Medical assistance method, device, equipment and medium

Abstract

The invention discloses a medical assistance method and device, equipment and a medium, and relates to the technical field of medical diagnosis, and the method comprises the steps: obtaining a mode selection instruction to control medical equipment to enter a corresponding working mode; if the mode is the first mode, verifying the intelligent algorithm based on the difference between the intelligent reasoning result and the user operation result; if the mode is the second mode, evaluating the user operation behavior based on the difference between the user operation result and the intelligent reasoning result; the user operation result and the intelligent reasoning result are respectively an operation result of the user on the first medical data and a reasoning result of the intelligent algorithm on the first medical data. According to the method, quantitative evaluation of the intelligent algorithm performance in a clinical scene can be realized, the influence caused by human factors is avoided, the safety problem caused by data export is avoided, and performance index testing is realized in an actual clinical scene. The invention further provides a quantitative skill assessment means and a clinical skill practice prompt platform, so that related personnel can be helped to quickly improve operation skills.

Description

Technical Field

[0001] The present invention relates to the field of medical diagnosis technology, and particularly relates to a medical assistance method, device, equipment and medium. Background Art

[0002] With the rapid development of artificial intelligence technology, more and more intelligent algorithms are applied to the medical field. During the process of artificial intelligence development, registration and application, it is often necessary to conduct performance tests on the performance of intelligent algorithms.

[0003] Existing verification methods can generally be divided into two categories: qualitative evaluation and quantitative evaluation. The former is based on subjective judgment, has strong subjectivity and lacks data support; the latter is evaluated by quantitative methods, which is objective and fair and can be statistically analyzed from multiple angles.

[0004] The solution for qualitative evaluation is as follows: Doctors use intelligent algorithms for reasoning to automatically complete disease screening or diagnosis and measurement work. Further, doctors evaluate the reasoning results of the intelligent algorithms to determine whether the reasoning is correct. Of course, it is also possible to record the intelligent reasoning results of some measurement or classification items and the manual operation results of senior doctors or the errors between the two, and then conduct statistical analysis. Since the doctor's evaluation is carried out on the premise that the intelligent algorithm has already given the results, it does not meet the double-blind verification principle and is mainly based on qualitative determination, with strong subjectivity. Although to a certain extent, quantitative evaluation of some items can also be done, it is powerless for quantitative evaluation such as contour fitting degree, measurement line angle deviation, measurement position deviation, etc. Moreover, it is inevitable that there will be omissions during the manual recording process.

[0005] Another solution for quantitative evaluation is as follows: Doctors perform image acquisition, select standard sections, and export the data. Then, under double-blind conditions, senior doctors read and annotate the collected data respectively, and the intelligent algorithm conducts reasoning and generates annotations. Finally, statistical comparison and analysis are carried out on the annotation results of the two to obtain the quantitative evaluation results. Although this solution can also complete quantitative evaluation, there are still many problems, such as:

[0006] 1. When doctors annotate, they are separated from the clinical scenario and cannot strictly restore the real clinical operation situation. In fact, factors such as lighting, display equipment, and the scenario during film reading can affect doctors' physiology and psychology, thereby affecting the verification results;

[0007] 2. Even if through a series of means, the results obtained by doctors and intelligence on the ultrasound machine can be converted into a format that can be compared and analyzed and exported for analysis, the process will be relatively cumbersome and data security issues will also be faced.

[0008] 3. Most of the above methods or links need to be completed manually and are more easily affected by human factors.

[0009] In addition, the traditional training mode for medical device operators often adopts the method of "the old leading the new" and self-exploration, which is inefficient and it is difficult for teachers to take care of each student and quantitatively evaluate the skill level.

[0010] Therefore, the above problems urgently need to be solved by those skilled in the art. Summary of the Invention

[0011] In view of this, the purpose of the present invention is to provide a medical assistance method, device, equipment and medium, which can realize the quantitative evaluation of intelligent algorithms in clinical scenarios, avoid the influence brought by human factors, and avoid the security problems brought by data export. The present invention can also provide a quantitative skill evaluation means and a clinical skill practice prompt platform to help relevant personnel quickly improve their operation skills. The specific solutions are as follows:

[0012] In the first aspect, the present application discloses a medical assistance method, including:

[0013] Obtain a mode selection instruction to control the medical device to enter the corresponding working mode;

[0014] If the working mode is the first mode, verify the accuracy of the current intelligent algorithm based on the difference between the current intelligent reasoning result and the current user operation result;

[0015] If the working mode is the second mode, evaluate the operation behavior of the current user based on the difference between the current user operation result and the current intelligent reasoning result;

[0016] Wherein, the current user operation result and the current intelligent reasoning result are respectively the operation result of the current user on the first medical data and the reasoning result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user through controlling the medical device to collect data.

[0017] Optionally, the medical assistance method further includes:

[0018] Configure the first user as the current user in the first mode to generate the current user operation result;

[0019] Configure the second user as the current user in the second mode to generate the current user operation result;

[0020] Wherein, the qualification authority of the first user is higher than that of the second user.

[0021] Optionally, the medical assistance method further includes:

[0022] If the working mode is the third mode, only trigger the intelligent reasoning process to infer the second medical data using the current intelligent algorithm to obtain the corresponding current intelligent reasoning result.

[0023] Optionally, the medical assistance method further includes:

[0024] If the working mode is the fourth mode, evaluate the current user's operation behavior using the difference between the current user operation result and the preset reference result;

[0025] Wherein, the current user operation result is the operation result of the current user on the third medical data selected from the system question bank, and the preset reference result is the result corresponding to the third medical data saved in the system question bank.

[0026] Optionally, after evaluating the current user's operation behavior using the difference between the current user operation result and the preset reference result, it further includes:

[0027] If the current evaluation result corresponding to any third medical data meets the first preset condition, create a new system question bank based on the any third medical data, and configure the corresponding selection probability for the any third medical data based on the historical statistical times that meet the first preset condition;

[0028] Establish a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time.

[0029] Optionally, after evaluating the current user's operation behavior using the difference between the current user operation result and the current intelligent reasoning result, it further includes:

[0030] If the current evaluation result corresponding to any first medical data meets the second preset condition, generate the corresponding operation optimization suggestion and send it to the current human-computer interaction interface for real-time display;

[0031] Create a new system question bank based on the any first medical data, and configure the corresponding selection probability for the any first medical data based on the historical statistical times that meet the second preset condition;

[0032] Establish a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time.

[0033] Optionally, the medical assistance method further includes:

[0034] Record the user operation results and / or intelligent inference results generated in any working mode in the form of logs to obtain corresponding log data, so as to process the log data generated within a preset time period by using a preset processing method;

[0035] Among them, the preset processing method includes any one or a combination of more of the analysis of target statistical parameters, the analysis of the accuracy of intelligent algorithms, the statistical analysis of operator behavior, the analysis of operator proficiency, the analysis of the error rate of operation items, the analysis of the time consumed by operation items, and chart creation.

[0036] In a second aspect, the present application discloses a medical assistance system, including:

[0037] A mode determination module, configured to obtain a mode selection instruction to control a medical device to enter a corresponding working mode;

[0038] A model verification module, configured to, if the working mode is the first mode, verify the accuracy of the current intelligent algorithm based on the difference between the current intelligent inference result and the current user operation result;

[0039] A behavior evaluation module, configured to, if the working mode is the second mode, evaluate the operation behavior of the current user based on the difference between the current user operation result and the current intelligent inference result;

[0040] Among them, the current user operation result and the current intelligent inference result are respectively the operation result of the current user on the first medical data and the inference result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user after controlling the medical device to perform data collection.

[0041] In a third aspect, the present application discloses an electronic device, including:

[0042] A memory, configured to store a computer program;

[0043] A processor, configured to execute the computer program to implement the medical assistance method disclosed above.

[0044] In a fourth aspect, the present application discloses a computer-readable storage medium, configured to store a computer program; wherein, when the computer program is executed by a processor, the medical assistance method disclosed above is implemented.

[0045] It can be seen that the present application proposes a medical assistance method, which obtains a mode selection instruction to control a medical device to enter a corresponding working mode; if the working mode is the first mode, the accuracy of the current intelligent algorithm is verified based on the difference between the current intelligent reasoning result and the current user operation result; if the working mode is the second mode, the operation behavior of the current user is evaluated based on the difference between the current user operation result and the current intelligent reasoning result; wherein, the current user operation result and the current intelligent reasoning result are respectively the operation result of the current user on the first medical data and the reasoning result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user through controlling the medical device to collect data.

[0046] The beneficial effects of the present application are as follows: First, the present application uses an intelligent algorithm to reason about the first medical data and verifies the intelligent algorithm in combination with the operation result of the user on the first medical data. Since the medical data used in the above verification process is all the first medical data, and since the first medical data is the medical data obtained by the current user through controlling the medical device to collect data, the present application realizes the quantitative evaluation of the intelligent algorithm in the clinical scenario. In this way, first, compared with the prior art that is detached from the clinical scenario in quantitative evaluation, the present application can obtain a more accurate verification result based on the annotation of the clinical scenario, and the present application can meet the principle of unified variables; second, since the present application can realize the comparative analysis of the doctor's operation result and the intelligent algorithm reasoning result based on the system without additional data export, the present application can avoid the data security problem caused by data export and can also avoid the influence of human factors in the data export process; third, in the present application, the verification of the intelligent algorithm by relevant personnel is not only based on the reasoning result of the intelligent algorithm, but also needs to be realized in combination with the operation result of the user. Therefore, compared with the prior art, the present application meets the principles of double-blind verification and quantitative analysis; fourth, the present application realizes the quantitative evaluation of the user's operation skills based on the reasoning result of the intelligent algorithm and provides skill tips for relevant users according to the evaluation result. That is, the present application provides a quantitative skill evaluation means and a clinical skill practice prompt platform to realize the auxiliary practice and scientific cultivation of relevant personnel and help relevant personnel quickly improve their operation skills. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0048] Figure 1A flowchart of a medical assistance method disclosed in this application;

[0049] Figure 2 A specific flowchart of a medical assistance method disclosed in this application;

[0050] Figure 3 Another specific flowchart of a medical assistance method disclosed in this application;

[0051] Figure 4 Another specific flowchart of a medical assistance method disclosed in this application;

[0052] Figure 5 A schematic structural diagram of a medical assistance device disclosed in this application;

[0053] Figure 6 A structural diagram of an electronic device disclosed in this application. Detailed implementation manners

[0054] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0055] First, the existing clinical verification scheme processes are relatively complex, and in the verification process, in addition to the operating doctor, a data recorder is also required to record and count data, and it is impossible to ensure that there are no errors in the manual recording process. Second, in the implementation process of the existing clinical verification scheme, it is extremely vulnerable to human factors, and it is very difficult to obtain effective compliance support documents, which brings great difficulties to the verification and supervision of the regulatory authorities. Third, the traditional training mode of medical device operators often uses the method of "experienced employees guiding new employees" and self-exploration, which is inefficient and it is difficult for the teacher to take care of each student and quantitatively evaluate the skill level.

[0056] Therefore, the embodiments of this application propose a medical assistance scheme, which can realize the quantitative evaluation of intelligent algorithms in clinical scenarios, avoid the influence brought by human factors, avoid the security problems brought by data export, and at the same time avoid the problem of deviation from the actual use state caused by reasoning in the offline state. The present invention can also provide a quantitative skill evaluation means and a clinical skill practice prompt platform to help relevant personnel quickly improve their operation skills.

[0057] The embodiments of this application disclose a medical assistance method. Refer to Figure 1 As shown, the method includes:

[0058] Step S11: Obtain a mode selection instruction to control the medical device to enter the corresponding working mode.

[0059] In this embodiment, the medical device can be an ultrasonic device or other medical devices, such as an endoscopic ultrasound, an endoscope, a CT (Computed Tomography), etc.; the medical device can be built with intelligent algorithms to achieve intelligent inference of medical images. For example, for an ultrasonic medical device, intelligent algorithms can be used to achieve intelligent inference of standard sections, and automatic measurement of measurement items can be realized accordingly; this embodiment is applied to a medical assistance system, which can be built into the medical device or an independent external intelligent product, and no specific limitation is made here.

[0060] In this embodiment, some working modes of the medical device can be developed as hidden modes. That is, before entering the above-mentioned working mode, it is necessary to select the working mode to be enabled in the system configuration file (config). For the medical assistance system, it is to obtain a mode selection instruction to enter the corresponding working mode. If no hidden mode is selected to be enabled, the default working mode is directly entered.

[0061] Step S12: If the working mode is the first mode, verify the accuracy of the current intelligent algorithm based on the difference between the current intelligent inference result and the current user operation result.

[0062] In this embodiment, the first mode can be understood as an intelligent algorithm verification mode. The current intelligent inference result is the inference result obtained by the intelligent algorithm reasoning on the first medical data, and the current user operation result is the operation result generated by the first user operating on the first medical data. The first user can be a doctor who can proficiently master the operation skills, etc. The first medical data is the medical data obtained by the current user after controlling the medical device to collect data, and can be understood as the medical data collected in the current user's clinical scenario. Further, the intelligent algorithm includes but is not limited to an intelligent model algorithm, such as a neural network model algorithm, etc.

[0063] In this way, in this embodiment, the accuracy of the current intelligent algorithm is verified through the difference between the current intelligent inference result and the user operation result. Since the user operation result is generated by a user such as a doctor who can proficiently master the operation skills, this embodiment can improve the accuracy of the intelligent inference result by comparing the inference result of the intelligent model algorithm with the user operation result.

[0064] Step S13: If the working mode is the second mode, evaluate the operation behavior of the current user based on the difference between the current user operation result and the current intelligent inference result; wherein, the current user operation result and the current intelligent inference result are respectively the operation result of the current user on the first medical data and the inference result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user through controlling the medical device for data collection.

[0065] In this embodiment, the second mode can be understood as a skill training mode. In this mode, the current intelligent inference result is the inference result obtained by the intelligent algorithm for inferring the first medical data, and the current user operation result is the operation result generated by the second user for operating the first medical data. The second user can be a training trainee who needs to improve the operation skill, etc. It can be understood that the qualification authority of the first user is higher than that of the second user.

[0066] In this way, this embodiment evaluates the operation behavior of the current user through the difference between the operation result of the user who needs to improve the operation skill and the current intelligent inference result, which is beneficial to helping the user quickly improve the operation skill. It can be seen that this embodiment no longer adopts the way of "experienced person leading the novice" and self-exploration, but evaluates the operation behavior of the current user through the difference between the current user operation result and the current intelligent inference result. Compared with the existing solution, the efficiency and effect of this embodiment have both been improved.

[0067] Further, if the working mode is the third mode, only trigger the intelligent inference process to use the current intelligent algorithm to infer the second medical data to obtain the corresponding current intelligent inference result, wherein the second medical data may be the historically collected data or the data automatically collected by the machine. In summary, the first mode in this embodiment is the default working mode, that is, if no hidden mode is selected to be enabled, directly enter the third mode to only trigger the intelligent inference process.

[0068] Further, if the working mode is the fourth mode, evaluate the operation behavior of the current user based on the difference between the current user operation result and the preset reference result; wherein, the current user operation result is the operation result of the current user on the third medical data selected from the system question bank, and the preset reference result is the result corresponding to the third medical data saved in the system question bank. It can be understood that the third medical data is the data in the system question bank.

[0069] That is to say, in this embodiment, not only can the operation behavior of the current user be evaluated based on the current intelligent reasoning result to improve the user's operation skills, but also the operation behavior of the current user can be evaluated based on a preset reference result to improve the user's operation skills. In this evaluation method, the preset reference result is pre-stored in the system question bank. In addition, third medical data is also stored in the system question bank, and the current user operates on the third medical data to obtain an operation result.

[0070] In addition, this embodiment can record the user operation result and / or intelligent reasoning result generated in any working mode in the form of a log to obtain corresponding log data, so as to process the log data generated within a preset time period by using a preset processing method; wherein, the preset processing method includes any one or a combination of more of analyzing target statistical parameters, analyzing the accuracy of intelligent algorithms, statistically analyzing the behavior of operators, analyzing the proficiency of operators, analyzing the error rate of operation items, analyzing the time consumed by operation items, and creating charts. The target statistical parameters include but are not limited to the mean error, standard deviation, etc. In this way, the log data recorded in each working mode can be used as a real-time record of the current clinical verification, thereby providing data support for the compliance, objectivity, etc. of the clinical verification and providing precious traceable materials for the clinical verification.

[0071] It can be seen that this application proposes a medical assistance method, which obtains a mode selection instruction to control a medical device to enter a corresponding working mode; if the working mode is the first mode, the accuracy of the current intelligent algorithm is verified based on the difference between the current intelligent reasoning result and the current user operation result; if the working mode is the second mode, the operation behavior of the current user is evaluated based on the difference between the current user operation result and the current intelligent reasoning result; wherein, the current user operation result and the current intelligent reasoning result are respectively the operation result of the current user on the first medical data and the reasoning result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained after the current user controls the medical device to collect data.

[0072] The beneficial effects of the present application are as follows: First, the present application uses an intelligent algorithm to infer the first medical data, and verifies the intelligent algorithm in combination with the user's operation results on the first medical data. Since the medical data used in the above verification process are all first medical data, and since the first medical data is the medical data obtained by the current user after controlling the medical device to collect data, the present application realizes the quantitative evaluation of the intelligent algorithm in the clinical scenario. In this way, first, compared with the prior art that is separated from the clinical scenario during quantitative evaluation, the present application can obtain more accurate verification results based on the annotation of the clinical scenario, avoiding the problem of deviation from the actual usage status caused by reasoning in an offline state or out of the actual clinical scenario, and the present application can meet the variable unification principle; second, the doctor's operation results and the intelligent algorithm reasoning results of the present application will not be separated from the medical assistance system, so the present application better restores the machine reasoning effect. In addition, since the present application does not require additional data export but is based on The system can realize comparative analysis between the doctor's operation results and the reasoning results of the intelligent algorithm. Therefore, this application can avoid the data security issues caused by data export, and can also avoid the influence of human factors brought about by the data export process; third, the verification of the intelligent algorithm by relevant personnel in this application is not only based on the reasoning results of the intelligent algorithm, but must be combined with the user's operation results. Therefore, compared with the existing technology, this application meets the double-blind verification and quantitative analysis principles; fourth, this application realizes quantitative evaluation of user operation skills based on the reasoning results of the intelligent algorithm, and provides skill prompts to relevant users based on the evaluation results, that is, this application provides a quantitative skill evaluation method and a clinical skill practice prompt platform to realize auxiliary practice and scientific training for relevant personnel, so as to help relevant personnel quickly improve their operation skills.

[0073] The embodiment of the present application discloses a specific medical assistance method. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution. Figure 2 As shown, specifically including:

[0074] Step S21: If the current evaluation result corresponding to any third medical data meets the first preset condition, a new system question bank is created based on the any third medical data, and a corresponding selection probability is configured for the any third medical data based on the historical statistical number of times the first preset condition is met.

[0075] In this embodiment, the third medical data can be data collected by the device controlled by the current user, historical collected data, or data automatically collected by the machine. Further, the first preset condition can be that the current evaluation result is lower than a certain preset score. It can be understood that if the current evaluation result is lower than a certain preset score, it means that the operation level has not reached an excellent level. For example, if the total score is 100 points and the current evaluation result is less than 80 points, a new system question bank needs to be created based on the third medical data of operation errors, and the probability of selecting such data should be increased according to the actual situation.

[0076] Step S22: Establish a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time.

[0077] It can be understood that after generating the new system question bank in this embodiment, a binding relationship can be established between the new system question bank and the current user, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time. Since the new system question bank is created based on the wrong questions of the user, this embodiment can continuously strengthen the weak skills of the user to achieve targeted training for the user.

[0078] That is to say, if the user's purpose is to improve skills, the skill improvement function can be enabled. After enabling, the system will re-add the data of operation errors to the system question bank and significantly increase the selection probability of such data, so that the user can improve the operation skills during the continuous strengthening process.

[0079] The embodiment of the present application discloses a specific medical assistance method. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution. See Figure 3 as shown, specifically including:

[0080] Step S31: If the current evaluation result corresponding to any first medical data meets the second preset condition, generate corresponding operation optimization suggestions and send them to the current human-computer interaction interface for real-time display.

[0081] In this embodiment, the second preset condition can be that the current evaluation result is lower than a certain preset score. It can be understood that if the current evaluation result is lower than a certain preset score, it means that the operation level has not reached an excellent level. Further, the system can generate corresponding operation optimization suggestions and send the suggestions to the current human-computer interaction interface for real-time display.

[0082] Step S32: Create a new system question bank based on the any first medical data, and configure the corresponding selection probability for the any first medical data based on the historical statistical times that meet the second preset condition.

[0083] It can be understood that in this embodiment, a new system question bank can be created based on the first medical data of operation errors, and the probability of such data being selected can be increased according to the actual situation for the user to practice repeatedly.

[0084] Step S33: Establish a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time.

[0085] After generating the new system question bank in this embodiment, a binding relationship between the new system question bank and the current user can be established, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time. Since the new system question bank is created based on the user's wrong question situation, during the user's practice process in this embodiment, certain clinical guidance can be given to the user in a timely manner to help the user correct mistakes in real time.

[0086] Taking the medical device as an ultrasonic device as an example, the medical assistance method described in this application will be specifically described. See Figure 4 as shown:

[0087] Taking the diagnosis of the breast as an example, when the intelligent verification mode (i.e., the first working mode) is enabled in the system setting file, the system will automatically enter the intelligent verification mode.

[0088] (1) Intelligent verification mode

[0089] In the intelligent verification mode, it first automatically enters the manual operation mode. A senior doctor uses the ultrasound machine to scan the patient's breast. If a nodule is found, manually obtain the standard section for breast nodule diagnosis, and complete the measurement, phase marking, BI-Rads (Breast Imaging Reporting and Data System) grading, margin, echo, posterior characteristics, presence or absence of calcification and other feature selections under freezing to obtain the operation results. Further, if the manual operation is completed, click a certain button (this button can be named the completion button, save button, etc.). At this time, the intelligent algorithm performs intelligent (Artificial Intelligence, AI) reasoning on the section data of the doctor's manual operation to obtain the reasoning result. After the intelligent reasoning is completed, the system will automatically compare the doctor's manual operation results with the AI automatic reasoning results, and calculate information such as measurement error and feature compliance. Then the system will save the result images of the manual and automatic reasoning in a double-image form. At this time, the above measurement, analysis results and verification comparison results will also be printed at the appropriate positions of the double-image. The above manual and AI automatic reasoning results, as well as the operation records, will be saved in the form of a log for subsequent callback analysis. Further, when a batch of verifications is completed, the verification records of the entire verification stage can be statistically analyzed by calling back the log, and finally parameters such as the mean value and standard deviation of the measurement errors of the long and short diameters of breast nodules, and the accuracy rate of the intelligent algorithm for each feature category are obtained, and the corresponding charts are drawn. It should be noted that all the operation record logs in the entire verification process will be used as the real-time record of this clinical verification, providing data support for the compliance and objectivity of the clinical verification, and providing precious clinically traceable materials.

[0090] (2) Intelligent working mode

[0091] If no working mode is enabled in the system settings file, the system will enter the intelligent working mode (i.e., the third working mode). In this mode, only the intelligent algorithm is used to automatically measure / identify / diagnose medical data.

[0092] (3) Skill assessment mode

[0093] After enabling the skill assessment mode in the system settings file, the system will automatically enter the skill assessment mode. The skill assessment mode includes the clinical actual measurement / skill training mode (i.e., the second mode) and the question bank assessment / skill training mode (i.e., the fourth mode).

[0094] 1) Question bank assessment / skill training mode

[0095] In this mode, a skill assessment question bank is established. For a certain operation skill, a certain number of data can be randomly selected for the test takers to operate. After each piece of data operation is completed, the system will automatically compare the operation results of the test takers with the system's standard answers, and then give quantitative evaluation indicators. If the purpose of the test taker is to improve skills, the skill improvement function can also be enabled. After enabling, the system will re-add the data with operation errors to the database to be tested, and focus on increasing the selection probability of such data, so that students can continuously improve their operation skills in the continuous strengthening process.

[0096] 2) Clinical actual measurement / skill training mode.

[0097] In this mode, first, the student uses the ultrasonic equipment to perform real-time imaging and carry out measurement or diagnosis operations. At the same time, the system will also perform the same operations using intelligent algorithms. Then, the system will compare the reasoning results of the student and the intelligent algorithm and give quantitative evaluation indicators. At the same time, the system can also be set to a skill improvement model. During the student's practice, the system will give the student certain clinical guidance in a timely manner and correct the student's mistakes in real time. For the data with operation errors or error-prone data of the student, the student can choose to add them to the system question bank for review and repeated practice.

[0098] In addition, in addition to the above real-time indicators, the system can also provide comprehensive evaluation indicators for each student, each case, and each project for reference by teaching staff / students, so as to formulate targeted improvement plans.

[0099] In summary, on the one hand, the present application can automatically, safely, and efficiently complete the clinical verification of intelligent algorithms on the machine, so as to achieve the characteristics of double-blind verification, closed-loop efficiency, data security, traceability, and complete and clear process records. And the entire verification process of the present application only requires one operator, without the need for additional recorders to record or data export, reducing the influence of human factors in the clinical verification process. On the other hand, the present application provides a standard example for the clinical verification of ultrasonic intelligent algorithms, and is expected to promote the standardization, automation, and intelligent level of the clinical verification of ultrasonic intelligent algorithms. On the third hand, all operations in the clinical verification process of the present application are recorded and traceable, which can provide a support basis for the compliance and standardization of clinical verification, and provide effective convenience for the registration supervision of such medical devices by relevant regulatory departments. On the fourth hand, by comparing the operation results of the operator and the results of the artificial intelligence algorithm, the present application quantitatively evaluates the accuracy of the operator's section acquisition, measurement, and diagnosis, and gives appropriate clinical instructions, so as to guide the operator to improve in the correct direction and complete the evaluation of the operator's comprehensive skills, which helps teaching teachers or students to clarify teaching or skill shortcomings, so as to formulate targeted skill training or improvement plans.

[0100] Correspondingly, the embodiment of the present application also discloses a medical assistance system, see Figure 5 As shown, the device includes:

[0101] A mode determination module 11, configured to obtain a mode selection instruction to control a medical device to enter a corresponding working mode;

[0102] A model verification module 12, configured to, if the working mode is the first mode, verify the accuracy of the current intelligent algorithm based on the difference between the current intelligent reasoning result and the current user operation result;

[0103] A behavior evaluation module 13, configured to, if the working mode is the second mode, evaluate the operation behavior of the current user based on the difference between the current user operation result and the current intelligent reasoning result; wherein, the current user operation result and the current intelligent reasoning result are respectively the operation result of the current user on the first medical data and the reasoning result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user after controlling the medical device to perform data collection.

[0104] Wherein, for the more specific working processes of the above-mentioned respective modules, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details will not be elaborated herein.

[0105] It can be seen that the present application proposes a medical assistance method, which obtains a mode selection instruction to control a medical device to enter a corresponding working mode; if the working mode is the first mode, it verifies the accuracy of the current intelligent algorithm based on the difference between the current intelligent reasoning result and the current user operation result; if the working mode is the second mode, it evaluates the operation behavior of the current user based on the difference between the current user operation result and the current intelligent reasoning result; wherein, the current user operation result and the current intelligent reasoning result are respectively the operation result of the current user on the first medical data and the reasoning result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user after controlling the medical device to perform data collection.

[0106] The beneficial effects of the present application are as follows: First, the present application uses an intelligent algorithm to infer the first medical data, and verifies the intelligent algorithm in combination with the user's operation results on the first medical data. Since the medical data used in the above verification process are all first medical data, and since the first medical data is the medical data obtained by the current user after controlling the medical device to collect data, the present application realizes the quantitative evaluation of the intelligent algorithm in the clinical scenario. In this way, first, compared with the prior art that is separated from the clinical scenario during quantitative evaluation, the present application can obtain more accurate verification results based on the annotation of the clinical scenario, avoiding the problem of deviation from the actual usage status caused by reasoning in an offline state or out of the actual clinical scenario, and the present application can meet the variable unification principle; second, the doctor's operation results and the intelligent algorithm reasoning results of the present application will not be separated from the medical assistance system, so the present application better restores the machine reasoning effect. In addition, since the present application does not require additional data export but is based on The system can realize comparative analysis between the doctor's operation results and the reasoning results of the intelligent algorithm. Therefore, this application can avoid the data security issues caused by data export, and can also avoid the influence of human factors brought about by the data export process; third, the verification of the intelligent algorithm by relevant personnel in this application is not only based on the reasoning results of the intelligent algorithm, but must be combined with the user's operation results. Therefore, compared with the existing technology, this application meets the double-blind verification and quantitative analysis principles; fourth, this application realizes quantitative evaluation of user operation skills based on the reasoning results of the intelligent algorithm, and provides skill prompts to relevant users based on the evaluation results, that is, this application provides a quantitative skill evaluation method and a clinical skill practice prompt platform to realize auxiliary practice and scientific training for relevant personnel, so as to help relevant personnel quickly improve their operation skills.

[0107] In some specific embodiments, the medical assistance system further includes:

[0108] A first user operation result generating unit, configured to configure the first user as a current user in the first mode to generate a current user operation result;

[0109] A second user operation result generating unit, configured to configure the second user as the current user in the second mode to generate a current user operation result;

[0110] The qualification authority of the first user is higher than the qualification authority of the second user.

[0111] In some specific embodiments, the medical assistance system further includes:

[0112] The intelligent reasoning unit is used to trigger only the intelligent reasoning process if the working mode is the third mode, so as to use the current intelligent algorithm to reason the second medical data and obtain the corresponding current intelligent reasoning result.

[0113] In some specific embodiments, the medical assistance system further includes:

[0114] A user operation behavior evaluation unit, configured to, if the working mode is the fourth mode, evaluate the operation behavior of the current user by using the difference between the current user operation result and a preset reference result;

[0115] Wherein, the current user operation result is the operation result of the current user on the third medical data selected from the system question bank, and the preset reference result is the result corresponding to the third medical data stored in the system question bank.

[0116] In some specific embodiments, after the user operation behavior evaluation unit, the following is further included:

[0117] A first system question bank creation unit, configured to, if the current evaluation result corresponding to any third medical data meets a first preset condition, create a new system question bank based on the any third medical data, and configure a corresponding selection probability for the any third medical data based on the historical statistical times that meet the first preset condition;

[0118] A first binding relationship establishment unit, configured to establish a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to perform a new round of operation behavior evaluation after entering the fourth mode next time.

[0119] In some specific embodiments, after the behavior evaluation module 13, the following is further included:

[0120] An optimization suggestion generation unit, configured to, if the current evaluation result corresponding to any first medical data meets a second preset condition, generate a corresponding operation optimization suggestion and send it to the current man-machine interface for real-time display;

[0121] A second system question bank creation unit, configured to create a new system question bank based on the any first medical data, and configure a corresponding selection probability for the any first medical data based on the historical statistical times that meet the second preset condition;

[0122] A second binding relationship establishment unit, configured to establish a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to perform a new round of operation behavior evaluation after entering the fourth mode next time.

[0123] In some specific embodiments, the medical assistance system further includes:

[0124] A log data generation unit, configured to record user operation results and / or intelligent inference results generated in any working mode in the form of logs to obtain corresponding log data, so as to process the log data generated within a preset time period by using a preset processing method;

[0125] Wherein, the preset processing method includes any one or a combination of more of analysis of target statistical parameters, analysis of the accuracy rate of intelligent algorithms, statistical analysis of operator behavior, analysis of operator proficiency, analysis of the error rate of operation items, analysis of the time consumed by operation items, and chart creation.

[0126] Furthermore, an embodiment of the present application also provides an electronic device. Figure 6 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure should not be considered as any limitation on the scope of use of the present application.

[0127] Figure 6 It is a schematic structural diagram of an electronic device 20 provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the medical assistance method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0128] In this embodiment, the power supply 26 is used to provide working voltages for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and no specific limitation is imposed on it here; the input / output interface 24 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0129] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc., and the resources stored thereon may include a computer program 221, and the storage method may be short-term storage or permanent storage. Among them, in addition to the computer program that can be used to complete the medical assistance method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.

[0130] Further, the embodiments of the present application also disclose a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the medical assistance method disclosed above is implemented.

[0131] For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated herein.

[0132] The embodiments in this application are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts between the embodiments, reference may be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and reference may be made to the description of the method part for the relevant parts.

[0133] Those skilled in the art can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0134] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0135] Finally, it should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0136] The above has introduced in detail a medical assistance method, device, equipment, and storage medium provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A medical assistance method, characterized in that, including: Obtaining a mode selection instruction to control the medical device to enter the corresponding working mode; If the working mode is the first mode, verifying the accuracy of the current intelligent algorithm based on the difference between the current intelligent reasoning result and the current user operation result; If the working mode is the second mode, evaluating the current user's operation behavior based on the difference between the current user operation result and the current intelligent reasoning result; Wherein, the current user operation result and the current intelligent reasoning result are respectively the operation result of the current user on the first medical data and the reasoning result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user through controlling the medical device to collect data.

2. The medical assistance method according to claim 1, wherein also including: Configuring the first user as the current user in the first mode to generate the current user operation result; Configuring the second user as the current user in the second mode to generate the current user operation result; Wherein, the qualification authority of the first user is higher than that of the second user.

3. The medical assistance method according to claim 1, wherein also including: If the working mode is the third mode, only triggering the intelligent reasoning process to use the current intelligent algorithm to reason about the second medical data to obtain the corresponding current intelligent reasoning result.

4. The medical assistance method according to claim 1, characterized in that, also including: If the working mode is the fourth mode, evaluating the current user's operation behavior based on the difference between the current user operation result and the preset reference result; Wherein, the current user operation result is the operation result of the current user on the third medical data selected from the system question bank, and the preset reference result is the result corresponding to the third medical data saved in the system question bank.

5. The medical assistance method according to claim 4, characterized in that, After evaluating the current user's operation behavior based on the difference between the current user operation result and the preset reference result, it further includes: If the current evaluation result corresponding to any third medical data meets the first preset condition, creating a new system question bank based on the any third medical data, and configuring a corresponding selection probability for the any third medical data based on the historical statistical times that meet the first preset condition; Establishing a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time.

6. The medical assistance method according to claim 4, wherein After evaluating the current user's operation behavior based on the difference between the current user operation result and the current intelligent reasoning result, it further includes: If the current evaluation result corresponding to any first medical data meets the second preset condition, generating a corresponding operation optimization suggestion and sending it to the current human-computer interaction interface for real-time display; Creating a new system question bank based on the any first medical data, and configuring a corresponding selection probability for the any first medical data based on the historical statistical times that meet the second preset condition; Establishing a binding relationship between the new system question bank and the current user, so that the current user can use the new system question bank to conduct a new round of operation behavior evaluation after entering the fourth mode next time.

7. The medical assistance method according to claim 1, wherein also including: The user operation results and / or intelligent inference results generated in any working mode are recorded in the form of logs to obtain corresponding log data, so as to process the log data generated within a preset time period by using a preset processing method; Among them, the preset processing method includes any one or a combination of more of the analysis of target statistical parameters, the analysis of the accuracy of intelligent algorithms, the statistical analysis of operator behavior, the analysis of operator proficiency, the error rate analysis of operation items, the time consumption analysis of operation items, and chart creation.

8. A medical assistance system, characterized in that, It includes: A mode determination module, configured to obtain a mode selection instruction to control the medical device to enter the corresponding working mode; A model verification module, configured to, if the working mode is the first mode, verify the accuracy of the current intelligent algorithm based on the difference between the current intelligent inference result and the current user operation result; A behavior evaluation module, configured to, if the working mode is the second mode, evaluate the operation behavior of the current user based on the difference between the current user operation result and the current intelligent inference result; Among them, the current user operation result and the current intelligent inference result are respectively the operation result of the current user on the first medical data and the inference result of the current intelligent algorithm on the first medical data; the first medical data is the medical data obtained by the current user after controlling the medical device to perform data collection.

9. An electronic device, characterized in that, It includes: A memory, configured to store a computer program; A processor, configured to execute the computer program to implement the medical assistance method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, For storing a computer program; wherein, when the computer program is executed by a processor, the medical assistance method according to any one of claims 1 to 7 is implemented.

Images