Medical teaching and research integrated system based on common bottom layer

Abstract

The invention relates to the technical field related to medical systems, in particular to a medical teaching and research integrated system based on a common bottom layer, and aims to break through information islands among medical treatment, teaching and scientific research and realize closed-loop linkage and dynamic knowledge conversion of a whole process. The system comprises a diagnosis and treatment decision subsystem, a scientific research queue management subsystem and a teaching subsystem, integrates data through a three-in-one data engine, and realizes information sharing and cooperative work. The diagnosis and treatment decision subsystem provides diagnosis and treatment support for severe diseases based on an expert thinking chain. And the scientific research queue management subsystem is responsible for screening cases, sorting data, implementing quality control and statistical analysis, and adjusting an expert thinking chain according to scientific research results. And the teaching subsystem carries out teaching by using a standardized case presentation mode. Through a feedback closed loop of clinical discovery, scientific research verification, knowledge updating and teaching feedback, rapid propagation and application of medical knowledge are promoted, and the medical service quality and the medical education level are improved.

Description

Technical Field

[0001] The present application relates to the technical field related to medical systems, and specifically to an integrated medical, teaching and research system based on a common underlying layer. Background Art

[0002] With the rapid development of medical technology and the continuous advancement of medical information technology, medical institutions have accumulated massive amounts of data in clinical diagnosis and treatment, medical education, and scientific research and innovation. However, this data is currently scattered across different systems and lacks effective integration and sharing mechanisms. This has led to a significant disconnect between medical care, teaching, and scientific research, seriously impacting the quality of medical services and the improvement of medical education and research. Summary of the Invention

[0003] In view of this, the embodiments of the present application are committed to providing an integrated medical, teaching and research system based on a common underlying layer to integrate and share data between medical care, teaching and scientific research work.

[0004] This application provides an integrated medical, teaching and research system based on a common underlying layer, including: The diagnosis and treatment decision-making subsystem is used to provide diagnosis and treatment decision support for preset diseases and syndromes based on the expert thinking chain. Specifically, for each case, based on the collected information, it determines the core indicators related to the disease, guides the user to sort out the information and analyze the disease, automatically generates disease analysis and treatment recommendations, records treatment choices and effect feedback, and automatically reminds whether to include the case in the research cohort when the case meets the preset research cohort conditions, prompts treatment nodes, and visualizes the disease progression; The expert thinking chain is a set of medical processes and medical plans based on historical cases and expert advice; the core indicators are the indicators necessary for judging the condition under the existing diagnosis and treatment plan; The scientific research cohort management subsystem is used to obtain medical information and include cases that meet preset requirements in the medical information into the scientific research cohort; based on the preset structured data set, organize the various cases in the scientific research cohort and desensitize the case information; among which, the structured data set is a general data set or a personalized data set obtained by adjusting based on user input information; assist researchers in generating treatment recommendations and send them to the corresponding clinical physicians to obtain the clinicians' actual treatment choices and effect feedback; eliminate cases that do not meet the requirements in the scientific research cohort; implement quality control and statistical analysis on the data of the scientific research cohort, and access AI tools to query relevant background information, sort out the statistical result framework, and generate data result analysis reports; adjust the expert thinking chain based on the actual scientific research results of the scientific research cohort; the medical information includes: patient medical records, examination and test results and treatment plans during clinical diagnosis and treatment; The teaching subsystem is used to set up preset case presentation methods based on expert thought chains and preset cognitive structures to guide users to form thinking habits for disease analysis and engage in structured thinking. Based on the material sets and case sets obtained from the diagnosis and treatment decision-making subsystem and the scientific research queue management subsystem, teaching materials are generated after standardization and expert-level quality control. Combined with the simulator, it forms a skills training system and a capacity improvement training system. The standardization and expert-level quality control include: conversion to a preset case presentation format and review by preset experts; The simulator is a device used to simulate a patient.

[0005] In some embodiments, the diagnosis and treatment decision subsystem includes: The core indicator preset module is used to pre-set the core indicators required for diagnosis of different diseases and syndromes based on expert experience, and present them to medical staff in a table form on the system interface; The core indicators are those necessary for judging the condition under the existing diagnosis and treatment plan; The information collection and analysis module supports manual input or automatic collection of core information related to disease diagnosis. After the collection is completed, the disease analysis is automatically generated and treatment recommendations are given; The core information is the information necessary to determine the condition under the existing diagnosis and treatment plan; The recording and feedback module is used to record and provide feedback to medical staff on treatment plans and treatment effects; it prompts treatment nodes and visually displays the disease progression; The scientific research cohort reminder module is used to automatically remind whether to include a case in the scientific research cohort when a case meets the preset scientific research cohort conditions.

[0006] In some embodiments, the research queue management subsystem includes: The platform design and dataset editing module is used to provide a general structured dataset or a general scientific research process platform, or to generate a personalized structured dataset or a personalized scientific research process platform based on user configuration; The treatment recommendation and feedback module is used to generate and present treatment recommendations for research cases to researchers; obtain the research treatment recommendations determined by researchers and send them to clinicians; obtain the clinicians' choice of whether to adopt the recommendations and record the clinical behavior and corresponding treatment effects; if the current case does not meet the current research needs, the current case will be eliminated; The data quality control and analysis report generation module is used to perform quality control and statistical analysis on scientific research cohort data online, access AI tools to query relevant background information, sort out the statistical result framework, and generate data result analysis reports; The expert thinking chain adjustment module is used to regularly evaluate and optimize the diagnosis and treatment processes and plans in the expert thinking chain based on scientific research results and expert opinions.

[0007] In some embodiments, the teaching subsystem includes: Standardized presentation setting module: set preset case presentation methods based on expert thinking chains and preset cognitive architecture; Material and case collection management module: stores a preset number of material and case collections generated by the diagnosis and treatment decision subsystem and the scientific research queue management subsystem, and uses them as teaching materials after standardization and expert-level quality control; Training system generation module: Combined with the simulator to generate skill training system and capability improvement training system; AI automatic recognition and quality control platform generation module: annotates a preset number of medical images and text materials, and trains AI models to achieve automatic recognition and quality control.

[0008] In some embodiments, further comprising a trinity data engine; The trinity data engine uses optical character recognition technology and natural language processing technology to identify and analyze medical record texts, extract key information such as disease names and symptom descriptions, and store expert thinking chains in the form of data structures in the system database for call by the diagnosis and treatment decision-making subsystem and the scientific research queue management subsystem; it is also used to bind clinical cases with expert thinking chains and scientific research conclusions, generate diagnosis and treatment guidelines and teaching cases, provide real-time patient condition data and expert advice to the diagnosis and treatment decision-making subsystem, provide structured scientific research data sets to the scientific research queue management subsystem, and provide teaching cases and materials to the teaching subsystem.

[0009] In some embodiments, the trinity data engine is also used to update the diagnosis and treatment processes and plans in the expert thinking chain in real time according to the treatment effect data in clinical feedback and the statistical analysis data in scientific research results, in accordance with preset update rules and algorithms, and to adjust the diagnosis and treatment guidelines and teaching cases in accordance with the expert opinions.

[0010] In some embodiments, the diagnosis and treatment decision subsystem further includes a behavior guidance and compliance monitoring module; The behavior guidance and compliance monitoring module is used to compare the deviation between the doctor's behavior and the expert's thinking chain. If the deviation is greater than the preset value, an early warning is triggered. Through the system's built-in authority management and approval process monitoring module, the data usage and ethical approval status are recorded in real time.

[0011] In some embodiments, the case presentation method includes: The system integrates the patient's full-cycle diagnosis and treatment trajectory according to the timeline, combining the seven key steps of patient admission to the hospital / department, preliminary examination and diagnosis after information collection, treatment plan formulation, observation of the treatment process, evaluation and feedback of changes in the condition, adjustment of the treatment plan, and patient discharge from the hospital / department. It sorts out the development process of the disease, presents the content of each time point based on the preset format, and shows the changing trend of the core indicators in the case over time, reflecting the changing trend of the disease and the direction of treatment.

[0012] In some embodiments, the scientific research queue management subsystem is also used to use data mining and machine learning algorithms to automatically analyze medical data, identify abnormal data patterns and potential correlations, and propose scientific research hypotheses based on the characteristics and distribution patterns of abnormal data, combined with medical knowledge and expert experience, and generate corresponding scientific research project proposals.

[0013] The present application provides an integrated medical, teaching and research system based on a common underlying layer, a diagnosis and treatment decision-making subsystem, which is used to provide diagnosis and treatment decision support for preset diseases and syndromes based on the expert thinking chain, specifically including: for each case, based on the collected information, judging various indicators related to the disease, guiding the user to sort out the information and analyze the disease, automatically generating disease analysis and treatment suggestions, recording treatment choices and effect feedback, and automatically reminding whether to include the case in the scientific research cohort when the case meets the preset scientific research cohort conditions; wherein, the expert thinking chain is a set of medical processes and medical plans constructed based on historical cases and expert suggestions; the scientific research cohort management subsystem is used to obtain medical information and include cases that meet the preset requirements in the medical information into the scientific research cohort; based on the preset structured data set, organize the various cases in the scientific research cohort and desensitize the case information; wherein, the structured data set is a general data set or a data set based on user input information. The personalized data set obtained after the integration; assist scientific researchers in generating treatment recommendations and send them to corresponding clinical physicians to obtain the actual treatment choices and effect feedback of clinical physicians; eliminate cases that do not meet the requirements of the scientific research cohort; implement quality control and statistical analysis on the data of the scientific research cohort, and access AI tools to query relevant background information, sort out the statistical result framework, and generate a data result analysis report; adjust the expert thinking chain based on the actual scientific research results of the scientific research cohort; the medical information includes: patient medical records, examination and test results, and treatment plan teaching subsystems in the clinical diagnosis and treatment process, which are used to set preset case presentation methods based on expert thinking chains and preset cognitive architectures, and guide users to develop thinking habits and structured thinking for disease analysis; based on the material sets and case sets obtained from the diagnosis and treatment decision-making subsystem and the scientific research cohort management subsystem, teaching materials are generated after standardization and expert-level quality control, and combined with the simulator to generate skill training systems and capacity improvement training systems. With such a configuration, the present application provides an integrated medical, teaching and research system based on a common underlying layer. By integrating diagnosis and treatment decision-making, scientific research cohort management and teaching functions, it realizes the deep integration and collaborative work of medical care, teaching and scientific research, and has the following significant beneficial effects: Improving the efficiency and quality of diagnosis and treatment: The diagnosis and treatment decision-making subsystem is based on the expert thinking chain, which can quickly judge indicators and generate treatment recommendations, standardize clinical behavior, reduce the risk of misdiagnosis and mistreatment, and improve the accuracy and timeliness of diagnosis and treatment of serious diseases. Promoting scientific research innovation and transformation: The scientific research cohort management subsystem realizes automatic screening of cases, data collation and quality control analysis, and improves scientific research efficiency and quality. The scientific research results are fed back to the diagnosis and treatment decision-making system, optimizing the expert thinking chain and accelerating the transformation and application of scientific research results into clinical practice. Optimizing medical education resources and effects: The teaching subsystem uses standardized cases and expert-level quality control materials, combined with simulation technology, to build an interactive teaching environment, cultivate medical students' clinical thinking and practical ability, improve the quality and effect of medical education, and realize the dynamic update of teaching content.Break down information silos and achieve data sharing and collaboration: Based on a common underlying architecture, the system integrates medical, teaching, and scientific research data, breaks down information barriers between fields, achieves seamless data sharing and interaction, provides strong data support for the integration of medical care, teaching, and research, and promotes the coordinated development of medical services and medical education and research. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0015] Figure 1 This is a structural diagram of an integrated medical, teaching and research system based on a common underlying layer provided by an embodiment of the present application. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0017] Figure 1 This is a schematic diagram of the structure of the medical, teaching and research integration system based on a common bottom layer provided by an embodiment of the present application. Figure 1 As shown, the integrated medical, teaching and research system based on a common underlying layer includes: Diagnosis and Treatment Decision-Making Subsystem 1 is used to provide diagnosis and treatment decision support for pre-set diseases and syndromes (pre-set diseases and syndromes are generally common severe diseases and syndromes recognized by the medical community) based on the expert thinking chain. Specifically, it includes: for each case, based on the collected information, it determines various indicators related to the disease, guides the user to sort out the information and analyze the disease, automatically generates disease analysis and treatment recommendations, records treatment choices and effect feedback, and automatically reminds whether to include the case in the research cohort when the case meets the pre-set research cohort conditions; Among them, the expert thinking chain is a collection of medical processes and medical plans based on historical cases and expert advice; The scientific research cohort management subsystem 2 is used to obtain medical information and include cases that meet preset requirements in the medical information into the scientific research cohort; based on the preset structured data set, organize the various cases in the scientific research cohort and desensitize the case information; where the structured data set is a general data set or a personalized data set obtained by adjusting based on user input information; assist researchers in generating treatment recommendations and send them to the corresponding clinical physicians to obtain the clinicians' actual treatment choices and effect feedback; eliminate cases that do not meet the requirements in the scientific research cohort; implement quality control and statistical analysis on the data of the scientific research cohort, and access AI tools to query relevant background information, sort out the statistical result framework, and generate data result analysis reports; adjust the expert thinking chain based on the actual scientific research results of the scientific research cohort; the medical information includes: patient medical records, examination and test results, and treatment plans during clinical diagnosis and treatment; Teaching subsystem 3 is used to set preset case presentation methods based on expert thinking chains and preset cognitive architecture, guiding users to form thinking habits for disease analysis and conduct structured thinking; based on the material sets and case sets obtained from the diagnosis and treatment decision-making subsystem and the scientific research queue management subsystem, teaching materials are generated after standardization and expert-level quality control, and combined with the simulated person to generate a skill training system and a capacity improvement training system.

[0018] The standardization and expert-level quality control include: conversion to a preset case presentation format and review by preset experts; The preset case presentation method is a standardized and structured case display format designed based on the expert thinking chain (a collection of medical processes and plans constructed from historical cases and expert advice) and the preset cognitive architecture.

[0019] The specific presentation logic is: integrating the patient's full-cycle diagnosis and treatment trajectory according to the timeline, covering 7 key steps: patient admission to the hospital / department, preliminary examination and diagnosis after collecting information, treatment plan formulation, observation of the treatment process, assessment and feedback of changes in the condition, adjustment of the treatment plan, and patient discharge from the hospital / department.

[0020] Presentation requirements: The content of each time point should be structured and standardized according to the preset format, focusing on showing the changing trends of core indicators (such as vital signs, laboratory test results, etc.) over time, and intuitively reflecting the changes in the condition and treatment direction.

[0021] Review by preset experts: The review body is the system's preset expert team, which is composed of medical experts with rich clinical experience, teaching experience and scientific research background.

[0022] The review content includes: whether the presentation of the converted case meets the preset standards, whether the core information in the case (such as condition analysis, treatment recommendations, data logic, etc.) is accurate and complete, and whether it complies with the latest medical guidelines and expert consensus.

[0023] Purpose of review: To ensure the scientificity, standardization and practicality of teaching materials and to provide a high-quality case basis for medical teaching.

[0024] Manikins are specialized medical devices used to simulate patients, offering highly realistic simulations of physiological and pathological conditions. Within the teaching subsystem, manikins are combined with standardized teaching materials to create both skill-building and competency-enhancing training systems. Learners can use the manikins to conduct realistic clinical practice exercises, such as physical examinations, punctures, and first aid, to enhance their clinical skills.

[0025] The simulator can be combined with AI, VR / MR and other technologies to achieve interactive, virtual reality training effects, enhancing the immersiveness and practicality of teaching.

[0026] The diagnosis and treatment decision-making subsystem is a core component of the integrated medical, teaching and research system based on a common underlying layer, and is designed to provide diagnosis and treatment decision support for diseases and syndromes. By integrating expert experience and the latest medical knowledge, the system constructs an expert thinking chain to provide comprehensive diagnosis and treatment assistance to medical staff. Its main functions include: Core indicator judgment: For each case, based on the collected information, the core indicators related to the condition are judged. Information sorting and condition analysis: Guide users to sort information and analyze the condition. Automatic generation of condition analysis and treatment recommendations: Automatically generate condition analysis and treatment recommendations based on preset rules and expert thinking chains. Record treatment choices and effect feedback: Record the medical staff's treatment plan and the patient's treatment effect. Scientific research cohort reminder: When a case meets the preset scientific research cohort conditions, it automatically reminds whether to include the case in the scientific research cohort.

[0027] Specifically, core indicators typically include, but are not limited to, vital signs (such as temperature, blood pressure, heart rate, etc.), laboratory test results (such as blood routine, biochemical indicators, etc.), imaging test results (such as X-rays, CT, MRI, etc.), and other clinical manifestations closely related to the condition. For example, oxygen metabolism indicators (such as Lac, ScvO2) and perfusion indicators (such as mottling, PI) for patients in shock. These indicators are determined based on expert experience, through the collection and analysis of large amounts of historical case data and expert clinical experience, and have undergone rigorous review and verification by a team of experts to ensure their scientific and practical application. The system will display these core indicators in a prominent position on the interface in table format. The table not only lists the indicator name, but may also include information such as normal ranges and abnormal prompts, allowing medical staff to quickly view, reference, and diagnose the condition.

[0028] The diagnosis and treatment decision subsystem 1 includes: The core indicator preset module 11 is used to pre-set the core indicators required for the diagnosis of different diseases and syndromes based on expert experience, and present them to medical staff in a table form on the system interface; Core indicators are medical parameters that must be focused on when diagnosing and treating a specific disease or syndrome. These indicators typically include, but are not limited to, vital signs (such as temperature, blood pressure, and heart rate), laboratory test results (such as blood tests and biochemical parameters), imaging test results (such as X-rays, CT scans, and MRIs), and other clinical manifestations closely related to the condition. Core indicators for each disease or syndrome are determined by collecting and analyzing extensive historical case data and expert clinical experience. These indicators are rigorously reviewed and validated by a team of experts to ensure their scientific and practical application. The system displays these core indicators in a prominent tabular format within the interface for quick review and reference by medical staff. The table not only lists the indicator name but may also include information such as normal ranges and abnormality indicators to help medical staff better understand and apply these indicators.

[0029] By defining core indicators, medical staff can more accurately identify and assess conditions, reducing the risk of misdiagnosis and missed diagnoses. This ensures that medical staff adhere to standardized procedures during diagnosis, improving both efficiency and quality. By embedding expert experience in the system as core indicators, it facilitates learning and reference for young doctors, ultimately improving the overall performance of the medical team.

[0030] The information collection and analysis module 12 is used to support manual input or automatic collection of core information related to the diagnosis of the disease, automatically generate a disease analysis after the collection is completed, and give treatment suggestions based on the preset conditions; Core information is clearly defined as the information necessary to determine the condition under the existing diagnosis and treatment plan. It is the key basis for supporting diagnosis and treatment decisions and condition analysis. Its specific characteristics are as follows: Directly related to "core indicators" (key medical parameters for judging the condition, such as vital signs, laboratory test results, etc.), it is various types of information centered around the core indicators and used to accurately judge the condition.

[0031] Core information includes, but is not limited to, the patient's symptoms, medical history (e.g., past medical history, allergies), detailed description of test results, treatment response, etc. For example, for patients with shock, in addition to core indicators such as oxygen metabolism (Lac, ScvO2) and perfusion indicators (mottling, PI), information such as the cause of shock, duration, and response to initial treatment are also considered core information.

[0032] Core information acquisition methods: It can be obtained through manual input by medical staff (such as entering patient symptoms and medical history) or automatic collection by the system (such as synchronizing laboratory reports and imaging results from the hospital information system).

[0033] The core role of core information: It is the key input of the system's "information collection and analysis module". Based on the core information and the expert thinking chain, the module automatically generates disease analysis and treatment recommendations, providing a basis for clinical diagnosis and treatment decisions.

[0034] The system supports multiple information collection methods, including manual input and automatic collection. Manual input allows medical staff to enter patient information such as medical history, symptoms, and test results based on actual circumstances. Automatic collection, through integration with hospital information systems (such as electronic medical records, laboratory information systems, and imaging systems), automatically obtains real-time patient data, reducing medical staff workload. The system analyzes and processes the collected information based on pre-set rules and expert thought processes. First, core indicators are evaluated to determine whether they are within normal ranges. Then, considering the patient's medical history, symptoms, and other relevant factors, a condition analysis report is generated. Based on the condition analysis results, the system further provides treatment recommendations, including medication, surgery, and rehabilitation. Pre-set rules are a series of logical judgment rules developed based on expert experience and medical guidelines, guiding the system's analysis of the condition and generating treatment recommendations. The expert thought process is a more complex decision-making model that simulates the expert's thought process during diagnosis and treatment, taking into account the interplay and influence of multiple factors.

[0035] Automated information collection and analysis significantly reduces the time medical staff spend manually processing data, improving diagnosis and treatment efficiency. Condition analysis and treatment recommendations based on expert thought chains provide more scientific and comprehensive diagnosis and treatment plans, helping to improve treatment outcomes. This provides strong decision-making support for medical staff, especially when faced with complex or difficult cases, enabling them to make more accurate judgments quickly.

[0036] The recording and feedback module 13 is used to record and provide feedback to medical staff on treatment plans and treatment effects; prompt treatment nodes and visually display the disease progression process; The system records in detail the treatment plans developed by medical staff for patients, including information such as drug name, dosage, route of administration, treatment duration, and the specific surgical procedures and steps. Medical staff can provide feedback to the system on the patient's treatment outcomes, including symptom improvement, changes in laboratory test results, and comparisons of imaging findings. The system also automatically collects patient follow-up data to provide an objective assessment of treatment effectiveness.

[0037] By recording and analyzing treatment outcomes, medical staff can promptly assess the effectiveness of treatment plans, adjust treatment strategies, and improve treatment outcomes. The system's recording and feedback capabilities provide data support for medical quality assessments, helping medical institutions continuously optimize medical service processes and improve overall medical service quality.

[0038] Prompt medical staff of key treatment milestones to ensure standardized and timely treatment. Key treatment milestones, such as medication adjustment times, follow-up times, and surgery times, are preset based on disease characteristics and treatment plans. When approaching preset treatment milestones, the system automatically sends reminders to medical staff to ensure timely implementation of treatment measures. Dynamically adjust treatment milestones based on the patient's treatment outcome and condition changes, ensuring flexibility and adaptability of treatment plans.

[0039] Visualizing the progression of a disease helps medical professionals and patients better understand its progression. A timeline displays the patient's condition, including symptom onset, examination time, and treatment duration, enabling medical professionals to clearly understand the progression of the disease. Combining multi-dimensional data such as laboratory and imaging results, charts and graphs illustrate disease trends, such as blood pressure curves and tumor volume changes. Comparative analysis of data at different time points helps medical professionals assess treatment effectiveness and adjust treatment plans in a timely manner.

[0040] The scientific research cohort reminder module 14 is used to automatically remind whether to include the case into the scientific research cohort when there is a case that meets the preset scientific research cohort conditions.

[0041] The research cohort conditions are pre-set based on the research objectives and requirements of the research project, and typically include multi-dimensional conditions such as the patient's disease type, severity of the condition, treatment method, and treatment effect. These conditions are stored in the system as rules and are used to screen cases that meet the requirements. The system monitors patient case information in real time and automatically sends reminder notifications to medical staff when a case that meets the research cohort conditions is found. Reminder notifications can be sent through various methods such as system interface pop-ups, text messages, and emails to ensure that medical staff receive reminder information in a timely manner. After receiving the reminder, medical staff can decide whether to include the case in the research cohort based on the actual situation. Cases included in the research cohort will serve as research subjects for the research project and provide data support for scientific research work.

[0042] Automated case screening and reminder functions significantly improve the efficiency of research cohort construction, reduce the workload of researchers for manual case screening, and accelerate the progress of research projects. System-screened cases that meet pre-defined research cohort criteria ensure the quality and consistency of research data and enhance the reliability of research results. The research cohort reminder module not only facilitates research work but also provides feedback and guidance for clinical practice, promoting the coordinated development of clinical and research practices and advancing medical progress. The diagnosis and treatment decision-making subsystem provides comprehensive diagnosis and treatment decision-making support for medical staff through functional modules such as core indicator presetting, information collection and analysis, recording and feedback, and research cohort reminders. This not only improves the efficiency and quality of diagnosis and treatment, promotes the close integration of clinical and research practices, and provides strong support for improving medical service quality and optimizing medical education. The research cohort management subsystem is a key component of the integrated medical, educational, and research system based on a common underlying infrastructure. It aims to efficiently manage and utilize medical information to support the smooth progress of research projects. The system implements comprehensive management of research cohorts through the following functional modules: Case Inclusion and Organization: This system acquires medical information, screens cases that meet pre-defined requirements for inclusion in the research cohort, and organizes and desensitizes them based on structured datasets. Treatment Recommendations and Feedback: Assists researchers in generating treatment recommendations, sends them to clinicians, and obtains feedback on actual treatment choices and outcomes. Case Elimination: Eliminates cases that do not meet research requirements. Data Quality Control and Analysis: Implements quality control and statistical analysis, integrates AI tools to query relevant background information, and generates data analysis reports. Expert Thought Chain Adjustment: Adjusts expert thought chains based on research results and expert opinions.

[0043] The scientific research queue management subsystem 2 includes: a platform design and data set editing module 21, which is used to provide a general structured data set or a general scientific research process platform, or generate a personalized structured data set or a personalized scientific research process platform according to user configuration; the details are as follows: Common structured datasets: Pre-set standardized datasets that cover the basic data structures of common diseases and syndromes and are suitable for most scientific research projects.

[0044] Personalized dataset generation: Based on specific scientific research needs input by users, such as studying specific disease subtypes or the effects of specific treatment options, general datasets are adjusted and customized to generate personalized structured datasets.

[0045] General scientific research process platform: provides a standardized scientific research process framework, including case screening, data collection, quality control analysis and other links, to ensure the standardization and consistency of scientific research projects.

[0046] Personalized scientific research process platform: allows users to customize and optimize general scientific research processes according to the special requirements of specific scientific research projects, thereby improving scientific research efficiency and quality.

[0047] This setup meets the individual data and process requirements of different research projects, enhancing the flexibility and adaptability of research. By providing standardized data sets and process frameworks, it ensures the standardization and scientific nature of research projects. It also provides researchers with powerful tools and support, fostering innovation and breakthroughs.

[0048] The treatment suggestion and feedback module 22 is used to generate and display treatment suggestions for research cases to researchers; obtain the research treatment suggestions determined by researchers and send the research treatment suggestions to clinical physicians; obtain the clinical physicians' choice of whether to adopt and record the clinical behavior and corresponding treatment effect feedback; if the current case does not meet the current research needs, the current case will be eliminated; Based on pre-defined expert thought processes and research objectives, targeted treatment recommendations are generated for each case included in the research cohort. These recommendations may include medications, surgical procedures, rehabilitation plans, and more. Researchers make decisions based on the treatment recommendations and send the finalized recommendations to clinicians. Clinicians then decide whether to adopt the recommendations based on the actual situation and record the actual treatment choice and feedback on the treatment effects. If, during the research process, a case is found to be incompatible with research requirements, such as a treatment plan that does not align with the research objectives or significant data missing, the system will automatically prompt researchers to remove the case to ensure the quality and consistency of the research cohort.

[0049] Specific intelligent management of scientific research queues includes: Dynamic enrollment: Automatically screen eligible patients based on research objectives (e.g., "The value of lung ultrasound in analyzing and predicting common causes of acute respiratory failure"); The system presets the conditions for inclusion in the scientific research cohort. When the conditions of the patient undergoing clinical diagnosis and treatment are met, the system automatically reminds whether to include him / her in the corresponding scientific research cohort, and at the same time reminds and screens the corresponding exclusion criteria. During the scientific research cohort process, if the exclusion conditions are met, a real-time reminder will be given whether to exclude the cohort. Ultimately, the platform user will determine whether to include him / her in the cohort or exclude him / her, and the user behavior and the exclusion conditions involved will be recorded simultaneously.

[0050] Data enrichment: linking patient genomic data, follow-up records, and imaging features to generate research-ready datasets; Manually input / automatically capture the patient's medical history description, laboratory tests, imaging examinations and other indicators during the treatment process, Risk monitoring: Real-time detection of missing or abnormal data (such as dropout follow-up) and triggering automatic reminders.

[0051] The system sets required and optional items. If the required items are not filled in, an automatic reminder will be displayed. You can proceed to the next step only after filling in all the items. At the same time, if the filled-in value exceeds the preset range during the actual filling process, an automatic reminder will be triggered for verification, and the normal range will be prompted.

[0052] Transformation and update: Update the expert thinking chain based on the results of the scientific research cohort, and further generate new scientific research cohort recommendations to verify their superiority.

[0053] This automated process reduces the workload for researchers and clinicians, improving research efficiency. Real-time feedback on treatment outcomes is captured and recorded, ensuring the accuracy and completeness of research data. This strengthens communication and collaboration between researchers and clinicians, promoting the clinical application of research findings.

[0054] Data quality control and analysis report generation module 23 is used to perform quality control and statistical analysis on scientific research cohort data online, access AI tools to query relevant background information, sort out the statistical result framework, and generate data result analysis reports; Conduct real-time monitoring and quality control of research cohort data to ensure accuracy, completeness, and consistency. Quality control includes data format checks, outlier detection, and data integrity verification. Analyze research data using statistical methods, including descriptive statistics, correlation analysis, and hypothesis testing, to uncover patterns and trends within the data. Access AI tools such as natural language processing (NLP) and machine learning to query relevant background information, such as literature and guideline recommendations, to provide richer references for data analysis. Generate structured data analysis reports based on statistical analysis results, including charts, text descriptions, and more, to facilitate rapid understanding and application by researchers.

[0055] In this way, AI tools and professional statistical methods improve the accuracy and reliability of data analysis. Automatically generating analysis reports reduces the time researchers spend manually organizing and analyzing data, accelerating the research process. Presenting analysis results in reports facilitates sharing and communication within the research team, promoting the dissemination and application of knowledge.

[0056] The Expert Thinking Chain Adjustment Module 24 is responsible for regularly evaluating and optimizing the diagnostic and treatment processes and plans within the Expert Thinking Chain based on research results and expert opinions. It regularly collects and analyzes data from research cohorts to assess the effectiveness and limitations of existing Expert Thinking Chains. It organizes expert teams to discuss and analyze research results and provide optimization recommendations. Based on research results and expert opinions, it adjusts and optimizes the diagnostic and treatment processes and plans within the Expert Thinking Chain to ensure they consistently reflect the latest medical knowledge and clinical practices.

[0057] The goal is to continuously optimize expert thought processes to improve the scientific nature and accuracy of diagnosis and treatment decisions. This will enable timely translation of scientific research findings into clinical practice, promoting the updating and dissemination of medical knowledge. This will accelerate the application of scientific research findings in clinical diagnosis and treatment, improving the efficiency of scientific research translation.

[0058] The research cohort management subsystem provides comprehensive support for research projects through functional modules such as platform design and dataset editing, treatment recommendations and feedback, data quality control and analysis report generation, and expert thought chain coordination. It not only improves research efficiency and quality, promotes the close integration of clinical practice and research, but also provides strong support for the updating and dissemination of medical knowledge.

[0059] Teaching Subsystem 3 is a key component of the integrated medical, teaching, and research system based on a common foundation. It aims to provide high-quality medical education resources and cultivate the clinical thinking and practical skills of medical staff by integrating expert experience and clinical practice. This system provides comprehensive support for medical education through the following functional modules: Specifically, based on expert thought chains and a pre-set cognitive architecture, a standardized and structured case presentation method is established to guide users in developing analytical thinking habits and engaging in structured thinking. Teaching materials are generated using material and case collections obtained from the diagnosis and treatment decision-making subsystem and the scientific research cohort management subsystem, standardized, and subject to expert-level quality control. This is combined with a simulator to generate skill training and capacity building training systems. A preset number of medical images and text materials are annotated, and an AI model is trained for automatic recognition and quality control, improving the quality and accuracy of teaching materials.

[0060] Standardized presentation setting module 31: Setting the preset case presentation method based on the expert thinking chain and the preset cognitive framework; The Expert Thinking Chain is a collection of medical processes and plans based on historical cases and expert advice. It simulates the expert's thought process during diagnosis and treatment, taking into account the interaction and influence of multiple factors. The pre-set cognitive framework is designed based on the goals and requirements of medical education, aiming to guide learners in developing a systematic clinical thinking model. It includes the steps of disease analysis, identification of core indicators, and diagnostic reasoning methods.

[0061] The system presents case information in a standardized and structured form (i.e., preset case presentation method), such as through flow charts, tables, timelines, etc., so that learners can clearly understand and master the logic and methods of disease analysis.

[0062] Through standardized case presentations, learners are guided to develop systematic clinical thinking patterns and improve their ability to analyze conditions and conduct diagnostic reasoning. Structured presentations enable learners to quickly grasp key information, improving learning efficiency. Standardized presentations facilitate the dissemination and sharing of knowledge, promoting the standardization of medical education.

[0063] The behavior guidance driven by the expert thinking chain is as follows: Real-time guidance for diagnosis and treatment: The system presets the diagnosis and treatment framework according to different clinical scenarios and clinical problems, including the information to be collected, the results of information interpretation and diagnosis and treatment decision-making recommendations, guiding users to collect and sort out information, interpret information thinking paths, and give corresponding treatment decision-making recommendations, especially for critical treatments.

[0064] If a patient in shock is in the emergency stage, the system automatically recommends the immediate use of vasoactive drugs to maintain vital signs. Emergency blood gas analysis will determine whether there are any factors that may cause the condition to worsen or even cardiac arrest in a short period of time. Simultaneously, the cause of shock will be quickly determined through examination methods such as critical ultrasound for further treatment. After stabilizing vital signs, further detailed evaluation will be carried out to optimize subsequent treatment, such as completing the patient's oxygen metabolism, perfusion, flow and anterior and posterior obstruction, body response and primary cause evaluation and treatment recommendations. If a patient with acute brain injury has anisocoria, which indicates brain herniation, the first thing to do is to quickly establish an artificial airway, emergency infiltration treatment and synchronously call a specialist for surgical treatment. If it is simple intracranial hypertension, it is necessary to evaluate and treat the systemic circulation and perfusion, local brain circulation and perfusion, brain oxygen metabolism, and EEG function.

[0065] For example, patients with shock need to display oxygen metabolism indicators such as Lac and ScvO2, perfusion indicators such as mottling and PI, flow such as CO and GAP, forward obstruction such as nasopharyngeal artery spectrum and RI, backward return resistance such as hepatic vein spectrum and portal vein spectrum, body response indicators such as inflammatory indicators, coagulation indicators, ultrasound cardiopulmonary drive status, cardiac stress balling, etc., as well as possible primary disease types such as infection. Fever, purulent sputum, and CT consolidation often indicate the presence of lung infection.

[0066] If there is oxygen metabolism imbalance, low perfusion, insufficient flow, low volume, high power, high drive, and decreased hemoglobin, it is recommended to supplement volume while matching blood for transfusion and finding the bleeding site to stop bleeding.

[0067] Material and case collection management module 32: stores a preset number of material collections and case collections generated by the diagnosis and treatment decision subsystem and the scientific research queue management subsystem, and uses them as teaching materials after standardization and expert-level quality control; The training system generation module 33 is combined with the simulated human to generate a skill training system and a capability improvement training system; A simulated human is a highly realistic medical training device that can simulate the physiological and pathological states of real patients. By combining with the simulated human, learners can train clinical skills in a nearly real environment. The system combines standardized cases and teaching materials with simulated human technology to generate an interactive skill training system. Learners can perform actual operations on the simulated human according to case prompts, such as physical examination, puncture operation, surgery simulation, etc. In addition to skill training, the system also provides ability enhancement training, including clinical decision-making ability, team collaboration ability, communication ability, and other aspects of training.

[0068] By simulating real clinical environment, the clinical practice ability and operation skills of learners are improved. The interactive training method enhances the learners' sense of participation and experience, improves learning interest and effect. In addition to clinical skills, the comprehensive ability of learners is also cultivated, such as clinical decision-making ability, team collaboration ability, etc.

[0069] AI automatic identification and quality control platform generation module 34: label a preset number of medical images and text materials, train AI model to realize automatic identification and quality control, improve the quality and accuracy of teaching materials.

[0070] Label a preset number of medical images and text materials, including disease name, symptom description, examination result, etc. Key information. Use these labeled data to train AI model to automatically identify and extract key information. The trained AI model can automatically identify and extract key information from medical images and text, improving the efficiency and accuracy of data processing. AI model can also control the quality of teaching materials, check the integrity and accuracy of data, and correct errors in time.

[0071] Automatic identification and processing function greatly improves the efficiency of data processing, reduces the workload of manual labeling and auditing. Through the quality control of AI model, the accuracy and reliability of teaching materials are ensured, and the teaching quality is improved. Intelligent technology is introduced into medical education, promoting the modernization and intelligent development of medical education.

[0072] The teaching subsystem provides comprehensive support for medical education through standardized presentation settings, material set and case set management, skill training system generation, and AI automatic identification and quality control function modules. It not only enriches medical education resources, improves teaching quality and learning efficiency, but also cultivates the clinical thinking and practical ability of medical personnel, promotes the standardization and intelligent development of medical education.

[0073] In some embodiments, based on the common bottom medical education research integration system, it also includes a trinity data engine 4; The trinity data engine uses optical character recognition (OCR) technology and natural language processing (NLP) technology to identify and analyze medical record texts, extract key information such as disease names and symptom descriptions, and store expert thinking chains in the form of data structures in the system database for call by the diagnosis and treatment decision-making subsystem and the scientific research cohort management subsystem; it is also used to bind clinical cases with expert thinking chains and scientific research conclusions, generate diagnosis and treatment guidelines and teaching cases, provide real-time patient condition data and expert advice to the diagnosis and treatment decision-making subsystem, provide structured scientific research data sets to the scientific research cohort management subsystem, and provide teaching cases and materials to the teaching subsystem.

[0074] The Trinity Data Engine is the core technology module of the integrated medical, teaching, and research system, built on a common foundation. It integrates optical character recognition (OCR) and natural language processing (NLP) technologies to achieve efficient recognition and in-depth analysis of medical records. This engine not only extracts key information but also provides powerful data support and intelligent decision-making for each subsystem of the system through data structuring and storage of expert thought processes.

[0075] Further, Optical character recognition (OCR) technology recognizes medical record text, converting the text within the image into editable, searchable electronic text. Detailed instructions are as follows: De-noising, binarization, and skew correction are performed on the medical record image to improve recognition accuracy. Advanced OCR algorithms are used to identify text within the image, supporting multiple fonts and formats. Spell checking and contextual analysis are performed on the recognition results to further improve text accuracy and readability.

[0076] Natural Language Processing (NLP) technology: This technology conducts in-depth analysis of electronic text after OCR recognition to extract key information, such as disease names and symptom descriptions. Detailed instructions are as follows: Electronic text undergoes preprocessing operations, including word segmentation, part-of-speech tagging, and named entity recognition. Using machine learning and deep learning algorithms, it identifies and extracts key information from the text, such as disease names, symptom descriptions, and test results. Contextual analysis and semantic understanding ensure the accuracy of the extracted information.

[0077] Data Structuring and Storage: The extracted key information is stored in the system database as a data structure for access by various subsystems. Detailed instructions are as follows: Design a suitable data structure, such as a relational database table structure, to store the extracted key information. Store the structured data in the system database to ensure data security and accessibility. Establish data indexes to improve data query and retrieval efficiency.

[0078] Expert thought chain storage and access refers to storing expert thought chains in the system database as a data structure, making them available for access by the diagnosis and treatment decision-making subsystem and the scientific research queue management subsystem. The details are as follows: Experts' diagnostic and treatment experience and thought processes are converted into executable rules and models. The expert thought chain model is stored in the database to ensure accessibility and scalability. The diagnosis and treatment decision-making subsystem and the scientific research queue management subsystem can access the expert thought chain in real time to obtain diagnosis and treatment recommendations and scientific research guidance.

[0079] Bind clinical cases with expert reasoning and scientific research conclusions to generate diagnostic and treatment guidelines and teaching cases. Specifically, key information from clinical cases is associated and bound with expert reasoning and scientific research conclusions. Based on this bound data, personalized diagnostic and treatment guidelines are generated to support clinical decision-making. This bound data is converted into teaching cases, providing rich teaching materials for the teaching subsystem.

[0080] Specifically, it provides real-time patient condition data and expert advice to the diagnosis and treatment decision-making subsystem. This data is pushed to the diagnosis and treatment decision-making subsystem to ensure the timeliness and accuracy of the information. Based on the expert's chain of thought, it provides scientific diagnosis and treatment advice to the diagnosis and treatment decision-making subsystem, assisting medical staff in making more accurate decisions.

[0081] Provides structured research datasets for the research cohort management subsystem. Organizes extracted and structured data into research datasets to support the smooth progress of research projects. Performs quality control on research datasets to ensure data accuracy and completeness.

[0082] Provide teaching cases and materials for the teaching subsystem. Transform clinical cases into teaching cases to enrich the teaching resources of the teaching subsystem. Provide high-quality medical images and text materials to support skill training and capacity building of the teaching subsystem.

[0083] This setup improves data processing efficiency. Through OCR and NLP technologies, efficient recognition and in-depth analysis of medical record texts are achieved, reducing the workload of manual processing. Through data structuring and the storage of expert thought processes, data accuracy and reliability are ensured, improving overall system performance. This promotes the integration of medical care, education, and research, providing strong data support for diagnosis and treatment decisions, scientific research management, and teaching and training, fostering the deep integration of medical care, education, and research. It also promotes intelligent healthcare, introduces advanced technologies, drives the intelligent development of the medical system, and improves the quality and efficiency of medical services.

[0084] The Trinity Data Engine integrates OCR and NLP technologies to efficiently recognize and deeply analyze medical record texts, providing strong data support and intelligent decision-making basis for the medical, teaching, and research integrated system. It not only improves the efficiency and quality of data processing, but also promotes the deep integration of medical, teaching, and research, and drives the intelligent development of the medical system.

[0085] Furthermore, the Trinity Data Engine is also used to update the diagnosis and treatment processes and schemes in the expert thinking chain in real time according to the preset update rules and algorithms, and adjust the diagnosis and treatment guidelines and teaching cases in combination with expert opinions based on the treatment effect data in clinical feedback and the statistical analysis data in research results.

[0086] The Trinity Data Engine not only collects, processes, and distributes data, but also has the ability to dynamically update. This function ensures that the system can adjust and optimize the diagnosis and treatment processes and schemes in the expert thinking chain in real time according to the latest clinical feedback and research results, and optimize and adjust the diagnosis and treatment guidelines and teaching cases in combination with expert opinions. This dynamic updating mechanism helps the system to always maintain the latest medical knowledge and best practices, improving the accuracy of diagnosis and treatment decisions and the timeliness of teaching content.

[0087] The Trinity Data Engine first automatically collects treatment effect data (such as patient symptom improvement, test result changes, etc.) in clinical feedback and statistical analysis results (such as research conclusions, data analysis reports, etc.) of the research cohort management subsystem. Through preset algorithms, it analyzes these data to identify content that deviates from existing diagnosis and treatment guidelines, teaching cases, or expert thinking chains (such as a treatment scheme that does not achieve the expected effect, research conclusions that conflict with existing guidelines, etc.), and triggers a reminder function.

[0088] When the engine identifies content that needs to be adjusted (especially information that significantly deviates from the existing architecture), it will organize the relevant data and abnormal points and submit them to a preset expert team. The expert team is composed of medical experts with rich clinical, teaching, and research experience, and discusses these contents in a centralized manner, combining their own professional experience and the latest medical cognition to assess whether adjustment is needed and the direction of adjustment.

[0089] For diagnosis and treatment guidelines: the expert team determines whether to update the diagnosis and treatment processes, drug recommendations, index judgment criteria, etc. in the guidelines based on the discussion results. If adjustment is needed, the engine will convert the expert consensus into structured rules and embed them into the diagnosis and treatment guidelines to ensure that the guidelines are consistent with the latest clinical practice and research achievements.

[0090] For teaching cases: The expert panel reviewed the presentation, core knowledge points, and clinical thinking guidance of existing teaching cases. Based on new diagnostic and treatment guidelines and scientific research findings, they provided revision suggestions (such as adding new treatment plans and updating case analysis key points). Based on these expert opinions, the engine updated the standardized presentation content, interactive modules, and assessment points of the teaching cases to ensure the scientific nature and timeliness of the teaching materials.

[0091] Adjusted treatment guidelines and teaching cases are synchronized with various system subsystems (diagnosis and treatment decision-making subsystem and teaching subsystem), and further feedback is collected through clinical application and teaching practice. The engine continuously monitors this feedback data. If new deviations are detected, the above process is restarted, forming a closed loop of "data identification - expert evaluation - optimization and adjustment - practical verification", ensuring that treatment guidelines and teaching cases are always consistent with expert consensus and the latest medical advances.

[0092] Patient treatment outcome data, including symptom improvement, changes in laboratory test results, and comparisons of imaging findings, are collected from the diagnosis and treatment decision-making subsystem and clinical information system. A combination of automatic collection and manual input ensures data comprehensiveness and accuracy. Statistical analysis results of research projects, including research conclusions and data analysis reports, are collected from the research cohort management subsystem. A combination of automatic system extraction and manual upload by researchers ensures data timeliness and reliability. Based on pre-set update rules and algorithms, the diagnosis and treatment processes and plans in the expert thinking chain are updated in real time. A series of pre-set logical judgment rules are used to evaluate the impact of clinical feedback and research results on existing diagnosis and treatment processes and plans. Machine learning and data mining algorithms are used to analyze clinical feedback and research results data and generate update recommendations. Based on the evaluation results of the update rules and algorithms, the system automatically adjusts the diagnosis and treatment processes and plans in the expert thinking chain to ensure they always reflect the latest medical knowledge and best practices. Treatment guidelines and teaching cases are optimized based on expert feedback. Senior medical experts are organized to review and evaluate the updated diagnosis and treatment processes and plans. Expert opinions and suggestions on the updates are collected through expert meetings and online discussions. Based on expert opinions, further optimize and adjust the diagnosis and treatment guidelines and teaching cases to ensure their scientific and practical application. The system automatically collects treatment effect data from clinical feedback and statistical analysis data from scientific research results. Based on preset update rules and algorithms, the collected data is evaluated and update suggestions are generated. The update suggestions are submitted to the expert team for review and evaluation, and expert opinions are collected. Based on expert opinions, the diagnosis and treatment processes and plans in the expert thinking chain are optimized and adjusted. The updated diagnosis and treatment guidelines and teaching cases are published to the system for access by various subsystems. The system continuously monitors clinical feedback and scientific research results to ensure the continued effective operation of the update mechanism.

[0093] By updating expert thought chains in real time, we ensure that diagnosis and treatment decisions are always based on the latest medical knowledge and clinical practice, improving the accuracy and effectiveness of diagnosis and treatment. We optimize and adjust diagnosis and treatment guidelines and teaching cases based on expert opinions to ensure the timely updating and effective dissemination of medical knowledge. Optimized teaching cases better reflect actual clinical needs, improving the quality and effectiveness of medical education. This dynamic update mechanism enables the system to quickly adapt to changes and developments in the medical field, maintaining its advancement and practicality.

[0094] The dynamic update function of the Trinity Data Engine collects clinical feedback and scientific research data, combines it with pre-set update rules and algorithms, and expert opinions to update and optimize the diagnosis and treatment processes and plans in the expert thinking chain in real time. This function not only improves the accuracy of diagnosis and treatment decisions and the timeliness of teaching content, but also promotes the updating and dissemination of medical knowledge, enhances the system's adaptability and flexibility, and provides strong support for the continuous optimization of the integrated medical, teaching and research system.

[0095] The diagnosis and treatment decision subsystem 1 also includes a behavior guidance and compliance monitoring module; The behavior guidance and compliance monitoring module is used to compare the deviation between the doctor's behavior and the expert's thinking chain. If the deviation is greater than the preset value, an early warning will be triggered. Through the system's built-in authority management and approval process monitoring module, the data usage and ethical approval status will be recorded in real time to ensure the compliance and legality of data use.

[0096] The Behavior Guidance and Compliance Monitoring module is a key component of the diagnosis and treatment decision-making subsystem. It aims to ensure that medical staff's diagnosis and treatment behaviors align with expert reasoning and pre-defined treatment protocols, while also guaranteeing the compliance and legality of data use. Through real-time monitoring and early warning mechanisms, this module helps medical staff standardize their diagnosis and treatment behaviors, reduce medical risks, and ensure medical quality and data security.

[0097] The behavior guidance function is as follows: compare the deviation between the doctor's behavior and the expert's thinking chain. If the deviation is greater than the preset value, an early warning is triggered.

[0098] The Expert Thought Chain is a collection of medical processes and plans based on historical cases and expert advice, simulating the expert's thought process during diagnosis and treatment. The system monitors medical staff's behavior in real time during the diagnosis and treatment process, including diagnostic decisions, treatment plan selection, and requests for examinations and tests. Using pre-set evaluation rules and algorithms, it calculates the degree of deviation between medical staff's behavior and the Expert Thought Chain. This deviation assessment considers multiple factors, such as diagnostic accuracy, treatment plan rationality, and the necessity of examinations and tests. When the deviation exceeds a preset threshold, the system automatically triggers an alert, prompting medical staff to reassess and adjust their diagnosis and treatment behavior.

[0099] The compliance monitoring function means: through the system's built-in permission management and approval process monitoring modules, real-time recording of data usage and ethical approval status to ensure the compliance and legality of data use.

[0100] The system has a built-in permission management module, which assigns different data access and operation permissions to users with different roles (such as doctors, nurses, scientific researchers, etc.) to ensure the security and confidentiality of the data. The system monitors the approval process for data use to ensure that all data use has undergone necessary ethical approval and compliance review. The approval process includes data use application, approval opinion record, approval result feedback, etc. The system records data usage in real time, including data access time, access content, operation records, etc., to facilitate subsequent audits and traceability. The system conducts compliance checks regularly to ensure that data use complies with relevant laws, regulations and ethical requirements. The inspection content includes the legitimacy of the data source, the rationality of the data use purpose, and the compliance of the data processing process.

[0101] Through real-time monitoring and early warning mechanisms, medical staff can standardize their diagnosis and treatment practices, reduce the risk of misdiagnosis and mistreatment, and improve the quality of treatment. Through permission management and approval process monitoring, the compliance and legality of data use are ensured, protecting patient privacy and data security. Combined with the guidance of expert thinking chains, medical staff can make more scientific and reasonable diagnosis and treatment decisions, thereby improving the quality of medical services. Through early warning mechanisms and compliance monitoring, potential medical risks can be promptly identified and corrected, reducing medical disputes and legal risks.

[0102] The Behavior Guidance and Compliance Monitoring module compares the degree of deviation between physician behavior and expert reasoning, triggering real-time alerts. Combined with the system's built-in permission management and approval process monitoring, this module ensures the compliance and legality of data use. This module not only standardizes medical staff's diagnostic and treatment behaviors and improves treatment quality, but also ensures data security and legality, providing strong support for the efficient operation and risk management of the medical system.

[0103] The case presentation method includes: integrating the patient's full-cycle diagnosis and treatment trajectory according to the timeline, combining the seven key steps of patient admission to the hospital / department, preliminary examination and diagnosis after information collection, treatment plan formulation, observation of the treatment process, evaluation and feedback of changes in the condition, adjustment of the treatment plan, and patient discharge from the hospital / department, sorting out the development process of the disease, and presenting the content of each time point in a structured and standardized manner, showing the changing trends of core indicators in important cases over time, reflecting the changing trends of the disease and the direction of treatment.

[0104] Case presentation is a key component of the teaching subsystem. It aims to help learners better understand and grasp the full patient diagnosis and treatment cycle through structured and standardized presentations. This approach integrates key steps from admission to discharge into a timeline, demonstrating the progression of the disease and treatment outcomes, helping learners develop systematic clinical thinking and analytical skills.

[0105] The patient's entire diagnosis and treatment cycle is organized along a timeline, encompassing seven key steps: admission to the hospital / department, initial examination and diagnosis after information collection, treatment plan development, observation of treatment progress, assessment and feedback on conditional changes, treatment plan adjustment, and discharge from the hospital / department. The timing and specific content of each key step are presented in a timeline format, enabling learners to clearly understand the chronological order and key milestones of the patient's entire diagnosis and treatment process. The content of each time point is presented in a structured and standardized manner (i.e., based on a pre-set format). The content of each time point is divided into different categories, such as symptom description, examination results, treatment measures, and conditional changes. A unified format and template are used to present the content to ensure accuracy and consistency. For example, visual tools such as tables, flow charts, and timelines can be used to present key information. Key indicators in key case studies, such as vital signs, laboratory test results, and imaging findings, should be highlighted, and their trends over time should be displayed. Trends in key indicators over time in key case studies should be presented to reflect disease progression and treatment direction. Use charts (such as line graphs and bar charts) to display the changing trends of core indicators, helping learners intuitively understand the evolution of the condition. Evaluate treatment effectiveness based on the timing of treatment measures, demonstrating their impact on the progression of the condition. Dynamically adjust the treatment plan based on the progression of the condition and the effectiveness of treatment, and record the timing and details of the adjustments on the timeline.

[0106] Through structured and standardized presentations, learners can quickly understand and grasp the entire patient diagnosis and treatment process, improving learning efficiency. This guides learners to develop a systematic clinical mindset, enabling them to holistically analyze and assess their condition, thereby enhancing their diagnostic and treatment capabilities. Rich visualization tools and dynamic presentation methods make teaching content more vivid and intuitive, enhancing teaching effectiveness. Standardized case presentation facilitates the dissemination and sharing of knowledge, promoting the standardization of medical education.

[0107] The case presentation method integrates the patient's entire diagnosis and treatment cycle along a timeline, combining structured and standardized narratives to demonstrate the progression of the disease and the effectiveness of treatment. This presentation method not only helps learners better understand and grasp the patient's diagnosis and treatment process, but also cultivates their clinical thinking and analytical skills, improving the quality and effectiveness of medical education.

[0108] In some embodiments, the scientific research queue management subsystem is also used to use data mining and machine learning algorithms to automatically analyze medical data, identify abnormal data patterns and potential correlations, and propose scientific research hypotheses with research value based on the characteristics and distribution patterns of abnormal data, combined with medical knowledge and expert experience, and generate corresponding scientific research project proposals.

[0109] Automated analysis of medical data identifies unusual patterns and potential correlations. Medical data from research cohorts is cleaned, standardized, and feature extracted to ensure data quality and usability. A variety of data mining and machine learning algorithms, such as cluster analysis, association rule mining, decision trees, random forests, and neural networks, are employed, with the appropriate algorithm selected based on specific research needs. Historical data is used to train the selected algorithm, optimize model parameters, and improve model accuracy and generalization. The model identifies unusual patterns in the data, such as abnormally high test results or unusual treatment responses. Potential correlations are discovered, such as the association between certain symptoms and specific diseases or the comparison of the effectiveness of different treatment options. Based on the characteristics and distribution patterns of unusual data, combined with medical knowledge and expert experience, promising research hypotheses are proposed. Feature analysis is performed on identified unusual data to extract key features and patterns. Combining medical literature, guidelines, and expert experience, the unusual data is interpreted to identify possible medical explanations. Based on feature analysis and medical knowledge, promising research hypotheses are proposed. For example, if a drug is found to have significant efficacy in a specific patient population, a hypothesis for further investigation of its mechanism of action may be proposed. Generate a corresponding research project proposal. Design a standardized research project proposal template, including sections such as research background, research objectives, research methods, expected results, and timeline. Automatically fill in the relevant content in the proposal template based on the generated research hypotheses to ensure the proposal's completeness and scientific validity. Submit the generated proposal to a team of experts for review and evaluation, and revise and improve based on their feedback. Submit the refined research project proposal to the research management department or funding agency for project approval and funding.

[0110] Through automated data mining and machine learning algorithms, we can quickly identify unusual data patterns and potential correlations, reducing the workload of researchers in manual data analysis and improving research efficiency. Combining medical knowledge and expert experience, we can propose research hypotheses with research value, helping to discover new medical research directions and breakthroughs. Generated research project proposals undergo expert review and evaluation to ensure the scientific nature and feasibility of the research projects and improve the quality of research. This provides researchers with powerful tools to stimulate innovative thinking and promote the development of medical research.

[0111] The research cohort management subsystem automatically analyzes medical data using data mining and machine learning algorithms, identifying unusual patterns and potential correlations. Combining medical knowledge and expert experience, it proposes promising hypotheses and generates corresponding research project proposals. This functionality not only improves the efficiency and quality of scientific research but also provides new directions and insights for medical research, promoting scientific innovation and medical progress.

[0112] Step 3: Generate and feed back the teaching case library Case construction: Encapsulate the entire diagnosis and treatment process of a typical case (data + decision chain + results) into an interactive teaching module; The large number of real clinical cases generated in steps 2 and 3 based on the standardized structured expression of expert thinking framework are desensitized, and the large amount of data, decision chains and treatment results generated are encapsulated as interactive teaching module content according to different needs.

[0113] The large amount of traditional data indicators and text content generated are combined with medical history information for structured sorting, which can be used as teaching content for clinical analysis. Among them, the modular sorting of different systems can be used as teaching content for evaluating different systems.

[0114] The large amount of image data generated, such as ultrasound images and other pictures and video content, are automatically identified and labeled by the AI ​​in Patent 2 and are subject to expert-level quality control. Individual pictures and videos can be used for image quality control and teaching content judgment, and grouped image data combined with clinical information can be used as phenotypic teaching content, thereby achieving visual accumulation in the learning process.

[0115] The generated data, decision chains, treatment result feedback and other information are combined in time series to form a complete disease diagnosis and treatment process, and are structured and presented according to the framework preset by expert experience. It can be used as teaching content for classic cases, simulation deductions, and interactive exercises.

[0116] Combining the above-mentioned clinical analysis, visual accumulation and case deduction teaching content with the simulator training system can form a basic clinical ability, image acquisition ability, image interpretation ability, clinical decision-making ability and special competency training system, and integrate AI, VR / MR and other technologies to achieve interactive and virtual reality effects.

[0117] The content of each of the above-mentioned teaching modules will be marked with its content focus, highlights, teaching value, etc. according to the existing expert prior standards. The corresponding learning modules will link relevant professional knowledge, guidelines, literature, etc. through the AI ​​big model to achieve the learning goal of expanding from point to surface.

[0118] (2) Dynamic update: When the scientific research conclusions of the case are released or the guidelines are updated, the teaching case will automatically synchronize with the latest knowledge; The underlying framework of the above learning modules is set up after joint review by an expert group based on expert experience and the latest knowledge. The system automatically searches for relevant content updates on a regular basis and synchronizes relevant knowledge points. In addition, if any content is found to be significantly inconsistent with the existing architecture, a reminder function is set up and the content is sorted out. The expert group will discuss this and adjust or maintain the architecture based on the results of the discussion.

[0119] (3) Ability assessment: The students’ ability to apply the expert thinking chain is assessed through simulated diagnosis and treatment (such as virtual patient consultation).

[0120] The system has an assessment and evaluation feedback module, which sets after-class exam questions and user feedback based on the key points of each learning module. The system regularly collects, organizes and analyzes assessment results and evaluation feedback content, and pushes them to managers, and combines AI to give suggestions. Ultimately, managers organize meetings to decide whether to adopt them.

[0121] A special assessment module is set up to conduct batch assessments on the above-mentioned learning content, including assessments of basic clinical skills, image acquisition capabilities, image interpretation and interpretation capabilities, clinical decision-making capabilities, and special disease / syndrome management competency. This assessment can be conducted through direct answering, comparative answering, simulated diagnosis and treatment, etc., to assess the trainees' mastery of the above content. The system regularly collects, organizes and analyzes assessment results and evaluation feedback, and pushes them to management personnel, and combines AI to give suggestions. Finally, the manager organizes a meeting to decide whether to adopt them, and continuously updates and iterates.

[0122] An example of scientific hypothesis generation is as follows: Automatically propose research hypotheses based on abnormal patterns in clinical data (such as an increased rate of adverse reactions to a certain drug); link historical research to recommend similar project designs and analysis methods.

[0123] An example of a closed-loop feedback mechanism for teaching, clinical research, and collaboration based on the system provided in this application is as follows: 1. Clinical findings: The efficacy of a certain antihypertensive drug is reduced in obese patients; Specifically, the diagnosis and treatment decision-making subsystem collects clinical feedback data and discovers that a certain antihypertensive drug is less effective than expected in obese patients. When using this antihypertensive drug, medical staff find that the blood pressure of obese patients is poorly controlled. This phenomenon is recorded and reported to the system.

[0124] 2. Scientific research verification: Automatically construct a cohort of obese hypertensive patients and analyze the correlation between treatment efficacy and BMI; Automatically construct a cohort of obese hypertensive patients to analyze the correlation between treatment efficacy and BMI. The research cohort management subsystem automatically selects a cohort of obese hypertensive patients, ensuring that patients within the cohort have similar BMIs. Efficacy analysis is performed on the cohort, statistically analyzing the response to antihypertensive drugs across different BMI ranges and assessing the correlation between treatment efficacy and BMI. Statistical analysis and machine learning algorithms are used to validate the hypothesis that antihypertensive drug efficacy is reduced in obese patients.

[0125] 3. Knowledge update: convert the conclusion into a new expert rule ("BMI ≥ 30 → drug X is preferred"); Based on the research validation results and expert opinions, a new expert rule is generated to prioritize drug X for patients with a BMI ≥ 30. The new expert rule is stored in the system database and made available to the diagnosis and treatment decision-making subsystem. Treatment guidelines are updated to incorporate the new expert rule, ensuring that clinical practice decisions are consistent with the latest medical knowledge.

[0126] 4. Teaching feedback: Generate an interactive teaching case on "Selection of blood pressure reduction plan for obese patients" and push it to the doctor side.

[0127] Based on new expert rules and scientific research findings, the teaching subsystem generates interactive teaching cases, demonstrating the process of selecting a blood pressure-lowering treatment for obese patients. These teaching cases include basic patient information, description of the condition, rationale for treatment selection, and evaluation of treatment effectiveness. Through interactive Q&A and simulated procedures, they help learners master correct diagnostic and treatment methods. These teaching cases are then pushed to physicians for learning and reference, improving their clinical decision-making and diagnostic skills.

[0128] The feedback loop of the teaching, clinical, and scientific research linkage mechanism, through four key steps: clinical discovery, scientific research verification, knowledge updating, and teaching feedback, achieves rapid knowledge updating and dissemination, improving the quality of medical services and the level of medical education. This mechanism not only promotes the close integration of scientific research and clinical practice, but also enhances the professional capabilities of medical staff and promotes the development of medicine.

[0129] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps in the medical, teaching and research integrated system based on a common underlying layer according to various embodiments of the present application described in the above-mentioned relevant parts of this specification.

[0130] The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0131] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A medical, teaching and research integrated system based on a common underlying layer, characterized by: include: The diagnosis and treatment decision-making subsystem is used to provide diagnosis and treatment decision support for preset diseases and syndromes based on the expert thinking chain. Specifically, for each case, based on the collected information, it determines the core indicators related to the disease, guides the user to sort out the information and analyze the disease, automatically generates disease analysis and treatment recommendations, records treatment choices and effect feedback, and automatically reminds whether to include the case in the research cohort when the case meets the preset research cohort conditions, prompts treatment nodes, and visualizes the disease progression; The expert thinking chain is a set of medical processes and medical plans based on historical cases and expert advice; the core indicators are the indicators necessary for judging the condition under the existing diagnosis and treatment plan; The scientific research cohort management subsystem is used to obtain medical information and include cases that meet preset requirements in the medical information into the scientific research cohort; based on the preset structured data set, organize the various cases in the scientific research cohort and desensitize the case information; among which, the structured data set is a general data set or a personalized data set obtained by adjusting based on user input information; assist researchers in generating treatment recommendations and send them to the corresponding clinical physicians to obtain the clinicians' actual treatment choices and effect feedback; eliminate cases that do not meet the requirements in the scientific research cohort; implement quality control and statistical analysis on the data of the scientific research cohort, and access AI tools to query relevant background information, sort out the statistical result framework, and generate data result analysis reports; adjust the expert thinking chain based on the actual scientific research results of the scientific research cohort; the medical information includes: patient medical records, examination and test results and treatment plans during clinical diagnosis and treatment; The teaching subsystem is used to set up preset case presentation methods based on expert thought chains and preset cognitive structures to guide users to form thinking habits for disease analysis and engage in structured thinking. Based on the material sets and case sets obtained from the diagnosis and treatment decision-making subsystem and the scientific research queue management subsystem, teaching materials are generated after standardization and expert-level quality control. Combined with the simulator, it forms a skills training system and a capacity improvement training system. The standardization and expert-level quality control include: conversion to a preset case presentation format and review by preset experts; The simulator is a device used to simulate a patient.

2. The medical, teaching and research integrated system based on a common bottom layer according to claim 1 is characterized in that: The diagnosis and treatment decision subsystem includes: The core indicator preset module is used to pre-set the core indicators required for diagnosis of different diseases and syndromes based on expert experience, and present them to medical staff in a table form on the system interface; The information collection and analysis module supports manual input or automatic collection of core information related to disease diagnosis. After the collection is completed, the disease analysis is automatically generated and treatment recommendations are given; The core information is the information necessary to determine the condition under the existing diagnosis and treatment plan; The recording and feedback module is used to record and provide feedback to medical staff on treatment plans and treatment effects; it prompts treatment nodes and visually displays the disease progression; The scientific research cohort reminder module is used to automatically remind whether to include a case in the scientific research cohort when a case meets the preset scientific research cohort conditions.

3. The medical, teaching and research integrated system based on a common bottom layer according to claim 1 is characterized in that: The scientific research queue management subsystem includes: The platform design and dataset editing module is used to provide a general structured dataset or a general scientific research process platform, or to generate a personalized structured dataset or a personalized scientific research process platform based on user configuration; The treatment recommendation and feedback module is used to generate and present treatment recommendations for research cases to researchers; obtain the research treatment recommendations determined by researchers and send them to clinicians; obtain the clinicians' choice of whether to adopt the recommendations and record the clinical behavior and corresponding treatment effects; if the current case does not meet the current research needs, the current case will be eliminated; The data quality control and analysis report generation module is used to perform quality control and statistical analysis on scientific research cohort data online, access AI tools to query relevant background information, sort out the statistical result framework, and generate data result analysis reports; The expert thinking chain adjustment module is used to regularly evaluate and optimize the diagnosis and treatment processes and plans in the expert thinking chain based on scientific research results and expert opinions.

4. The medical, teaching and research integrated system based on a common bottom layer according to claim 1 is characterized in that: The teaching subsystem includes: Standardized presentation setting module: set preset case presentation methods based on expert thinking chains and preset cognitive architecture; Material and case collection management module: stores a preset number of material and case collections generated by the diagnosis and treatment decision subsystem and the scientific research queue management subsystem, and uses them as teaching materials after standardization and expert-level quality control; Training system generation module: Combined with the simulator to generate skill training system and capability improvement training system; AI automatic recognition and quality control platform generation module: annotates a preset number of medical images and text materials, and trains AI models to achieve automatic recognition and quality control.

5. The medical, teaching and research integrated system based on a common bottom layer according to any one of claims 1 to 4, characterized in that: Also included is the Trinity Data Engine; The trinity data engine uses optical character recognition technology and natural language processing technology to identify and analyze medical record texts, extract key information such as disease names and symptom descriptions, and store expert thinking chains in the form of data structures in the system database for call by the diagnosis and treatment decision-making subsystem and the scientific research queue management subsystem; it is also used to bind clinical cases with expert thinking chains and scientific research conclusions, generate diagnosis and treatment guidelines and teaching cases, provide real-time patient condition data and expert advice to the diagnosis and treatment decision-making subsystem, provide structured scientific research data sets to the scientific research queue management subsystem, and provide teaching cases and materials to the teaching subsystem.

6. The medical, teaching and research integrated system based on a common bottom layer according to claim 5 is characterized in that: The Trinity Data Engine is also used to update the diagnosis and treatment processes and plans in the expert thinking chain in real time based on the treatment effect data in clinical feedback and the statistical analysis data in scientific research results, according to preset update rules and algorithms, and to adjust the diagnosis and treatment guidelines and teaching cases in accordance with expert opinions.

7. The medical, teaching and research integrated system based on a common bottom layer according to claim 5 is characterized in that: The diagnosis and treatment decision subsystem also includes behavior guidance and compliance monitoring modules; The behavior guidance and compliance monitoring module is used to compare the deviation between the doctor's behavior and the expert's thinking chain. If the deviation is greater than the preset value, an early warning is triggered. Through the system's built-in authority management and approval process monitoring module, the data usage and ethical approval status are recorded in real time.

8. The medical, teaching and research integrated system based on a common bottom layer according to claim 2 is characterized in that: The case presentation methods include: The system integrates the patient's full-cycle diagnosis and treatment trajectory according to the timeline, combining the seven key steps of patient admission to the hospital / department, preliminary examination and diagnosis after information collection, treatment plan formulation, observation of the treatment process, evaluation and feedback of changes in the condition, adjustment of the treatment plan, and patient discharge from the hospital / department. It sorts out the development process of the disease, presents the content of each time point based on the preset format, and shows the changing trend of the core indicators in the case over time, reflecting the changing trend of the disease and the direction of treatment.

9. The medical, teaching and research integrated system based on a common bottom layer according to claim 1 is characterized in that: The scientific research cohort management subsystem is also used to automatically analyze medical data using data mining and machine learning algorithms, identify abnormal data patterns and potential correlations, and propose scientific research hypotheses based on the characteristics and distribution patterns of abnormal data, combined with medical knowledge and expert experience, and generate corresponding scientific research project proposals.

Images