Clinical medicine practice skill evaluation system

Abstract

The invention discloses a clinical medicine practice skill evaluation system, and relates to the technical field of clinical medicine education, and the system comprises the following components: a comprehensive data processing module which collects and preprocesses real patient electronic medical record data and examinee multi-modal data, fuses all modal data features, cleans the electronic medical record data, and stores the cleaned electronic medical record data; providing data for subsequent modules; the personalized intelligent virtual patient is generated based on the electronic medical record data of the real patient, rich and diversified clinical simulation scenes are provided for examinees, the complexity and diversity of the real patient are achieved, the illness state can be adjusted in real time according to decisions of the examinees, the uncertainty and complexity of the clinical scenes are simulated, and the clinical simulation experience of the examinees is improved. The system has the advantages that the system is simple in structure and convenient to use, clinical thinking of examinees can be cultivated and improved in practice, the examinees can learn to make accurate judgment and decisions when the illness state changes, and meanwhile, the examinees can exercise the strain capacity of the examinees through interaction with virtual patients so as to better adapt to various challenges in actual clinical work.

Description

Technical Field

[0001] The present invention relates to the technical field of clinical medical education, and specifically to a clinical medical practice skill assessment system. Background Art

[0002] In the field of clinical medical education and assessment, the assessment of practical skills has always been the focus and difficulty. With the continuous progress of medical technology and the increasing growth of medical needs, the requirements for the clinical practice skills of medical students are also getting higher and higher. The traditional medical education model has gradually revealed its limitations in the cultivation of practical skills. Therefore, it is particularly important to seek an efficient, comprehensive and safe method for assessing clinical practice skills. In recent years, with the rapid development of intelligent technology and virtual reality technology, new ideas and means have been provided for the assessment of clinical medical practice skills.

[0003] However, there are many deficiencies in the traditional clinical medical assessment methods. Although theoretical examinations can examine students' mastery of medical knowledge, they are limited to the memory of fixed knowledge and are difficult to truly reflect students' ability to make accurate judgments and decisions based on the changes in the condition in actual clinical scenarios. Although clinical internships provide students with certain practical opportunities, due to the uncontrollability and diversity of real cases, students have limited opportunities to contact typical and complex cases, and there are risks in operating on real patients. In addition, some existing simulation assessment systems lack personalization, cannot generate targeted simulation cases based on real patient data, and the assessment methods are single, only evaluating based on single-dimensional data, ignoring multi-modal information such as the action postures, voice communications, physiological indicators, and images and videos during the operation of the examinees, resulting in incomplete and inaccurate assessment results and being difficult to truly reflect the clinical practice skill level of the examinees.

[0004] In view of the above problems, it is necessary to optimize the existing clinical medical practice skill assessment system. By using the electronic medical record data of real patients to generate personalized intelligent virtual patients and simulating the changes in the condition in real time, and integrating multi-modal data for comprehensive assessment. Therefore, it is of great significance to develop a clinical medical practice skill assessment system that can comprehensively achieve the above characteristics. Summary of the Invention

[0005] The purpose of the present invention is to make up for the deficiencies of the prior art and provide a clinical medicine practice skill assessment system. It can generate personalized intelligent virtual patients by using real patient electronic medical record data, provide diverse clinical simulation scenarios for candidates, and through the disease condition dynamic regulation module, adjust the disease condition in real time according to the candidates' decisions, simulating the uncertainty and complexity of the clinical scenario. The comprehensive data processing module fuses multi-modal data for evaluation, comprehensively reflecting the candidates' clinical practice skills from multiple perspectives. The assessment and analysis module uses a multi-dimensional evaluation index system and combines expert experience for comprehensive evaluation, providing a scientific and objective basis for clinical medicine education and assessment. The interactive display module uses virtual reality or augmented reality technology to provide a more realistic clinical simulation experience for candidates, improving the candidates' participation and learning effect.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A clinical medicine practice skill assessment system, which includes the following components:

[0007] Comprehensive data processing module: Collect and preprocess real patient electronic medical record data and candidates' multi-modal data, and provide data for subsequent modules by fusing the characteristics of each modal data and cleaning the electronic medical record data.

[0008] Intelligent virtual patient generation module: Analyze the preprocessed electronic medical record data, construct an intelligent virtual patient model by combining the typical characteristics, random characteristics, medical knowledge graph characteristics, and new characteristics of medical research of the electronic medical record, and introduce the uncertainty of the disease condition to generate a virtual patient disease condition that conforms to clinical reality.

[0009] Disease condition dynamic regulation module: Real-time monitor the decisions of candidates in the simulation assessment, calculate the change amount of the virtual patient's disease condition based on the decisions, and predict the evolution of the disease condition, so that the virtual patient's disease condition changes dynamically with the candidates' decisions, simulating the real clinical diagnosis and treatment process.

[0010] Assessment and analysis module: Construct a multi-dimensional evaluation index system, calculate the scores of candidates on each individual evaluation index and the comprehensive score respectively, and comprehensively evaluate the clinical practice skill level of candidates by adjusting and optimizing the index weights.

[0011] Interactive display module: Design an interactive interface by using virtual reality or augmented reality technology, achieve natural interaction through voice and gesture recognition technology, and display the changes in the patient's disease condition, examination results, and operation prompt information in real time.

[0012] Furthermore, the comprehensive data processing module collects and preprocesses real patient electronic medical record data and candidates' multi-modal data. The electronic medical record data includes patient basic information, disease history, symptom manifestations, and various examination indicators. The candidates' multi-modal data includes action posture data, voice communication data, physiological index data, and image and video data.

[0013] Furthermore, the intelligent virtual patient generation module analyzes the preprocessed electronic medical record data. Specifically, it receives the preprocessed electronic medical record data from the comprehensive data processing module, parses the data format, extracts the key information related to disease diagnosis and treatment, stores it in the database, deeply analyzes and learns the parsed data, mines the hidden rules and patterns in the data, and constructs an intelligent virtual patient model based on them. At the same time, to make the virtual patient closer to the real clinical situation, uncertainty factors are introduced into the model, so that the condition manifestation and development of each virtual patient are random and different.

[0014] Furthermore, the intelligent virtual patient generation module constructs an intelligent virtual patient model, and its model formula is: P = α·E + β·R + γ·N + δ·C, where P is the condition feature vector of the generated intelligent virtual patient, including various condition information of the patient, E is the typical condition feature vector extracted from the electronic medical record data, R is the randomly generated condition feature vector, N is the condition feature vector generated based on the medical knowledge graph, reflecting the general laws of diseases, C is the condition feature vector generated according to the current medical research hotspots and new discoveries, making the virtual patient more timely, and α, β, γ, δ are the weight coefficients of E, R, N, C respectively, which are determined by scoring according to the importance of different factors in the generation of virtual patients. Different diseases and evaluation scenarios have different degrees of dependence on each factor. According to the understanding of the disease, judge which factors are more critical to the condition generation of virtual patients, so as to determine the weights.

[0015] Furthermore, the intelligent virtual patient generation module introduces uncertainty factors into the model, and its uncertainty adjustment formula is: where ΔP is the introduced condition uncertainty adjustment amount, used to increase uncertainty in the condition generation process, U is the uncertainty coefficient, which is set according to the actual clinical situation and evaluation requirements to control the magnitude of uncertainty, P i is the i-th eigenvalue in the condition feature vector, is the mean value of all eigenvalues in the condition feature vector, and m is the dimension number of the condition feature vector.

[0016] Furthermore, the disease condition dynamic regulation module monitors the decisions of candidates in the simulated assessment in real time. Specifically, it monitors the diagnosis and treatment decisions of candidates during the simulated assessment in real time, compares and analyzes the decisions with the pre-set standard diagnosis and treatment plans, judges the rationality and effectiveness of the decisions, and establishes a disease condition evolution model that can reflect the disease development law and treatment effect. Taking the decisions of the candidates and the current disease condition status of the virtual patient as inputs, it predicts the development direction and change degree of the disease condition. According to the prediction results of the disease condition evolution model, it adjusts the disease condition of the intelligent virtual patient in real time, and dynamically displays the development and change of the disease condition by changing the symptom manifestations and examination index methods of the virtual patient.

[0017] Furthermore, the disease condition dynamic regulation module establishes a disease condition evolution model that can reflect the disease development law and treatment effect, and its model formula is: where S t+1 is the predicted disease condition status value at the next time step, S t is the disease condition status value at the current time step, θ is the epidemic evolution coefficient, which controls the evolution speed of the epidemic with decisions and time, ΔS is the change in the epidemic caused by the current decision, and its calculation formula is: ΔS is the change in the disease condition of the virtual patient after the candidate's decision, l is the number of decisions taken by the candidate, which is determined by the actual number of decisions taken by the candidate during the simulated assessment, a j is the effect coefficient of the j-th decision, which reflects the influence degree of the decision on the disease condition, D j is the intensity factor of the j-th decision, which is determined according to the specific content of the candidate's decision, b j is the decision sensitivity coefficient, which controls the response speed of the disease condition to the decision, S0 is the current disease condition status value of the virtual patient, c j is the threshold of the j-th decision, is the random interference coefficient, which introduces randomness to simulate the uncertainty in clinical practice, ∈ is the random interference term, and it follows a probability distribution.

[0018] Furthermore, the assessment and analysis module constructs an evaluation index system covering multiple dimensions, including evaluation indexes in terms of diagnostic accuracy, treatment plan rationality, emergency handling ability, communication ability, operation standardization, concentration, and psychological state.

[0019] Furthermore, the assessment and analysis module calculates the scores of candidates on each individual evaluation index and the comprehensive score respectively. By adjusting and optimizing the index weights, it comprehensively evaluates the clinical practice skill level of candidates. The score calculation formula for each individual evaluation index is: where Score single is the score of the candidate on a certain individual evaluation index, p is the number of sub-evaluation items under this individual index, is the weight of the i-th sub-evaluation item, which is determined according to the importance of each sub-evaluation item in this single indicator. is the matching score of the candidate on the i-th sub-evaluation item, which is obtained by comparing and analyzing the candidate's performance on this sub-evaluation item with the standard. The comprehensive score formula is: Among them, Score total is the comprehensive score of the candidate, reflecting the candidate's clinical practice skill level. q is the total number of evaluation indicators, and ω k is the weight of the k-th evaluation indicator. is the score of the candidate on the k-th evaluation indicator.

[0020] Compared with the prior art, the clinical medicine practice skill evaluation system has the following beneficial effects:

[0021] First, the present invention generates personalized intelligent virtual patients based on real patient electronic medical record data, providing rich and diverse clinical simulation scenarios for candidates. It not only has the complexity and diversity of real patients, but also can adjust the condition in real time according to the candidate's decision, simulating the uncertainty and complexity of clinical scenarios, which helps candidates cultivate and improve their clinical thinking in practice, enabling them to learn to make accurate judgments and decisions when the condition changes. At the same time, through interaction with virtual patients, candidates can also exercise their adaptability and better adapt to various challenges in actual clinical work.

[0022] Second, the present invention can fuse multi-modal data for evaluation through the comprehensive data processing module, including multi-dimensional information such as action postures, voice communications, physiological indicators, and images and videos during the operation process. This comprehensive evaluation method can more truly reflect the candidate's clinical practice skill level, avoiding the one-sidedness and inaccuracy that may be brought by single-dimensional evaluation. In addition, the evaluation and analysis module uses a multi-dimensional evaluation index system and combines expert experience for comprehensive evaluation, further improving the scientificity and objectivity of the evaluation results. It not only helps to accurately measure the candidate's skill level, but also provides a strong basis for clinical medicine education and assessment, promoting the sustainable development of clinical medicine education.

[0023] Other advantages, objectives and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. Brief Description of the Drawings

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0025] Figure 1 It is a flow operation diagram of a clinical medical practice skill evaluation system;

[0026] Figure 2 It is a flow chart of a clinical medical practice skill evaluation system. Detailed implementation manners

[0027] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in combination with the drawings and preferred embodiments, detail the specific implementation manners, structures, features, and effects according to the present invention as follows.

[0028] Embodiment 1

[0029] In the clinical practice skill assessment scenario of medical colleges and universities, the intelligent clinical medical practice skill evaluation system of the present invention plays an important role.

[0030] The teaching hospital of the school provides the electronic medical record data of real patients through a standardized interface, covering rich case information in multiple departments such as internal medicine, surgery, gynecology and obstetrics, and pediatrics. At the same time, in the simulated assessment scenario, a high-precision motion capture device is used to record the posture information of candidates when performing surgical operations, physical examinations and other actions at a frequency of 120 frames per second, ensuring that every subtle movement can be accurately captured. The microphone array omnidirectionally collects the voice communication content between candidates and virtual patients and team members, with excellent noise reduction performance, and can clearly collect voice data even in a noisy simulated environment. The physiological monitor real-time monitors the physiological indicators of candidates such as heart rate, electroencephalogram, and blood pressure. The camera records the image and video data during the operation at 4K resolution, and the system preprocesses these data and performs multi-modal data fusion.

[0031] According to the teaching syllabus and assessment requirements, the system extracts typical disease characteristics from electronic medical record data, combines randomly generated characteristics, knowledge in the medical knowledge graph, and the latest medical research results to generate intelligent virtual patients. The virtual patient disease generation formula is used: P = α·E + β·R + γ·N + δ·C, where P is the disease characteristic vector of the generated intelligent virtual patient, E is the typical disease characteristic vector extracted from electronic medical record data, obtained through dimensionality reduction algorithms such as clustering analysis, R is the randomly generated disease characteristic vector, randomly generated by the system according to a certain probability distribution, N is the disease characteristic vector generated based on the medical knowledge graph, obtained by extracting and integrating relevant information from the medical knowledge graph database, C is the disease characteristic vector generated according to current medical research hotspots and new discoveries, obtained by collecting and analyzing the latest medical research literature, etc., α, β, γ, δ are weight coefficients, and α + β + γ + δ = 1. When generating virtual patients for appendicitis cases, clinical medical experts score according to the importance of different factors in virtual patient generation, and determine that α = 0.5, β = 0.2, γ = 0.2, δ = 0.1, that is, it focuses more on generating virtual patients based on the typical disease characteristics in electronic medical record data. After generating 100 appendicitis virtual patients and using them for simulation assessment, collecting candidates' feedback and expert evaluation opinions, it is found that 30% of the candidates reflect that the disease conditions of the virtual patients are too patterned and lack variation. Further analysis reveals that the contribution of randomly generated characteristics to disease diversity is insufficient. The weights are adjusted to α = 0.4, β = 0.3, γ = 0.2, δ = 0.1, and 100 virtual patients are generated again for assessment. The candidates' feedback shows that the disease diversity has improved, and the proportion of candidates who think the disease conditions are more in line with the actual situation has increased to 70%. For appendicitis virtual patients, the system will simulate different stages of onset, such as the stage with atypical early symptoms, the stage of typical right lower abdominal pain, and the possible complication stages (such as appendiceal perforation, peritonitis, etc.). When generating disease characteristics, not only symptoms (such as the nature, degree, and location change of abdominal pain, accompanying symptoms such as nausea and vomiting) are considered, but also laboratory test indicators (such as white blood cell count, neutrophil ratio, etc.) and imaging examination results (such as the shape, size, and surrounding exudation of the appendix) are combined. At the same time, according to the new progress of medical research, such as the impact of minimally invasive treatment methods for appendicitis on the disease condition, the disease characteristics and treatment responses of virtual patients are adjusted. To make the generated disease conditions more in line with the actual uncertainty, the disease uncertainty introduction formula is used: Among them, ΔP is the introduced uncertainty adjustment of the disease, and U is the uncertainty coefficient. According to the actual clinical situation and assessment needs, U=0.3 was initially set. In the assessment, it was found that the candidates generally reflected that the changes in the disease were highly predictable and the assessment difficulty was relatively low. After analyzing the assessment results of 80 candidates, it was found that the average score was high and the discrimination was not obvious. Therefore, the U value was adjusted to 0.5. After the assessment was conducted again, the average score of the candidates decreased, and the standard deviation of the score increased from 10 to 15, indicating that the discrimination was improved. At this time, it is considered that U=0.5 is more appropriate, P i is the i-th eigenvalue in the disease feature vector, is the mean of all eigenvalues ​​in the disease feature vector, and m is the number of dimensions of the disease feature vector, which is determined by the construction method of the disease feature vector.

[0032] During the exam, the system monitors the candidate's diagnosis and treatment plan in real time. When the candidate makes decisions such as issuing a checkup order and formulating a treatment plan, the system calculates the amount of change in the condition based on the effect and intensity of the decision, and predicts the evolution of the condition. For example, when the candidate is diagnosed with appendicitis and chooses to use antibiotics for treatment, the system will determine the change in the condition based on the type and dosage of the antibiotics and the medication time entered by the candidate. If the drug is selected correctly and the dosage is appropriate, the virtual patient's abdominal pain symptoms will gradually ease, and indicators such as white blood cell count will gradually return to normal. If the candidate delays diagnosis or the treatment plan is unreasonable, such as failure to undergo surgery in time, resulting in appendicitis perforation, the system will predict the evolution of the condition based on the formula: Simulate the process of disease progression, where S t+1 is the predicted disease status value of the next time step, S t is the disease state value at the current time step, θ is the disease evolution coefficient, and θ=0.4 is initially set according to the general development law of the disease and experience. For the adjustment process and data of the disease evolution coefficient of appendicitis, it was found in the simulation evaluation that the disease evolution speed was inconsistent with the actual situation and was too fast. After analyzing the disease evolution of 70 simulation evaluations, it was found that the actual disease evolution speed was 20% faster than the predicted speed, so the θ value was adjusted to 0.3. When the disease evolution was evaluated again, the conformity of the disease evolution with the actual situation increased from 60% to 75%. ΔS is the change in the disease caused by the current decision. is the random interference coefficient, which is initially set according to the degree of uncertainty in actual clinical practice In the exam, it was found that the uncertainty of the epidemic was not well reflected, and candidates were prone to predicting the development of the disease. After analyzing the feedback from 90 candidates, it was found that the proportion of candidates who believed that the disease was predictable was as high as 60%. The value was adjusted to 0.3. When the test was repeated, the proportion of candidates who believed that the condition was predictable dropped to 40%. More appropriate, ε is a random interference term, randomly generated by the system according to a preset probability distribution. At this time, symptoms of peritonitis will appear, such as abdominal pain all over, rebound tenderness, muscle tension in the abdomen, etc. At the same time, relevant examination indicators will also deteriorate further. After the assessment is over, the system calculates the scores of the examinees on individual indicators such as diagnostic accuracy, rationality of treatment plan, communication ability, etc. according to the pre-constructed evaluation index system, and then obtains the final assessment result by synthesizing the scores of each indicator. The individual indicator score formula is used: Among them, Score single is the score of an individual indicator, p is the number of sub-evaluation items under this individual indicator, determined by the developers of the assessment system according to the specific setting of the evaluation index, is the weight of the i-th sub-evaluation item. In the diagnostic accuracy index, 3 sub-evaluation items of symptom judgment, disease classification, and differential diagnosis are set. According to the importance of each sub-evaluation item in the individual indicator, scores are given to determine the symptom judgment weight Disease classification weight Differential diagnosis weight When analyzing the diagnostic accuracy index scores of 120 examinees, it was found that the scores of the disease classification sub-evaluation item were generally high and had too much influence on the final score, while the score differentiation of the differential diagnosis sub-evaluation item was not obvious. The weights were adjusted to symptom judgment weight Disease classification weight Differential diagnosis weight After re-evaluation, the score differentiation of the diagnostic accuracy index increased, and the standard deviation increased from 8 before to 12. is the matching degree score of the examinee on the i-th sub-evaluation item, obtained by comparing and analyzing the examinee's performance with the standard. The comprehensive score formula is used: Among them, Score total is the comprehensive score, q is the total number of evaluation indicators, preset by the developers of the assessment system, ω k is the weight of the k-th evaluation indicator. When analyzing the results of multiple rounds of evaluations, it was found that the correlation between the scores of the rationality of treatment plan indicator and the examinees' actual clinical ability was not as expected, while communication ability was becoming more and more important in the actual clinical scenario. Therefore, the weights were adjusted to diagnostic accuracy weight ω1 = 0.4, rationality of treatment plan weight ω2 = 0.3, and communication ability weight ω3 = 0.3. After adjustment, when analyzing the evaluation results of 100 examinees, it was found that the correlation between the comprehensive score and the examinees' performance in actual clinical practice increased from 0.6 before to 0.7. is the score of the examinee on the k-th evaluation index. When evaluating the diagnostic accuracy, not only whether the examinee correctly diagnoses the disease is considered, but also the timeliness and comprehensiveness of the diagnosis are evaluated, such as whether important symptoms or examination results are missed. For the evaluation of the rationality of the treatment plan, factors such as the choice of treatment method, the standard use of drugs, and the feasibility of surgical operations are considered.

[0033] The examinee interacts with the virtual patient through virtual reality or augmented reality devices. The system reasonably arranges the information display order according to the urgency, relevance, timeliness, and importance of the information. For example, when the condition of the virtual patient suddenly deteriorates, the emergency prompt information will be preferentially displayed to the examinee to ensure that the examinee can make correct decisions in a timely manner. During the interaction process, the virtual reality device provides the examinee with a highly immersive experience. The examinee can conduct a detailed physical examination in the virtual environment. For example, when palpating the abdomen, the examinee can feel the muscle tension and the location of tenderness of the virtual patient. The augmented reality device can superimpose the relevant information of the virtual patient in the real scene. For example, during a surgical operation, the device can display the anatomical structure of the surgical site, the location of important blood vessels and nerves in real time to assist the examinee in accurate operation. At the same time, the system will update the displayed information in real time according to the examinee's operations and the changes in the condition, such as the report of examination results and the prompt of the condition change, to help the examinee understand the progress of the condition and the effect of their operations in a timely manner. This interaction method not only improves the efficiency of the assessment but also provides the examinee with a more realistic clinical practice experience.

[0034] Example Two

[0035] In the scenario of skill improvement training and regular assessment of in-service doctors in a hospital, the system of the present invention can also be effectively applied.

[0036] The hospital's information system provides rich electronic medical record data covering various common and rare diseases, including not only the basic diagnosis and treatment information of patients but also multi-dimensional information such as long-term follow-up data and gene detection results. During the training and assessment process, multi-modal data during the interaction between the doctor and the virtual patient is collected. The motion capture device can track the gestures and body postures of the doctor during various operations in real time, such as the actions of cardiologists performing heart auscultation and dermatologists observing skin lesions. The voice collection device can not only clearly record the conversation between the doctor and the virtual patient but also analyze the emotional tendency and the use of professional terms in the voice. The physiological index monitoring device can continuously monitor the physiological reactions of the doctor during the diagnosis and treatment process, such as changes in heart rate variability and electroencephalogram activity.

[0037] Based on the training objectives and assessment requirements, the system customizes personalized virtual patients. For newly emerging diseases or treatment methods, the system generates corresponding medical conditions in combination with the latest medical research hotspots. For example, the system can generate virtual patients with the symptoms and disease progression characteristics of novel coronavirus infection for doctors to conduct simulated diagnosis and treatment. During the training process, doctors interact with the virtual patients multiple times, and the system continuously adjusts the medical conditions to simulate different clinical situations, helping doctors improve their ability to handle complex medical conditions.

[0038] For virtual patients with novel coronavirus infection, the system simulates different stages from asymptomatic infection, mild cases, severe cases to critical cases, as well as various possible complications, such as respiratory failure, heart injury, thrombosis, etc. At the same time, in combination with the latest diagnosis and treatment guidelines, the system adjusts the responses of virtual patients to different treatment measures, such as antiviral drugs, immunotherapy, respiratory support, etc. During the interaction between doctors and virtual patients, the system will provide real-time feedback on the changes in the medical condition according to the doctor's decisions, guiding doctors to deeply think about and analyze the medical condition, and improving the diagnosis and treatment level. In addition to newly emerging diseases, for some rare diseases, the system also refers to case reports and research results worldwide to generate representative virtual patients. During the training process, different difficulty levels are set, from basic diagnosis and treatment process training to multidisciplinary collaborative management of complex medical conditions, gradually improving doctors' capabilities.

[0039] The system monitors doctors' decisions in real-time and dynamically adjusts the medical conditions of virtual patients according to the evolution prediction formula. After each interaction, the system immediately provides a detailed evaluation report, including the scores and analysis of doctors on various evaluation indicators. For example, it points out the key symptoms missed by doctors during the diagnosis process and the unreasonable points in the treatment plan. Doctors can improve their clinical skills targeted according to the feedback information. At the same time, the hospital can formulate personalized training plans for doctors based on their comprehensive scores to improve the overall medical level.

[0040] The evaluation report not only includes the scores of doctors on traditional indicators such as diagnostic accuracy, rationality of treatment plans, and communication skills, but also evaluates doctors' decision-making ability, teamwork ability, and application ability of the latest medical knowledge when facing uncertainties. For example, when dealing with complex medical conditions, whether doctors can communicate and cooperate with doctors in other departments in a timely manner, and whether they can accurately apply the latest research results and treatment methods. For doctors with unsatisfactory evaluation results, the hospital will arrange a dedicated tutor for one-on-one guidance and conduct intensive training on the weak links of doctors. For doctors with excellent performance, it will provide higher-level training opportunities, such as participating in international academic exchanges and cutting-edge research projects, to encourage doctors to continuously improve their professional levels.

[0041] With the continuous update of medical knowledge and the accumulation of clinical practice, the system will regularly adjust the parameters and weights of each module. For example, when a new treatment guideline is released, the system will correspondingly adjust the decision-making effect coefficient and the weights of evaluation indicators to ensure that the content of training and evaluation always remains consistent with the latest medical standards. Through this continuous optimization method, the system can continuously adapt to the changes in clinical practice and provide more effective skill improvement and evaluation services for doctors.

[0042] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments by using the disclosed technical content within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A clinical medicine practice skill assessment system, characterized in that, The system includes the following components: Comprehensive data processing module: Collect and preprocess the electronic medical record data of real patients and the multi-modal data of examinees. By fusing the characteristics of various modal data and cleaning the electronic medical record data, it provides data for subsequent modules. Intelligent virtual patient generation module: Analyze the preprocessed electronic medical record data, combine the typical characteristics, random characteristics, medical knowledge graph characteristics, and new characteristics of medical research of the electronic medical record to construct an intelligent virtual patient model, and introduce the uncertainty of the condition to generate a virtual patient condition that conforms to clinical reality. Disease condition dynamic regulation module: Real-time monitor the decisions of examinees during the simulation assessment, calculate the change amount of the virtual patient's disease condition based on the decisions, and predict the evolution of the disease condition, so that the virtual patient's disease condition changes dynamically with the examinee's decisions, simulating the real clinical diagnosis and treatment process. Assessment and analysis module: Construct a multi-dimensional evaluation index system, calculate the scores of examinees on each single evaluation index and the comprehensive score respectively, and comprehensively evaluate the clinical practice skill level of examinees through the adjustment and optimization of the index weights. Interaction display module: Design an interaction interface using virtual reality or augmented reality technology, and achieve natural interaction through voice and gesture recognition technologies, and display the changes in the patient's disease condition, examination results, and operation prompt information in real time.

2. The clinical medicine practice skill evaluation system according to claim 1, characterized in that, The comprehensive data processing module collects and preprocesses the electronic medical record data of real patients and the multi-modal data of examinees. The electronic medical record data includes the patient's basic information, disease history, symptom manifestations, and various examination indicators. The multi-modal data of examinees includes action posture data, voice communication data, physiological index data, and image and video data.

3. The clinical medicine practice skill evaluation system according to claim 1, wherein The intelligent virtual patient generation module analyzes the preprocessed electronic medical record data. Specifically, it receives the preprocessed electronic medical record data from the comprehensive data processing module, parses the data format, extracts the key information related to disease diagnosis and treatment, and stores it in the database. It deeply analyzes and learns the parsed data, mines the hidden laws and patterns in the data, and constructs an intelligent virtual patient model based on it. At the same time, to make the virtual patient closer to the real clinical situation, uncertainty factors are introduced into the model, so that the disease condition performance and development of each virtual patient have randomness and differences.

4. The clinical medicine practice skill evaluation system according to claim 3, wherein The intelligent virtual patient generation module constructs an intelligent virtual patient model, and its model formula is: P = α·E + β·R + γ·N + δ·C, where P is the disease condition feature vector of the generated intelligent virtual patient, containing various disease condition information of the patient, E is the typical disease condition feature vector extracted from the electronic medical record data, R is the randomly generated disease condition feature vector, N is the disease condition feature vector generated based on the medical knowledge graph, reflecting the general laws of diseases, C is the disease condition feature vector generated according to the current medical research hotspots and new discoveries, making the virtual patient more timely, and α, β, γ, δ are the weight coefficients of E, R, N, C respectively.

5. The clinical medicine practice skill assessment system according to claim 3, wherein The intelligent virtual patient generation module introduces uncertainty factors into the model, and its uncertainty adjustment formula is: Among them, ΔP is the introduced disease condition uncertainty adjustment amount, which is used to increase uncertainty during the disease condition generation process. U is the uncertainty coefficient that controls the magnitude of uncertainty, and P i is the i-th eigenvalue in the disease condition feature vector, is the mean of all eigenvalues in the disease condition feature vector, and m is the number of dimensions of the disease condition feature vector.

6. The clinical medicine practice skill assessment system according to claim 1, wherein The disease condition dynamic regulation module monitors the decisions of candidates in the simulation assessment in real time. Specifically, it monitors the diagnosis and treatment decisions of candidates during the simulation assessment in real time, compares and analyzes the decisions with the pre-set standard diagnosis and treatment plans, judges the rationality and effectiveness of the decisions, and establishes a disease condition evolution model that can reflect the disease development law and treatment effect. Taking the candidates' decisions and the current condition of the virtual patient as inputs, it predicts the development direction and change degree of the disease condition. According to the prediction results of the disease condition evolution model, it adjusts the disease condition of the intelligent virtual patient in real time, and dynamically displays the development and change of the disease condition by changing the symptom manifestations and examination index methods of the virtual patient.

7. The clinical medicine practice skill assessment system according to claim 6, wherein The disease condition dynamic regulation module establishes a disease condition evolution model that can reflect the disease development law and treatment effect. Its model formula is: Among them, S t+1 is the predicted disease condition value at the next time step, S t is the disease condition value at the current time step, θ is the epidemic evolution coefficient, which controls the evolution speed of the epidemic with decisions and time, ΔS is the amount of epidemic change caused by the current decision, and its calculation formula is: ΔS is the amount of disease condition change of the virtual patient after the candidate makes a decision, l is the number of decisions made by the candidate, a j is the effect coefficient of the jth decision, which reflects the influence degree of the decision on the disease condition, D j is the intensity factor of the jth decision, b j is the decision sensitivity coefficient, which controls the response speed of the disease condition to the decision, S0 is the current disease condition value of the virtual patient, c j is the threshold of the jth decision, is the random interference coefficient, which introduces randomness to simulate the uncertainty in clinical practice. ∈ is the random interference term and follows a probability distribution.

8. The clinical medicine practice skill evaluation system according to claim 1, characterized in that The assessment and analysis module constructs a multi-dimensional evaluation index system, including evaluation indexes in aspects of diagnostic accuracy, rationality of treatment plan, emergency handling ability, communication ability, operation standardization, concentration and mental state.

9. The clinical medicine practice skill assessment system according to claim 1, characterized in that The evaluation and analysis module calculates the scores of candidates on each individual evaluation index and the comprehensive score respectively. By adjusting and optimizing the index weights, it comprehensively evaluates the clinical practice skill level of candidates. The score calculation formula for each individual evaluation index is as follows: Among them, Score single is the score of the candidate on a certain individual evaluation index, p is the number of sub-evaluation items under this individual index, is the weight of the i-th sub-evaluation item, which is determined according to the importance of each sub-evaluation item in this individual index, is the matching degree score of the candidate on the i-th sub-evaluation item, which is obtained by comparing and analyzing the performance of the candidate on this sub-evaluation item with the standard. Its comprehensive score formula is as follows: Among them, Score total is the comprehensive score of the candidate, reflecting the clinical practice skill level of the candidate, q is the total number of evaluation indexes, ω k is the weight of the k-th evaluation index, is the score of the candidate on the k-th evaluation index.

Images