WO2013029242A1 - Medical training method and system thereof - Google Patents

Abstract

A medical training method and system thereof. The medical training method comprises: obtaining case data of a plurality of clinical cases and corresponding diagnosis results of each of the plurality of clinical cases; forming training examples based on the obtained case data of the clinical cases and the diagnosis results, wherein the case data of one clinical case and the corresponding diagnosis results of the clinical case constitute one training example (101); presenting the case data of the current training example to trainee for simulating diagnosis (102); receiving the stimulated diagnosis results from the trainee diagnosed with the presented case data (103); comparing the stimulated diagnosis results with the diagnosis results of the current training example and/or comparatively displaying the stimulated diagnosis results and the diagnosis results of the current training example (104). The medical training method and system thereof can effectively improve the diagnosis level of physicians in small hospitals so that the functions of the small hospitals can be fully put into practice.

Description

 ,

TECHNICAL FIELD The present invention relates to the field of medicine, and in particular to a medical training method and system. BACKGROUND OF THE INVENTION At present, there are not only large hospitals with strong diagnostic capabilities, but also many community hospitals, small hospitals such as county and township hospitals. The purpose of establishing these small hospitals is to expand the coverage of medical care and divert the number of patients in large hospitals, in order to alleviate the influx of patients into large hospitals, making registration difficult, long waiting time for medical treatment, and incomplete medical coverage in remote areas. And other issues.

 Due to the advantages of working environment, treatment and medical conditions, senior doctors and doctors with higher medical education are still mainly concentrated in large hospitals, while community hospitals and small hospitals such as county and township hospitals have relatively low entry barriers. Therefore, the total level of doctors in these hospitals may be relatively low. This makes large hospitals not only have the human resources to handle complex cases, but also has more experience in dealing with conventional diseases than small hospitals because of the relatively large number of patients. As a result, some patients will still go to the big hospitals for treatment, especially those with a slightly more complicated condition. This will not only waste the patient's human and financial resources, but also can not really play the role of a small hospital. In addition, because the technical level of some doctors in small hospitals is not enough, the probability of misdiagnosis may be relatively high, and some emergency departments may be helpless, and the patient's condition may be delayed during the transfer process.

 In order to be able to truly play the role of a small hospital, a telemedicine program has been proposed, in which small hospitals transmit case information to large hospitals, and doctors at large hospitals still diagnose the case based on transmitted case information at a remote location and will diagnose As a result, or a further treatment is sent back to a small hospital. To a certain extent, the program can prompt patients to go to small hospitals for medical treatment. However, because telemedicine still needs doctors from small hospitals for diagnosis, it will still add to the burden of major hospitals. And in telemedicine, the network layout, speed, burden, and real-time diagnosis are still issues that still need to be solved.

It can be seen that the fundamental way to make small hospitals play their due role is to improve the diagnostic level of doctors in small hospitals. In addition, there is an urgent need for some medical personnel with learning needs to find a way to quickly improve their abilities. SUMMARY OF THE INVENTION In view of the above, the present invention provides a medical training method and system for efficiently improving a routine diagnosis level of a doctor.

 The medical training method provided by an embodiment of the present invention includes: acquiring case data of a plurality of clinical cases and a diagnosis result corresponding to each of the plurality of clinical cases; forming training according to case data and diagnosis results of the obtained clinical cases For example, the case data of one clinical case and the diagnosis result corresponding to the clinical case constitute a training paradigm; the case data in the current training paradigm is presented to the trainee for simulation diagnosis; and the trainee receives the case data of the present Simulating the diagnostic result; comparing the simulated diagnostic result with the diagnostic result in the current training paradigm and/or comparing the simulated diagnostic result with the diagnostic result in the current training paradigm.

 In a specific embodiment of the present invention, the step of comparing the simulated diagnosis result with the diagnosis result in the current training paradigm includes: comparing the simulated diagnosis result with a diagnosis result in the current training paradigm The degree is compared, and the simulated diagnosis result is scored according to the similarity comparison result.

 In a specific embodiment of the present invention, the step of acquiring case data of a plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases comprises: collecting case data of clinical cases from each data source and the The diagnosis result corresponding to the clinical case; and the step of forming the training paradigm according to the acquired case data of the clinical case and the diagnosis result includes: classifying the case data and/or the diagnosis result of the collected clinical case according to the set condition, and classifying the specific category The case data of the clinical case and the corresponding diagnosis result are associated with the training example; or include: correlating the collected case data of the clinical case and the corresponding diagnosis result to form a teaching case, and performing the teaching case according to the set condition Classification, using specific categories of teaching cases as training examples.

 In a specific embodiment of the present invention, the setting condition includes one or any combination of the following: data characteristics of case data, wherein the data characteristics include at least one of a patient's gender, age, diseased part, and disease type. One;

 The difficulty of the diagnosis results;

 Case data and/or department category to which the diagnosis results belong.

 In a specific embodiment of the present invention, before the case data in the current training paradigm is presented to the trainee for the simulation diagnosis, the method further includes: determining a current training paradigm presented to the trainee according to the training rule; The training rules include one of the following:

Randomly presenting different training examples in the category selected by the trainee to the trainee; , randomly presenting different training examples in the category selected by the manager to the trainee;

 Different training examples in the categories selected by the trainee are presented to the trainee according to the ease of diagnosis;

 Different training examples in the categories selected by the manager are presented to the trainee according to the ease of diagnosis;

 Different training examples in the category selected by the trainee are presented to the trainee according to the category of the case and/or the category of the diagnosis result;

 Different training examples in the category selected by the manager are presented to the trainee according to the case data and/or the category of the department to which the diagnosis results belong.

 In a specific embodiment of the present invention, the step of acquiring case data of a plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases includes:

 Determine the case data of the clinical cases that need to be obtained and the conditions that the corresponding diagnostic results should meet, based on the training examples that the trainees have used and the pre-determined distribution of training sample categories;

 The case data of the clinical case and the diagnosis result corresponding to the clinical case are collected from each data source according to the determined conditions;

 Wherein, the training examples that the trainee has used include: the number of training examples that have been used in each category; the predetermined training example category distribution includes: a predetermined training in each category The number of examples.

 In a specific embodiment of the present invention, the step of collecting case data of the clinical case from each data source according to the determined condition and the diagnosis result corresponding to the clinical case includes:

 Setting a central server, configured to obtain case data of the clinical case and corresponding diagnosis result from each data source; and collect case data of the clinical case and the diagnosis result corresponding to the clinical case from the central server according to the determined condition;

 and / or,

 Setting a central server, configured to obtain a case data index of the clinical case from each data source; retrieve a corresponding case data index from the central server according to the determined condition, and determine a data source where the case data of the required clinical case is located, Case data of the clinical case and corresponding diagnostic results are collected from the determined data sources.

In a specific embodiment of the present invention, the step of acquiring case data of a plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases comprises: collecting more data from each data source during a network off-peak period One , case data of clinical cases and the corresponding diagnosis results for each clinical case in the clinical case.

 In a specific embodiment of the present invention, the step of acquiring case data of a plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases comprises: collecting case data of multiple clinical cases from each data source And the diagnosis result corresponding to each clinical case in the clinical case, and the case data and the corresponding diagnosis result from each data source are processed into a unified format.

 In a specific embodiment of the present invention, the method further includes: acquiring case data to be diagnosed locally by the trainee, and presenting the local case data to be diagnosed in a presentation manner that presents the same case data in the current training paradigm. The trainee.

 In a specific embodiment of the present invention, the step of acquiring case data of a plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases includes:

 Obtaining case data from a number of actual clinical cases from a clinically experienced hospital and the diagnosis made by the doctor on the actual clinical case, especially the diagnosis made by a high-level doctor; or

 Obtain case data of clinical cases identified by the medical education department and the diagnosis results corresponding to the clinical cases. In a specific embodiment of the present invention, the case data includes one or any combination of the following: a gender, an age, a diseased part, a disease type, a symptom description, and image data of the patient;

 The image data includes a computed tomography system CT, a nuclear magnetic resonance imaging system MRI, a computer X-ray imaging system CR, a digital X-ray imaging system DR, a digital subtraction angiography device DSA, or a single-photon computed tomography scan. At least one of the instruments ECT.

 A medical training system according to an embodiment of the present invention includes:

 a data acquisition module, configured to acquire case data of a plurality of clinical cases and a diagnosis result corresponding to each of the plurality of clinical cases;

 a training example generation module, configured to form a training paradigm according to the obtained case data of the clinical case and the diagnosis result, wherein the case data of one clinical case and the diagnosis result corresponding to the clinical case constitute a training example; the simulation diagnosis module is configured to The case data in the current training paradigm is presented to the trainee for a simulated diagnosis, and receives the simulated diagnosis result of the presented case data of the trainee;

 The result judging module is configured to compare the simulated diagnosis result with the diagnosis result in the current training paradigm, and/or compare the simulated diagnosis result with the diagnosis result in the current training paradigm.

 In an embodiment of the present invention, the result judging module includes:

a scoring sub-module for using the simulated diagnostic result to be similar to the diagnostic result in the current training paradigm The degree is compared, and the simulated diagnosis result is scored according to the similarity comparison result.

 In a specific embodiment of the present invention, the data acquisition module collects case data of a clinical case and a diagnosis result corresponding to the clinical case from each data source;

 The training sample generation module includes:

 a first classification sub-module, configured to classify case data and/or diagnosis results collected by the data acquisition module according to a set condition;

 a first correlation sub-module, configured to correlate case data of a specific category of clinical cases and corresponding diagnosis results to obtain a training paradigm;

 Alternatively, the training example generation module includes:

 a second association sub-module, configured to associate case data of the clinical cases collected by the data acquisition module with corresponding diagnosis results to form a teaching case;

 The second classification sub-module is configured to classify the teaching cases according to the set conditions, and use a specific category of teaching cases as a training example.

 In an embodiment of the present invention, the first classification sub-module classifies case data and/or diagnosis results collected by the data acquisition module according to one of the following conditions or any combination of the following conditions:

 Data characteristics of case data, wherein the data characteristics include at least one of a patient's gender, age, diseased site, and type of disease;

 The difficulty of the diagnosis results;

 Case data and/or department category to which the diagnosis results belong;

 Or the second classification sub-module classifies the teaching case according to a setting condition of one of the following or any combination thereof;

 Data characteristics of case data, wherein the data characteristics include at least one of a patient's gender, age, diseased site, and type of disease;

 The difficulty of the diagnosis results;

 Case data and/or department category to which the diagnosis results belong.

 In a specific embodiment of the present invention, the system further includes: a presentation example determining module, configured to determine a current training paradigm presented to the trainee according to a training rule;

Wherein, the training rule includes one of the following: And randomly presenting different training examples in the category selected by the trainee to the trainee;

 Randomly presenting different training examples in the category selected by the manager to the trainee;

 Different training examples in the categories selected by the trainee are presented to the trainee according to the ease of diagnosis;

 Different training examples in the categories selected by the manager are presented to the trainee according to the ease of diagnosis;

 Different training examples in the category selected by the trainee are presented to the trainee according to the category of the case and/or the category of the diagnosis result;

 Different training examples in the category selected by the manager are presented to the trainee according to the case data and/or the category of the department to which the diagnosis results belong.

 In an embodiment of the present invention, the data acquisition module includes:

 The overall management sub-module is used to determine the case data of the clinical cases that need to be obtained and the conditions that the corresponding diagnosis results should meet according to the training examples that the trainees have used and the pre-determined distribution of the training case categories;

 a collection submodule, configured to collect case data of a clinical case and a diagnosis result corresponding to the clinical case from each data source according to the determined condition;

 Wherein, the training examples that the trainee has used include: the number of training examples that have been used in each category; the predetermined training example category distribution includes: a predetermined training in each category The number of examples.

 In a specific embodiment of the present invention, the system further includes:

 a central server, configured to obtain case data of clinical cases and corresponding diagnosis results from each data source; and/or obtain case data index of clinical cases from each data source;

 The collecting sub-module collects case data of the clinical case and the diagnosis result corresponding to the clinical case from the central server according to the determined condition; and/or, according to the determined condition, retrieves the corresponding case from the central server The data is indexed, and the data source of the case data of the required clinical case is determined, and the case data of the clinical case and the corresponding diagnosis result are collected from the determined data source.

 In a specific embodiment of the present invention, the data acquisition module collects case data of a plurality of clinical cases and diagnostic results corresponding to each clinical case of the clinical cases from each data source during a network off-peak period.

In a specific embodiment of the present invention, the data acquisition module collects multiple clinical cases from each data source. The case data and the diagnosis results corresponding to each clinical case in the clinical case, and the case data from each data source and the corresponding diagnosis result are processed into a unified format.

 In a specific embodiment of the present invention, the system further includes:

 The on-the-job diagnosis module is configured to obtain the case data to be diagnosed locally by the trainee, and present the local case data to be diagnosed to the trainee in the same presentation manner as presenting the case data in the current training example.

 In a specific embodiment of the present invention, the data acquisition module obtains case data of a plurality of actual clinical cases from a clinically experienced hospital and a diagnosis result of the doctor on the actual clinical case, especially a high-level doctor. The diagnosis result; or, the case data of the clinical case identified by the medical education department and the diagnosis result corresponding to the clinical case.

 In a specific embodiment of the present invention, the data acquisition module acquires case data of the plurality of clinical cases including one or any combination of the following and a diagnosis result corresponding to each of the plurality of clinical cases;

 Patient's gender, age, location, type of disease, symptom description and image data;

 The image data includes a computer tomography system (CT), a magnetic resonance imaging system (MRI), a computer X-ray imaging system (CR), a digital radiography system (DR), and a digital subtraction angiography device. (DSA) or emit at least one of a single photon computed tomography (ECT).

 As can be seen from the above scheme, since the case information and the diagnosis result of the specific clinical case are used as the training examples in the present invention, the training of the trainees can be effectively improved, and the training level of the trainees can be efficiently improved. And compared to traditional theoretical training and teaching, training with actual clinical cases allows trainees to gain more direct learning and experience, avoiding theoretical incomprehensibility and disconnection from practice, and helping trainees to quickly accumulate clinical diagnostic experience. And through the comparison between the diagnosis given by the trainee and the diagnosis given by the experienced doctor, the trainee can quickly realize the deficiency of his diagnosis and strengthen the diagnosis level. Through the training method provided by the present invention, the doctor's routine diagnosis level can be effectively improved, thereby realizing the purpose of setting up a small hospital.

 In addition, by automatically obtaining the case data of each clinical case processed by each high-level doctor of each data source and the corresponding diagnosis result, the human and material resources brought by the manual collection can be omitted, and the dynamic update training paradigm can be maximized. Further, it can ensure that the trainees get rich and up-to-date training examples, and maintain the advanced level of training as much as possible, avoiding the problem of backward medical knowledge caused by unsuccessful updates in the fixed training paradigm.

In addition, according to the training examples that the trainees have used and the pre-determined distribution of training paradigm categories, the case data of the clinical cases that need to be obtained and the corresponding diagnostic results should be met, and the case data and diagnosis should be obtained according to the conditions. As a result, the training examples obtained by different trainees or different categories of trainees are different, and this difference is maintained after the training examples are updated. That is, the training examples required for targeted acquisition can be achieved. , further improve the efficiency of training.

 Further, the data acquisition process can be made more efficient by setting up a central server for data relay and/or index queries.

 In addition, by further setting up the examination function, the medical training system can further realize the partial functions of the educational institution, so that the trainees can obtain the corresponding qualifications while improving their skills.

 In addition, by obtaining the case data to be diagnosed locally by the trainee and presenting it to the trainee in the same presentation of the case data in the training paradigm, the trainee can first be trained locally without using new equipment, new systems, There is also no need to change locations, that is, to enable trainees to receive training locally at work, which makes training easier and easier for small hospitals to promote. Moreover, it is also possible to integrate the diagnosis that the trainee needs to perform in the normal work to the training method and system provided by the present invention, that is, the trainer's usual work and the interface used in the training are the same, so that the trainee does not need to pay any extra Efforts can use this training method and training system, and also make the training method and training system provided by the invention closer to the trainee's usual work, to minimize the strangeness of the trainees when they are trained and to maximize the training. Examples help with actual diagnostic work. BRIEF DESCRIPTION OF THE DRAWINGS The above and other features and advantages of the present invention will become apparent to those skilled in the <RTIgt

 FIG. 1 is an exemplary flowchart of a medical training method in an embodiment of the present invention.

 FIG. 2 is a schematic diagnostic interaction interface in an embodiment of the present invention.

 FIG. 3 is a flowchart of a specific implementation method of step 101 shown in FIG. 1 according to an embodiment of the present invention.

 FIG. 4 is a schematic diagram of dynamically acquiring case data and corresponding diagnosis results according to an embodiment of the present invention.

 FIG. 5 is an exemplary flowchart of a medical examination method in an embodiment of the present invention.

 6 is an exemplary structural diagram of a medical training system in an embodiment of the present invention.

 FIG. 7 is a schematic structural diagram of a training example generation module in the system shown in FIG. 6.

 FIG. 8 is another schematic structural diagram of a training example generation module in the system shown in FIG. 6.

 FIG. 9 is a schematic structural diagram of a simulated diagnostic module in the system shown in FIG. 6.

 FIG. 10 is a schematic structural diagram of a data acquisition module in the system shown in FIG. 6.

FIG. 11 is a schematic structural view of a structure discriminating module in the system shown in FIG. 6. 12 is an exemplary structural diagram of a medical examination system in an embodiment of the present invention.

 In the figure: 101 - Get Training Example 102 - Present Case Data 103 - Receive Simulation Diagnostic Results 104 - Result Comparison and/or Comparison Display 301 - Acquisition 302 - Format Processing 303 - Post-Classification Association 304 - Association Category 501 - Get Exam Example 502 - Presenting Case Data and Receiving Examination Diagnostic Results 503 - Results Score 504 - Determining Examination Scores 601 - Data Acquisition Module 602 - Training Example Generation Module 603 - Simulation Diagnostics Module 604 - Results Discriminating Module 605 - Central Server 606 - On-Site Diagnostics Module 607 - Presentation Example Determination Module 701 - First Classification Sub-Module 702 - First Association Sub-Module 801 - Second Association Sub-Module 802 - Second Classification Sub-Module 901 - Case Data Presentation Sub-Module 902 - Diagnostic Template Provisioning Sub-Module 903 - Diagnostic result receiving sub-module 1001 - Coordinating management sub-module 1002 - Collecting sub-module 1101 - Comparing sub-module 1102 - Scoring sub-module 1201 - Exam data acquisition module 1202 - Exam example generating module 1203 - Exam diagnostic module 1204-Competing scoring module 1205 - Exam Result Determination Module Specific Embodiment In the present invention, in order to efficiently improve the doctor's routine diagnosis level, Simulate the trainees with a large number of real clinical cases, and obtain the diagnosis results of these clinical cases one-on-one, and strengthen the diagnostic knowledge through comparison, so that they can learn how to diagnose from these clinical cases, based on the true The understanding and judgment of the case improves their skills. Usually, the diagnosis results of these clinical cases are from doctors with high level of experience in large hospitals, which can enable trainees to improve their diagnostic level according to the actual diagnosis of large hospitals.

 In practical applications, with the use of training examples by trainees, it is also possible to continuously expand clinical cases processed by high-level doctors, that is, to continuously obtain case data and corresponding diagnosis results of clinical cases of high-level doctors.

 The high-level doctors described in this article can be medical practitioners with high medical skills, a certain reputation in the industry, or medical practitioners with extensive clinical experience in larger hospitals.

 In order to make the objects, technical solutions and advantages of the present invention more comprehensible, the present invention will be further described in detail below.

 FIG. 1 is an exemplary flowchart of a medical training method in an embodiment of the present invention. As shown in Figure 1, the method includes the following steps:

 Step 101: Obtain case data of the clinical case and corresponding diagnosis result, and form a training example according to the obtained case data of the clinical case and the diagnosis result.

In this embodiment, the obtained case data of the clinical case and the corresponding diagnosis result may be actual diagnosis from actual doctors of the actual clinical case. Or, in order to achieve the purpose of medical examination, it can also be medical education. Case data and diagnosis results of clinical cases recognized by the Department of Education.

 The case data may include patient information and symptom related data. The patient information may include: patient gender, age, etc.; symptom related data may include: diseased part data, disease type data, symptom description data, and image data. The data of the diseased part may be information such as the location of the patient's complaint during the clinical pre-diagnosis or the location determined by the doctor. The symptom description data may be information such as the discomfort of the patient's complaint. The image data may be a computed tomography system (CT), a magnetic resonance imaging system (MRI), a computer X-ray imaging system (CR), a digital radiography system (DR), a digital subtraction angiography device (DSA). Or an image obtained by a single photon computed tomography (ECT) or the like. In order to protect the patient's privacy, the patient's identity information, such as name and ID number, can be removed when the case data is obtained.

 In the specific implementation, this step 101 can have multiple implementation manners. For example, the case data of the clinical cases processed by the high-level doctors manually collected and recorded and the corresponding diagnosis results may be obtained, and the case data of each clinical case and the corresponding diagnosis result are taken as a training example. It is also possible to automatically collect and aggregate the case data of each clinical case processed by each high-level doctor and the corresponding diagnosis result, and use the case data of each clinical case and the corresponding diagnosis result as a training example. Preferably, the system server can effect automatic acquisition of case data and/or diagnostic results through a network connection to the medical device.

 In this embodiment, when the training example is formed, for example, the case data and/or the diagnosis result of the collected clinical cases may be classified according to the set conditions, and the case data of the specific category of clinical cases and the corresponding diagnosis result are associated. The training examples can be obtained; or the case data of the collected clinical cases and the corresponding diagnosis results can be correlated to form a teaching case, and the teaching cases are classified according to the set conditions, and a specific category of teaching cases is taken as a training example. Specific classification methods and specific teaching cases are described in detail in subsequent embodiments, and are not described herein again. By classifying the training cases, it is possible to avoid giving the trainees a very complicated and redundant training information, and only form training examples for the qualified clinical cases, which can avoid the system burden and complicated implementation caused by the system handling too many clinical cases. problem.

 Step 102: Present case data in the current training paradigm to the trainee for simulation diagnosis.

 In the specific implementation, in this step 102, the trainee can select the content to be learned according to his own needs. For example, the doctor of the ENT may be more inclined to consult the training examples of the ENT, and the doctor of the internal medicine may be more inclined to consult the training example of the internal medicine. The surgeon may be more inclined to consult the training examples of the surgery, etc., so in this step, for example, the current training paradigm is determined according to the trainee's choice, and the case data in the current training paradigm is presented to the trainee for the simulation diagnosis.

In this embodiment, step 102 may further include the step of determining a current training paradigm presented to the trainee according to the training rules. The training rules can be, for example, the trainee's own choice, and can be the manager's choice. Here, the manager is, for example, a manager of a small hospital or a department manager or other training system manager. And, the training rules can be packaged The provisions for the categories of different training paradigms may also include provisions for the number of training paradigms, or may also include provisions for the difficulty level of the training paradigm, or may also include provisions for the category of the department to which the training paradigm belongs.

 For example, the training rules include one of the following:

 Randomly presenting different training examples in the category selected by the trainee to the trainee;

 Randomly presenting different training examples in the category selected by the manager to the trainee;

 Different training examples in the categories selected by the trainee are presented to the trainee according to the ease of diagnosis;

 Different training examples in the categories selected by the manager are presented to the trainee according to the ease of diagnosis;

 Different training examples in the category selected by the trainee are presented to the trainee according to the category of the case and/or the category of the diagnosis result;

 Different training examples in the category selected by the manager are presented to the trainee according to the case data and/or the category of the department to which the diagnosis results belong.

 The trainees themselves set examples of training rules. For example, the trainee is a general practitioner. He can set up 30% of surgical training examples, 30% of internal training examples, 20% of gynecological training examples, and pediatrics. The training paradigm accounts for 20%, and the training examples for each department appear in the order of easy and difficult.

 A simulated diagnostic interaction interface in an embodiment of the invention is shown in FIG. Among them, the case data of the current training paradigm include: chest radiograph of a 76-year-old male patient, clinical pre-diagnosis as frequent premature ventricular and cardiac insufficiency.

 Step 103: Receive a simulated diagnosis result of the trainee on the case data.

In the specific implementation, in order to facilitate the trainee to quickly input the simulation diagnosis result, the diagnosis template corresponding to the category of the training example can be further provided to the trainee for selection. The template may include diagnostic related terms and description information of various diagnostic conditions, etc., as shown in the left side of FIG. 2, "normal chest radiograph", "rib image", "original tuberculosis", "invasive pulmonary tuberculosis"","invasive pulmonary tuberculosis, semi-cavitation", "tuberculosis", "case-like pneumonia", "acute miliary tuberculosis", "congenital bronchial cyst", "bronchitis", "chronic bronchitis", "bronchial expansion""The diagnostic category, and each diagnostic category has its description below. For example, after deploying the "rib image" option, you can see that the thoracic symmetry, the ribs are natural, no deformities and bone destruction. The size, position and density of the two hilums are normal, and the texture of the two lungs is natural and undistorted. The two lungs are clear, no consolidation and no swelling of the lungs. There is no thickening and adhesion of the pleura. The trachea is centered, the mediastinum is centered, and there is no widening. The heart shape is within the normal range. The bilateral diaphragm is smooth, the rib angle Sharp, etc. "This kind of trainee can copy and choose from it, which improves the training efficiency and simplifies the comparison of the similarity of diagnosis results. Of course, in the actual application, the above diagnostic template may not be provided, but the trainee directly inputs the simulated diagnosis result. In addition, for the image data described in FIG. 2, the method may further provide image processing options for the trainee as shown in the upper right corner of FIG. 2, so that the trainee can clearly view various details of the image data as needed. feature.

 For the training example shown in Figure 2, the diagnosis result entered by the trainee in this example is "thoracic symmetry, natural rib shape, no deformity and bone destruction. The size, position and density of the two hilums are normal, and the two lungs are textured. In the case of a natural shape, there is no distortion or gathering. For example, the content shown in the area corresponding to the "write report" at the bottom of Figure 2 is shown.

 Step 104: Compare the simulated diagnosis result with the diagnosis result in the current training paradigm and/or compare the two.

 In the specific implementation, the method may be similar to the "result comparison" option or the "end diagnosis" option, when the trainee selects the similar "result comparison" option and/or "end diagnosis" option, The simulated diagnosis results are compared with the diagnostic results in the current training paradigm and the two are compared. As shown in FIG. 2, in this embodiment, after the user selects the “Compare with Reference Report” option, the simulated diagnosis result is compared with the diagnosis result in the current training example, and the two are compared and displayed.

 In the specific implementation, if the training system only needs to evaluate the diagnosis results input by the trainees, it is not necessary to compare the two. Alternatively, the training system can only display the diagnostic results in the training paradigm. However, in order to make the trainees better learn, it is better to compare the two to improve the level of diagnosis of the trainees as soon as possible.

 For the training example shown in Figure 2, the diagnosis result in the training example is "thoracic symmetry, natural rib shape, no deformity and bone destruction. The size, position and density of the two hilums are normal, and the two lungs are textured. The shape is natural, there is no distortion and gathering. The trachea is centered, the mediastinum is centered, and there is no widening. The shape of the heart is within the normal range. The case is shown in the example below, as shown in the area below the "Reference Report" in Figure 2. Content. By comparison, it is found that the diagnosis result input by the trainee lacks the part of "the trachea is centered, the mediastinum is centered, and there is no widening. The heart shape is within the normal range." Therefore, in this embodiment, this part can be colored in different colors. display. For example, if the same part is displayed in black, this part can be displayed in colors such as red, green, purple or blue.

 In the example shown in Fig. 2, left and right arrows are set in the lower right corner. By clicking the right arrow, the next training example can be determined as the current example, and the process returns to step 102.

 In addition, when the specific implementation, the similarity score of the above-mentioned simulated diagnosis result relative to the diagnosis result in the training example (ie, the reference diagnosis result) can be given, thereby improving the interest of the training, and also realizing the assessment function, and other corresponding Features.

In an embodiment of the present invention, the training examples of the same difficulty level may be divided into a group according to the difficulty level of the diagnosis result, and the training cases of the low difficulty level may be first presented. Give training The simulation is performed. When the trainee's similarity score for each training case reaches the set upgrade threshold, the training case of the next difficulty level is presented to the trainee for simulation diagnosis. Alternatively, the trainee may select a training case of each difficulty level to perform a simulation diagnosis.

 The following is a detailed description of a case in step 101 in which the system automatically collects and aggregates the case data of each clinical case processed by each high-level doctor and the corresponding diagnosis result, as shown in FIG. 3, and FIG. 3 shows A flowchart of a specific implementation method of step 101 shown in FIG. 1 , the method includes the following steps:

 Step 301: Collect case data of each clinical case processed by a high level doctor from each data source and corresponding diagnosis results.

 Since most of the high-level doctors are concentrated in high-level large hospitals, the data source described in this step can be a database of high-level large hospitals. That is, in this step, the case data of a plurality of actual clinical cases and the diagnosis results made by the doctor on the actual clinical case can be obtained from a clinically experienced hospital, especially the diagnosis result by a high-level doctor.

 Alternatively, the case data of the clinical case identified by the medical education department and the diagnosis result corresponding to the clinical case may be obtained in this step.

 In this step, the case data of the clinical cases processed by the high-level doctors and the corresponding diagnosis results can be collected directly from each data source.

 Alternatively, a central server may be set in the method, and the central server stores case data of the clinical cases processed by the high-level doctors collected from the data sources and corresponding diagnosis results, and the step may be The central server collects case data and corresponding diagnosis results of clinical cases processed by high-level doctors, that is, indirectly from each data source.

 In addition, in order to prevent the storage capacity of the central server from being stored in the central server when all the case data and the corresponding diagnosis result are stored, the central server can also obtain the case data of the clinical case processed by the high-level doctor only from each data source. Index, in this step, according to the case data index in the central server, the case data of the clinical cases processed by the high-level doctors and the corresponding diagnosis results are collected from the corresponding data sources.

 In addition, while storing the case data index in the central server, the case data of the clinical cases processed by the high level doctors obtained from each data source and the corresponding diagnosis results may also be stored. In this step, the first step may be The central server collects case data and corresponding diagnosis results of each clinical case processed by each high-level doctor, and the case data not included in the central server may be indexed according to the case data in the central server from the corresponding data sources. Case data and corresponding diagnosis results of each clinical case processed by each high-level doctor are collected.

In practical applications, step 301 can collect case data and corresponding diagnosis results of high-level doctor-processed clinical cases from various data sources during off-peak hours of the network (such as at night) to avoid data congestion during peak hours and reduce the network. negative , burden, speed up the collection process.

 And collecting case data through the central server is conducive to the supplement and update of case data.

 Step 302: Process case data and corresponding diagnosis results from each data source into a unified format.

 In practical applications, case data from different data sources and corresponding diagnostic results may be in different formats. Therefore, in order to facilitate management, case data from each data source and corresponding diagnosis results may be processed into a unified format. . Of course, if the case data from each data source and the corresponding diagnosis result have the same format, this step can be omitted.

 Step 303: classify the case data and the corresponding diagnosis result in a unified format according to the set condition, and associate the case data of the specific category of the clinical case with the corresponding diagnosis result to obtain a training example.

 The setting conditions include, for example, one of the following or any combination thereof: data characteristics of the case data; difficulty level of the diagnosis result; case type and/or category of the department to which the diagnosis result belongs. Wherein, the data characteristic includes at least one of a patient's gender, age, diseased part, and type of disease.

 For example, it is classified according to different age groups, genders, different diseased parts, different disease types, and the like. In addition, in this step, the case data and the corresponding diagnosis results after the unified format can be further classified according to the difficulty of the clinical case.

 Case data for a particular category of clinical cases and corresponding diagnostic results can be, for example, case data for clinical cases of males between the ages of 30 and 40 and corresponding diagnostic results. Select a specific category of clinical cases, that is, clinical cases selected or combined according to different categories.

 How to classify specifically can be determined according to actual needs, and is not limited here.

 In this embodiment, step 303 can also be replaced by step 304.

 Step 304: Associate the case data of the collected clinical cases and the corresponding diagnosis results to form a teaching case, and classify the teaching cases according to the set conditions, and use a specific category of teaching cases as a training example.

 For the specific implementation of step 304, reference may be made to step 303. Among the specific categories of teaching cases are, for example, teaching cases of complex diagnosis of the lungs.

 In practical applications, training rules can be optimally configured based on educational psychology, trainee characteristics, and the like. For example, doctors in different specialist disciplines are given priority in the training of disease types corresponding to the department, as well as training examples for the GP to balance the configuration of each disease type. The training rules can be determined according to actual needs, and are not limited here.

In practical applications, in order to provide continuous training for trainees, and to avoid regular training websites or training schools, after the training time is completed, the training will be over, and the problem of continuous learning cannot be realized, as the trainees have examples of training. , using, continually replenishing new training paradigms, ie, the method may further include: determining the current clinical case to be obtained based on the trainee's simulated (ie used) training paradigm and the pre-determined distribution of training paradigms The case data and the corresponding diagnostic results should meet the conditions, such as the data characteristics of the case data and the corresponding number of clinical cases. This step can not only ensure the continuity of the training, but also ensure that the training received by the trainees is relatively advanced, rather than the practice that has fallen behind.

 Wherein, the training examples that the trainee has used include: the number of training examples that have been used in each category; the predetermined training example category distribution includes: a predetermined training in each category The number of examples.

 Thereafter, in step 101 and step 301, case data and corresponding diagnoses of clinical cases processed by high-level doctors can be collected from each data source according to the determined conditions, such as the data characteristics of the case data and the number of corresponding clinical cases. result. Specifically, the method may include: for directly collecting from each data source, searching for each data source according to the determined condition, such as the data characteristic and the corresponding number of clinical cases, and obtaining the content that meets the requirement from the data source. Case data and corresponding diagnosis results.

 For the case of collecting directly from the central server, the case data satisfying the requirements and the corresponding diagnosis result may be obtained from the central server according to the determined conditions, such as the data characteristics and the corresponding number of clinical cases.

 For the case where only the case data index exists in the central server, the corresponding case data index may be retrieved from the central server according to the determined condition, such as the data characteristics and the corresponding number of clinical cases, and each corresponding is determined. The data source where the case data is located, and then the corresponding case data and its corresponding diagnosis result are collected from the determined data source.

 For the case where there is only a part of the case data and the corresponding diagnosis result in the central server, and there is a part of the case data index, the case data satisfying the requirement and the corresponding diagnosis result may be first obtained from the central server, for the central server. If there is no case data and corresponding diagnosis result, the corresponding case data index may be retrieved from the central server, and the data source of each corresponding case data is determined, and then the corresponding case data is collected from the determined data source. And its corresponding diagnosis results.

A schematic diagram of dynamically acquiring case data and corresponding diagnostic results is given in FIG. As shown in Fig. 4, the case of applying to a central hospital in Fig. 4 is taken as an example. In the hospital, a preferred allocation scheme is set for the inspection site, the type of equipment for collecting data, the data source, and the diagnosis result. The current ratio is given in Figure 4. As the trainee uses the training case, The matching ratio of each category will also change accordingly. Therefore, according to the trainee's simulated (ie read) training paradigm and the predetermined training paradigm allocation scheme, the data characteristics of the current case data to be acquired and Corresponding number of clinical cases, and further determine the data source by the foregoing method, and finally determine the current downloading , the task, Figure 4 further shows the progress of all task downloads, including the downloaded task and the task to be downloaded, as well as the download progress of the task to be downloaded.

 In practical applications, the examination function can be further provided in this embodiment. That is, the medical training method in this embodiment may further include the medical examination method as shown in FIG. The method can include the following steps:

 Step 501: Obtain case data of a plurality of clinical cases identified by the medical education department and diagnosis results corresponding to each of the plurality of clinical cases, and form an examination example according to the obtained case data of the clinical cases and the diagnosis result, wherein Case data for a clinical case and corresponding diagnostic results constitute an exam sample. Among them, case data of a plurality of actual clinical cases and doctors' diagnosis results of the actual clinical cases can be obtained from clinically-experienced hospitals, especially the diagnosis results made by high-level doctors.

 The specific implementation process of this step may be similar to the implementation process described in step 101, that is, there may be multiple implementations, and the implementation method similar to that described in FIG. 3 may also be adopted, in which case only the "training" is required. Replace the words with the words "exam". For example, it may also include: collecting case data and corresponding diagnosis results of clinical cases processed by a high-level doctor recognized by the medical education department from each data source. Case data from each data source and corresponding diagnostic results are processed into a uniform format. The processed case data and the corresponding diagnosis results are classified according to the data characteristics of the case data and/or the difficulty level of the clinical case. The classified case data and the corresponding diagnosis results are organized according to the set examination rules, and an examination example corresponding to each clinical case is generated, wherein the case data of one clinical case and the corresponding diagnosis result constitute an examination example.

 Step 502: Present case data in the current test sample to the trainee, and receive an examination result of the trainee on the case data.

 The specific implementation process of this step may be similar to the implementation process described in steps 102 to 103, and is not described here.

 Step 503: Compare the test diagnosis result with the diagnosis result in the current test sample to obtain a similarity score.

 Step 504: Determine the test score of the trainee according to the score of the trainee in each test sample in the current exam. Further, when the test score of the trainee reaches the preset pass threshold, the trainee may also be given a corresponding certificate, which may be an electronic piece issued by the network or a paper delivered by the relevant part.

 In practical applications, the medical examination method shown in Figure 5 can also exist separately.

 The training method in one embodiment of the present invention may further comprise the following steps:

Obtain the case data of the trainee's local diagnosis, and present the same presentation of the case data in the current training paradigm And presenting the local case data to be diagnosed to the trainee. Further, the training result of the trainee for the case data can also be received.

 In a specific implementation, the interface for performing the step may be the same as the interface for performing step 102 shown in FIG. 1, so that the trainee can skillfully operate and use between the two without additional learning.

 Moreover, through integration and integration with the local diagnostic system, trainees can receive medical training locally without using new equipment, new systems, and no need to change locations, that is, trainees can receive training locally at work. This makes training easier and easier for small hospitals to promote. Moreover, it is also possible to integrate the diagnosis that the trainee needs to perform in the usual work to the training method and system provided by the embodiment, that is, the trainer's usual work and the interface used in the training are the same, so that the trainee does not need to pay any The training method and training system can be used with additional efforts, and the training method and training system provided by the present invention are closer to the normal work of the trainee, thereby minimizing the strangeness and maximum improvement of the trainee when being trained. Training examples help with actual diagnostic work.

 The medical training method in the embodiment of the present invention has been described in detail above, and the medical training system in the embodiment of the present invention will be described in detail below.

 Fig. 6 shows an exemplary structural diagram of a medical training system in an embodiment of the present invention. As shown in FIG. 6, the system may include: a data acquisition module 601, a training example generation module 602, an analog diagnosis module 603, and a result discrimination module 604.

 The data acquisition module 601 is configured to obtain case data of a plurality of clinical cases and a diagnosis result corresponding to each of the plurality of clinical cases.

 The training example generation module 602 is configured to form a training example according to the obtained case data of the clinical case and the diagnosis result, wherein the case data of a clinical case and the corresponding diagnosis result constitute a training example. The specific implementation process of the data acquisition module 601 and the training example acquisition module 602 can be consistent with the specific implementation process of step 101 shown in FIG.

 The simulated diagnostic module 603 is configured to present the case data in the current training paradigm to the trainee for a simulated diagnosis, and receive the simulated diagnosis result of the presented case data of the trainee. The specific implementation process of the analog diagnostic module can be consistent with the implementation process described in steps 102 through 103 of FIG.

The result judging module 604 is configured to compare the simulated diagnosis result with the diagnosis result in the current training paradigm, and/or compare the simulated diagnosis result with the diagnosis result in the current training paradigm. The specific implementation process of the result discriminating module can be consistent with the implementation process described in steps 103 and 104 of FIG. Further, the result judging module 604 can also give the similarity scores of the two, thereby improving the interest of the training, and , enough to achieve the assessment function, and other corresponding functions. In a specific implementation, the result judging module 604 may also only give the similarity scores of the two, without comparing the two.

 In an embodiment of the present invention, the medical training system may further include a presentation paradigm determination module 607, configured to determine a current training paradigm presented to the trainee according to the training rule; wherein the training rule includes one of the following: Different training examples in the category selected by the trainee are randomly presented to the trainee; different training examples in the category selected by the manager are randomly presented to the trainee; in the category selected by the trainee Different training examples are presented to the trainee according to the difficulty level of the diagnosis result; different training examples in the category selected by the manager are presented to the trainee according to the difficulty level of the diagnosis result; the category selected by the trainee Different training examples are presented to the trainee according to the category of the case data and/or the category of the diagnosis result; different training examples in the category selected by the manager are presented to the department according to the case data and/or the category of the diagnosis result Describe the trainee. For a detailed description, refer to the foregoing method embodiments, and details are not described herein again. The presentation example determination module 607 in this embodiment may, for example, obtain a training example obtained from the training paradigm generation module 602, and send the determined current training paradigm to the simulation diagnostic module 603.

 In addition, in an embodiment of the present invention, the medical training system may further classify the difficulty levels for each training example according to the difficulty level of the diagnosis result, and divide the training examples of the same difficulty level into a group. When the training rules are determined, the training cases with low difficulty levels can be presented to the trainees for simulation diagnosis. When the trainee's similarity score for each training case reaches the set upgrade threshold, the training case of the next difficulty level will be presented. Presented to the trainee for a simulated diagnosis. Alternatively, the trainee may select a training case of each difficulty level to perform a simulation diagnosis.

 In a specific implementation, the training example generation module 602 can have various specific implementation forms. Fig. 7 shows a schematic diagram of the internal structure of one of the specific implementations. As shown in FIG. 7, the training example generation module 602 can include: a first classification sub-module 701 and a first associated sub-module 702.

 The first classification sub-module 701 is configured to classify the case data and/or the diagnosis result collected by the data acquisition module 601 according to the set condition.

 The setting conditions include, for example, one of the following or any combination thereof: data characteristics of the case data; difficulty level of the diagnosis result; case type and/or category of the department to which the diagnosis result belongs. Wherein, the data characteristic includes at least one of a gender, an age, a diseased part, and a disease type of the patient.

 How to classify specifically can be determined according to actual needs, and is not limited here.

 The first correlation sub-module 702 is used to correlate case data of a particular category of clinical cases with corresponding diagnostic results to obtain a training paradigm.

FIG. 8 is a schematic diagram showing the internal structure of the training example generation module in another specific implementation. As shown in Figure 8, The training example generation module 602 can include: a second association sub-module 801 and a second classification sub-module 802.

 The second association sub-module 801 is configured to associate the case data of the clinical case collected by the data acquisition module 601 with the corresponding diagnosis result to form a teaching case.

 The second classification sub-module 802 is used to classify the teaching cases according to the set conditions, and use a specific category of teaching cases as a training example.

 The setting conditions include, for example, one of the following or any combination thereof: data characteristics of the case data; difficulty level of the diagnosis result; case type and/or category of the department to which the diagnosis result belongs. Wherein, the data characteristic includes at least one of a gender, an age, a diseased part, and a disease type of the patient.

 How to classify specifically can be determined according to actual needs, and is not limited here.

 In a specific implementation, the data acquisition module 601 can collect case data of the clinical case processed by the high-level doctor and the corresponding diagnosis result from each data source. For example, the clinically experienced hospitals obtain case data from a number of actual clinical cases and the doctor's diagnosis of the actual clinical case, especially the diagnosis made by a high-level doctor. Or, obtain case data of a clinical case identified by the medical education department and a diagnosis result corresponding to the clinical case. Further, considering the case data from the data sources and the corresponding diagnosis results, the format may not be uniform. Therefore, for the convenience of management, the data obtaining module 601 may further process the case data and the corresponding diagnosis results from the data sources into a unified format. If the case data from each data source and the corresponding diagnosis result have the same format, no format processing is required.

 In addition, in a specific implementation, the data acquisition module 601 collects case data of a plurality of clinical cases and diagnostic results corresponding to each clinical case of the clinical cases from each data source during a network off-peak period.

 In the specific implementation, the analog diagnostic module 603 can also have various implementation forms, and FIG. 9 shows a schematic diagram of one of the specific internal internal structures. As shown in FIG. 9, the simulation diagnostic module 603 can include: a case data presentation sub-module 901, a diagnosis template providing sub-module 902, and a diagnosis result receiving sub-module 903.

 The case data presentation sub-module 901 is configured to present the case data in the current training paradigm to the trainee for simulation diagnosis.

 The diagnostic template providing sub-module 902 is used to provide the trainee with a description of the diagnostic related term and various diagnostic conditions corresponding to the category to which the training paradigm belongs.

 The diagnostic result receiving sub-module 903 is configured to receive a simulated diagnosis result of the trainee on the case data.

 In practical applications, the sub-module 902 can also be provided without a diagnostic template.

In specific implementation, each data source may include a database of high-level large hospitals (ie, clinically experienced hospitals). At this time, the data acquisition module 601 in FIG. 6 can directly obtain the case data of the clinical case processed by the high-level doctor and the corresponding diagnosis result from each data source.

 Alternatively, the medical training system of the embodiment may further be as shown by the dotted line in FIG. 6, including: a central server 605, configured to store case data of each clinical case processed by a high level doctor collected from each data source. And the corresponding diagnosis results. At this time, the data acquisition module 601 in FIG. 6 can obtain case data and corresponding diagnosis results of each clinical case processed by each high-level doctor from the center server 605.

 In addition, in order to prevent all the case data and corresponding diagnosis results from being stored in the central server 605, causing the central server to have an excessive storage capacity, the central server 605 may also store only the clinically processed high-level doctors of each data source. The case data index of the case, the data obtaining module 601 in FIG. 6 can obtain case data of each clinical case processed by each high-level doctor from the corresponding data sources according to the case data index in the center server 605 and corresponding data. diagnostic result.

 In addition, while storing the case data index, the central server 605 may also store a part of the case data of the high-level doctor-processed clinical case obtained from each data source and the corresponding diagnosis result. At this time, the data obtaining module 601 in FIG. 6 may first obtain the case data of the clinical case processed by the high level doctor and the corresponding diagnosis result from the center server 605, and the case data not included in the center server 605 may be The case data index in the central server 605 acquires case data of the clinical case processed by the high level doctor and the corresponding diagnosis result from the corresponding data sources.

 In practical applications, the data acquisition module 601 in FIG. 6 can obtain case data and corresponding diagnosis results of high-level doctor-processed clinical cases from various data sources during off-peak hours of the network (such as at night) to avoid peak hours. The data is congested.

 In the actual application, in order to provide continuous training for the trainee, the data acquisition module 601 in the system of the embodiment may have an internal structure as described in FIG. 10, that is, the data acquisition module 601 may specifically include: a unified management sub-module 1001 And collecting sub-module 1002.

 The overall management sub-module 1001 is configured to determine the case data of the clinical case that needs to be obtained and the corresponding diagnostic result, such as the case, according to the trained training case simulated by the trainee and the predetermined training sample allocation plan. The data characteristics of the data and the corresponding number of clinical cases are notified to the collection sub-module 1002 of the determined conditions, such as the data characteristics and the number of corresponding clinical cases.

 The collection sub-module 1002 obtains case data of the clinical cases processed by the high-level doctors and corresponding diagnosis results from the data sources according to the determined conditions, such as the data characteristics and the number of corresponding clinical cases.

For the case of collecting directly from each data source, the collection sub-module 1002 may be based on the determined conditions, such as According to the characteristics and the number of corresponding clinical cases, each data source is searched sequentially, and the case data satisfying the requirements and the corresponding diagnosis result are obtained from the data source. For the case of collecting directly from the central server 605, the collecting sub-module 1002 can obtain the case data and the corresponding requirements from the central server 605 according to the determined conditions, such as the data characteristics and the corresponding number of clinical cases. The diagnosis result. For the case where only the case data index exists in the central server 605, the collecting sub-module 1002 may retrieve the corresponding case data from the central server 605 according to the determined conditions, such as the data characteristics and the corresponding number of clinical cases. Indexing, and determining the data source where each corresponding case data is located, and then collecting corresponding case data and corresponding diagnosis results from the determined data source. For the case where there is only a part of the case data and the corresponding diagnosis result in the central server 605, and there is a part of the case data index, the collection sub-module 1002 may first obtain the case data satisfying the requirement and the corresponding from the central server 605. The diagnosis result, for the case data not included in the central server 605 and the corresponding diagnosis result, the corresponding case data index may be retrieved from the central server 605, and the data source of each corresponding case data is determined, and then determined from the determined The corresponding case data and its corresponding diagnosis result are obtained from the data source.

 In a specific implementation, the result judging module 604 can have various internal structure implementation forms, and FIG. 11 shows a schematic diagram of an internal structure of the result judging module 604 in a specific implementation. As shown in FIG. 11 , the result judging module 604 may specifically include: a comparison sub-module 1101 and a scoring sub-module 1202.

 The comparison sub-module 1101 is configured to compare the simulated diagnosis result with the diagnosis result in the current training paradigm to obtain a similarity comparison result.

 The score sub-module 1102 is configured to score the simulated diagnosis result based on the similarity comparison result.

 In practical applications, the medical training system of the embodiment can further provide an examination function. That is, the examination training system in this embodiment may further include: an examination data acquisition module 1201, an examination example generation module 1202, an examination diagnosis module 1203, a comparison scoring module 1204, and an examination result determination module 1205.

 The test data acquisition module 1201 is configured to obtain case data of a plurality of clinical cases identified by the medical education department and diagnosis results corresponding to each of the plurality of clinical cases. Alternatively, case data from multiple actual clinical cases and results from doctors' actual clinical cases, especially those made by high-level doctors, can be obtained from clinically experienced hospitals.

 The test sample generation module 1202 is configured to form an examination example according to the obtained case data of the clinical case and the diagnosis result, wherein the case data of a clinical case and the corresponding diagnosis result constitute an examination example.

 The test diagnosis module 1203 is configured to present the case data in the current test sample to the trainee, and receive the test diagnosis result of the trainee on the case data.

The comparison scoring module 1204 is configured to compare the test diagnosis result with the diagnosis result in the current test sample , compared, the similarity score is obtained.

 The test result determination module 1205 is configured to determine the test score of the trainee based on the scores of the trainees in each test sample in the current exam.

 In a specific implementation, the test data obtaining module 1201 may be a module shared with the training data acquiring module 601, or may be a module independent of the training sample data acquiring module 601. Correspondingly, the test sample data obtaining module 1201 can also adopt the internal structure shown in FIG. 710, and the corresponding functions are similar, just replace the word "training" with the word "exam". Of course, the internal structure shown in FIG. 710 may not be used. The test sample generation module 1202 may be a module shared with the training sample generation module 602, or may be a module generated independently of the training sample generation 602. Correspondingly, the test sample generation module 1202 can also adopt the internal structure shown in FIG. 7 and FIG. 8, and the corresponding functions are similar, just replace the word "training" with the word "exam". The internal structure shown in Figs. 7 and 8 may not be employed. For example, the test sample generation module 1202 may classify the aggregated case data and the corresponding diagnosis result according to setting conditions, such as data characteristics of the case data and/or difficulty level of the clinical case, and then classify the classified case. The data and corresponding diagnostic results are organized according to the set test rules, and an exam sample corresponding to each clinical case is generated. Among them, the case data of a clinical case and the corresponding diagnosis result constitute an examination example.

 In an actual application, the above test data obtaining module 1201, the test sample generating module 1202, the test diagnosis module 1203, the comparison scoring module 1204, and the test result determining module 1205 may also constitute a medical examination system.

 In addition, in order to implement the on-the-job training of the trainee and the work environment of the trainee, the medical training system in this embodiment may further include an on-the-job diagnosis module 606, configured to acquire the case data to be diagnosed locally by the trainee. The local case data to be diagnosed is presented to the trainee in the same presentation manner as presenting the case data in the current training paradigm. Further, the training result of the trainee for the case data can also be received. In the specific implementation, the on-the-job diagnostic module 606 can have the same user interface (UI) as the analog diagnostic module 603. In this way, the trainee can operate and use it skillfully without additional labor.

Moreover, through integration and integration with the local diagnostic system, trainees can receive medical training locally without using new equipment, new systems, and no need to change locations, that is, trainees can receive training locally at work. This makes training easier and easier for small hospitals to promote. Moreover, it is also possible to integrate the diagnosis that the trainee needs to perform in the usual work to the training method and system provided by the embodiment, that is, the trainer's usual work and the interface used in the training are the same, so that the trainee does not need to pay any The training method and training system can be used with additional efforts, and the training method and training system provided by the present invention are closer to the normal work of the trainee, thereby minimizing the strangeness and maximum improvement of the trainee when being trained. , Training examples help with actual diagnostic work.

 In the above system, in addition to the central server 605, other modules may be provided in the user terminal.

 In addition to being used for training doctors, the above medical methods and systems can also be used for communication and cooperation between hospitals to share resources. The invention discloses a medical training method and a corresponding medical training system. The medical training method includes: obtaining case data of a plurality of clinical cases and a diagnosis result corresponding to each of the plurality of clinical cases; forming a training example according to the case data of the obtained clinical case and the diagnosis result, wherein one clinical case The case data and the diagnosis result corresponding to the clinical case constitute a training paradigm; present the case data in the current training paradigm to the trainee for simulation diagnosis; receive the simulated diagnosis result of the presented case data of the trainee; The simulated diagnostic results are compared to the diagnostic results in the current training paradigm and/or the simulated diagnostic results are compared to the diagnostic results in the current training paradigm. The medical training method and system provided by the present invention can effectively improve the diagnosis level of doctors in small hospitals and give full play to the role of small hospitals.

 The above is only the preferred embodiment of the present invention, and is not intended to limit the present invention. Any modifications, equivalents, improvements, etc., which are included in the spirit and scope of the present invention, should be included in the present invention. Within the scope of protection.

Claims

WO 2013/029242 +π TM -+÷ +, PCT/CN2011/079134 Claims

1. A medical training method, including:

Obtaining case data of a plurality of clinical cases and a diagnosis result corresponding to each of the plurality of clinical cases; forming a training example according to the case data of the obtained clinical cases and the diagnosis result, wherein the case data of one clinical case and the clinical The diagnostic results corresponding to the case constitute a training paradigm;

Presenting the case data in the current training paradigm to the trainee for simulation diagnosis;

Receiving, by the trainee, a simulated diagnosis result of the presented case data;

Comparing the simulated diagnostic results with diagnostic results in the current training paradigm and/or comparing the simulated diagnostic results with diagnostic results in the current training paradigm.

 2. The method according to claim 1, wherein the comparing the simulated diagnosis result with the diagnosis result in the current training paradigm comprises:

The simulated diagnosis result is compared with the diagnosis result in the current training paradigm, and the simulated diagnosis result is scored according to the similarity comparison result.

 3. The method according to claim 1, wherein

And obtaining the case data of the plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases, including: collecting case data of the clinical case from each data source and a diagnosis result corresponding to the clinical case;

The training example is formed according to the obtained case data of the clinical case and the diagnosis result, including: classifying the case data and/or the diagnosis result of the collected clinical case according to the set condition, and the case data of the specific category of the clinical case and Corresponding diagnostic results are correlated to obtain training examples; or include: correlating the collected case data of the clinical cases and the corresponding diagnosis results to form a teaching case, and classifying the teaching cases according to the set conditions, and teaching the specific categories The case is used as a training example.

 4. The method according to claim 3, wherein the setting condition comprises one or any combination of the following: data characteristics of case data, wherein the data characteristics include a patient's gender, age, diseased part, and disease At least one of the types; the difficulty level of the diagnosis result; the case data and/or the category of the department to which the diagnosis result belongs.

 5. The method according to claim 4, wherein, before the presenting the case data in the current training paradigm to the trainee for the simulated diagnosis, the method further comprises: determining, according to the training rule, presenting to the trainee Current training examples;

Wherein, the training rule includes one of the following: WO 2013/029242 _+π TM -+÷ +, PCT/CN2011/079134

 a request for random presentation of different training examples in the category selected by the trainee to the trainee;

Randomly presenting different training examples in the category selected by the manager to the trainee;

Different training examples in the category selected by the trainee are presented to the trainee according to the difficulty level of the diagnosis result; different training examples in the category selected by the manager are presented to the training according to the difficulty level of the diagnosis result Presenting different training examples in the category selected by the trainee to the trainee according to the category of the case and/or the category of the diagnosis result;

Different training examples in the category selected by the manager are presented to the trainee according to the category of the case and/or the category of the diagnosis to which the diagnosis results belong.

 The method according to claim 3, wherein the obtaining the case data of the plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases comprises:

Determine the case data of the clinical cases that need to be obtained and the conditions that the corresponding diagnostic results should meet, based on the training examples that the trainees have used and the pre-determined distribution of training sample categories;

The case data of the clinical case and the diagnosis result corresponding to the clinical case are collected from each data source according to the determined conditions; wherein the training examples that the trainee has used include: the training examples that have been used in each category The number of pre-determined training paradigm categories includes: Pre-determined number of training paradigms in each category

The method according to claim 6, wherein the collecting the case data of the clinical case from each data source according to the determined condition and the diagnosis result corresponding to the clinical case include:

Setting a central server, configured to acquire case data of the clinical case and corresponding diagnosis result from each data source; and collect case data of the clinical case and the diagnosis result corresponding to the clinical case from the central server according to the determined condition; and Or,

Setting a central server, configured to obtain a case data index of the clinical case from each data source; retrieve a corresponding case data index from the central server according to the determined condition, and determine a data source where the case data of the required clinical case is located, Case data of the clinical case and corresponding diagnostic results are collected from the determined data sources.

The method according to claim 1, wherein the obtaining the case data of the plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases comprises:

During off-peak hours of the network, case data of multiple clinical cases and diagnostic results corresponding to each clinical case in the clinical case are collected from various data sources.

9. The method according to claim 1, wherein the obtaining case data of the plurality of clinical cases and the plurality of clinical diseases WO 2013/029242 _+π TM -+÷ +, PCT/CN2011/079134

 Claims

 The diagnosis results corresponding to each clinical case in the example include: collecting case data of multiple clinical cases from each data source and corresponding diagnosis results of each clinical case in the clinical cases, and collecting case data from each data source And the corresponding diagnosis results are processed into a unified format.

 10. The method according to claim 1, wherein the method further comprises:

The case data to be diagnosed locally by the trainee is obtained, and the local case data to be diagnosed is presented to the trainee in the same presentation manner as presenting the case data in the current training paradigm.

 The method according to any one of claims 1 to 10, wherein the obtaining the case data of the plurality of clinical cases and the diagnosis result corresponding to each of the plurality of clinical cases comprises:

Obtaining case data from a number of actual clinical cases from a clinically experienced hospital and the diagnosis made by the doctor on the actual clinical case, especially the diagnosis made by a high-level doctor; or

Obtain case data of clinical cases identified by the medical education department and the diagnosis results corresponding to the clinical cases.

 The method according to any one of claims 1 to 10, wherein the case data comprises one or any combination of the following: a gender, an age, a diseased part, a disease type, a symptom description, and image data of the patient ;

The image data includes a computed tomography system CT, a nuclear magnetic resonance imaging system MRI, a computer X-ray imaging system CR, a digital X-ray imaging system DR, a digital subtraction angiography device DSA, or a single-photon computed tomography scan. At least one of the instruments ECT.

 13. A medical training system, including:

a data acquisition module, configured to acquire case data of a plurality of clinical cases and a diagnosis result corresponding to each of the plurality of clinical cases;

a training example generation module, configured to form a training paradigm according to the obtained case data of the clinical case and the diagnosis result, wherein the case data of one clinical case and the diagnosis result corresponding to the clinical case constitute a training example;

a simulation diagnosis module, configured to present case data in the current training paradigm to the trainee for simulation diagnosis, and receive a simulated diagnosis result of the presented case data of the trainee;

The result judging module is configured to compare the simulated diagnosis result with the diagnosis result in the current training paradigm, and/or compare the simulated diagnosis result with the diagnosis result in the current training paradigm.

 14. The system according to claim 13, wherein the result discrimination module comprises:

a comparison submodule, configured to compare the simulated diagnosis result with the diagnosis result in the current training paradigm to obtain a similarity comparison result;

a score sub-module, configured to score the simulated diagnosis result according to the similarity comparison result. WO 2013/029242 _+π TM -+÷ +, PCT/CN2011/079134

 Claims

The system according to claim 13, wherein the data acquisition module collects case data of a clinical case and a diagnosis result corresponding to the clinical case from each data source;

The training sample generation module includes:

a first classification sub-module, configured to classify case data and/or diagnosis results collected by the data acquisition module according to setting conditions;

a first correlation sub-module, configured to correlate case data of a specific category of clinical cases and corresponding diagnosis results to obtain a training paradigm;

Alternatively, the training example generation module includes:

a second correlation sub-module, configured to associate case data of clinical cases collected by the data acquisition module with corresponding diagnosis results to form a teaching case;

The second classification sub-module is configured to classify the teaching cases according to the set conditions, and use a specific category of teaching cases as a training example.

 The system according to claim 15, wherein the first classification sub-module classifies case data and/or diagnosis results collected by the data acquisition module according to setting conditions of one or any combination of the following :

Data characteristics of case data, wherein the data characteristics include at least one of a patient's gender, age, diseased site, and disease type; ease of diagnosis;

Case data and/or department category to which the diagnosis results belong;

Or the second classification sub-module classifies the teaching case according to a setting condition of one or any combination of the following; data characteristics of the case data, wherein the data characteristics include a gender, age, and illness of the patient At least one of a site and a type of disease; the ease of diagnosis;

Case data and/or department category to which the diagnosis results belong.

17. The system of claim 16, wherein the system further comprises: a presentation paradigm determination module for determining a current training paradigm presented to the trainee in accordance with a training rule;

Wherein, the training rule includes one of the following:

Randomly presenting different training examples in the category selected by the trainee to the trainee;

Randomly presenting different training examples in the category selected by the manager to the trainee;

Different training examples in the category selected by the trainee are presented to the trainee according to the difficulty level of the diagnosis result; WO 2013/029242 _+π TM -+÷ +, PCT/CN2011/079134

 The claims present different training paradigms in the categories selected by the manager to the trainee according to the ease of diagnosis; the different training paradigms in the categories selected by the trainee are based on case data and/or diagnostic results The department category is presented to the trainee;

Different training examples in the category selected by the manager are presented to the trainee according to the category of the case and/or the category of the diagnosis to which the diagnosis results belong.

 The system of claim 15, wherein the data acquisition module comprises:

The overall management sub-module is used to determine the case data of the clinical cases to be acquired and the corresponding diagnostic results according to the training examples that the trainees have used and the pre-determined distribution of the training examples; Case data for collecting clinical cases from respective data sources according to the determined conditions and diagnostic results corresponding to the clinical cases;

Wherein, the training examples that the trainee has used include: the number of training examples that have been used in each category; the predetermined training example category distribution includes: a predetermined training in each category The number of examples.

19. The system of claim 18, wherein the system further comprises:

a central server, configured to obtain case data of clinical cases and corresponding diagnosis results from each data source; and/or obtain case data index of clinical cases from each data source;

The collecting sub-module collects case data of the clinical case and the diagnosis result corresponding to the clinical case from the central server according to the determined condition; and/or, according to the determined condition, retrieves the corresponding case from the central server The data is extracted and the data source of the case data of the required clinical case is determined, and the case data of the clinical case and the corresponding diagnosis result are collected from the determined data source.

20. The system according to claim 13, wherein the data acquisition module collects case data of a plurality of clinical cases from each data source during a network off-peak period and a diagnosis corresponding to each clinical case of the clinical cases result.

The system according to claim 13, wherein the data acquisition module collects case data of a plurality of clinical cases from each data source and diagnosis results corresponding to each clinical case in the clinical cases, and The case data of the data source and the corresponding diagnosis result are processed into a unified format.

22. The system of claim 13, wherein the system further comprises:

The on-the-job diagnosis module is configured to obtain case data to be diagnosed locally by the trainee, and present the local case data to be diagnosed to the trainee in the same presentation manner as presenting the case data in the current training paradigm.

The system according to any one of claims 13 to 22, wherein the data acquisition module acquires case data of a plurality of actual clinical cases from a clinically experienced hospital and a doctor makes the actual clinical case The diagnosis result, especially the diagnosis result made by a high-level doctor; or, the case data of the clinical case identified by the medical education department and the diagnosis result corresponding to the clinical case. WO 2013/029242 _+π TM -+÷ +, PCT/CN2011/079134

 Claims

 The system according to any one of claims 13 to 22, wherein the data acquisition module acquires case data of a plurality of clinical cases including one or any combination of the following and each of the plurality of clinical cases Diagnostic results corresponding to clinical cases;

Patient's gender, age, location, type of disease, symptom description and image data;

The image data includes a computed tomography system CT, a nuclear magnetic resonance imaging system MRI, a computer X-ray imaging system CR, a digital X-ray imaging system DR, a digital subtraction angiography device DSA, or a single-photon computed tomography scan. At least one of the instruments ECT.