and medical entity attribute information; Based on the preset triple rules, a medical knowledge graph of the medical entity information and medical entity attribute information is constructed.

6. The method according to claim 4, characterized in that The second sub-model is trained by: Obtain a second medical training set; Based on the low-rank adaptation method, the second medical training set is used to fine-tune the large language model.

7. The method according to any one of claims 1 to 6, characterized in that: Further including: The auxiliary diagnosis results are used to train the medical inquiry model.

8. A clinical auxiliary diagnosis system, characterized in that: include: Information collection module, used to obtain the target object's medical information results and medical record information; A diagnostic reasoning module, used to input the medical inquiry information results and medical record information into a trained medical inquiry model to obtain auxiliary diagnosis results; in, The medical consultation information result is obtained in the following manner: Inputting the chief complaint information of the target subject into the trained medical inquiry model to obtain medical inquiry information; The target object answers the medical inquiry information to obtain the medical inquiry information result.

9. A computing device, characterized in that include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program to implement the clinical auxiliary diagnosis method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions or programs, and when the computer instructions or programs are executed on a computer, the clinical auxiliary diagnosis method according to any one of claims 1 to 7 is executed.

Images