Evaluation method for clinical medicine operation normalization, electronic equipment and storage medium

Through video analysis, the medical movements and action moments in clinical medical operations are obtained, and the standard action cohort is compared, which solves the problem that existing evaluation methods rely on subjective recognition, and achieves a more objective and accurate operational normative evaluation.

CN118919095APending Publication Date: 2024-11-08SHANGHAI TMI ROBOTICS TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410962431.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing clinical medical operation evaluation methods rely on human supervision and subjective identification, resulting in poor evaluation results and lack of objectivity.

Method used

By obtaining videos performed by clinicians on patients, performing video analysis to obtain medical actions and action moments, comparing with standard action execution queues to determine whether the operation is compliant, providing an objective evaluation method based on video analysis.

Benefits of technology

It improves the objectivity and accuracy of clinical medical operation evaluation, reduces subjective errors, and enhances the evaluation effect of operational normativeness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118919095A_ABST
    Figure CN118919095A_ABST
Patent Text Reader

Abstract

The invention provides a clinical medicine operation normalization evaluation method, electronic equipment and a storage medium. The method comprises the following steps: acquiring a video that a clinician performs clinical medical operation on a patient; analyzing the video to obtain each medical action occurring in the clinical medical operation and the occurrence time of each medical action; and determining whether the clinical medical operation is compliant or not according to each medical action occurring in the clinical medical operation and the occurrence time of each medical action. Compared with an existing evaluation mode which depends on subjective affirmation of related personnel, the method provides a more objective evaluation mode, so that the evaluation effect can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method, device, electronic device and storage medium for locating the cause of an obstruction. Background Art

[0002] In clinical medical operations such as blood collection, whether clinicians perform operations in accordance with relevant specifications is crucial to the accuracy of the results and patient safety. Therefore, in practical applications, it is usually necessary to evaluate the standardization of these clinical medical operations. Existing evaluation methods mainly include human supervision and observation, regular assessment, and patient feedback. These evaluation methods usually rely on the subjective determination of relevant personnel, resulting in poor evaluation results. Therefore, a more objective evaluation method is needed. Summary of the invention

[0003] The embodiments of the present application provide a method, device, electronic device and storage medium for evaluating the standardization of clinical medical operations, which can be used to evaluate the standardization of clinical medical operations.

[0004] The first aspect of the embodiment of the present application provides a method for evaluating the standardization of clinical medical operations, including:

[0005] Obtain videos of clinicians performing clinical medical operations on patients;

[0006] By parsing the video, each medical action occurring in the clinical medical operation and the time when each medical action occurs are obtained;

[0007] Whether the clinical medical operation is compliant is determined through various medical actions occurring in the clinical medical operation and the time when each medical action occurs.

[0008] Preferably, the video is parsed to obtain various medical actions and the time when each medical action occurs in the clinical medical operation, specifically including:

[0009] By parsing the video, each target image in the video is obtained, wherein the target image is specifically an image including a designated medical object and an operated object; the designated medical object is specifically a medical object used in each standard action included in the operation specification of the clinical medical operation; the operated object is specifically a specific part of the patient's body;

[0010] Each medical action occurring in the clinical medical operation and the time at which each medical action occurs are determined through each target image.

[0011] Preferably, the video is parsed to obtain each target image in the video, which specifically includes: parsing the video through a neural network model to obtain each target image in the video.

[0012] Preferably, determining each medical action occurring in the clinical medical operation and the time when each medical action occurs by each target image specifically includes: processing each target image in the following manner to determine each medical action occurring in the clinical medical operation and the time when each medical action occurs:

[0013] Determining the relative position of the designated medical object and the operated object in the target image;

[0014] determining whether a medical action has occurred according to the relative posture;

[0015] If yes, the type of the medical action that has occurred is determined according to the type of the designated medical article, and the time of occurrence of the medical action that has occurred is determined according to the timestamp of the target image in the video.

[0016] Preferably, determining whether the clinical medical operation is compliant is performed by determining each medical action occurring in the clinical medical operation and the time at which each medical action occurs, which specifically includes:

[0017] By determining whether the clinical medical operation complies with the corresponding operation specification through each medical action occurring in the clinical medical operation and the time when each medical action occurs, it is determined whether the clinical medical operation complies with the regulations.

[0018] Preferably, judging whether the clinical medical operation complies with the corresponding operation specification by means of each medical action occurring in the clinical medical operation and the time when each medical action occurs, specifically includes:

[0019] According to the occurrence time of each medical action, determine the sequence of each medical action and the time interval between adjacent medical actions;

[0020] According to the sequence of each medical action and the time interval between adjacent medical actions, an action execution queue is constructed, wherein the action execution queue includes a plurality of elements, each element being composed of a medical action and an actual time interval between the medical action and a previous medical action; and each element included in the action execution queue is arranged according to the sequence of the corresponding medical actions;

[0021] Compare each element in the action execution queue with each element in the standard action execution queue in turn, and determine whether the clinical medical operation is compliant based on the comparison results; wherein the standard action execution queue includes multiple elements, each element consists of a standard action and a reference time interval between the standard action and the previous standard action; and, each element included in the standard action execution queue is arranged in the order of the corresponding standard actions.

[0022] Preferably, the method further comprises:

[0023] Acquiring an operation specification corresponding to the clinical medical operation, wherein the operation specification includes a plurality of standard actions;

[0024] Obtaining the sequence of each standard action in the operation specification and the reference time interval between adjacent standard actions;

[0025] According to the sequence of each standard action in the operation specification and the reference time interval between adjacent standard actions, a standard action execution queue of the operation specification is constructed.

[0026] Preferably, each element in the action execution queue is compared with each element in the standard action execution queue in sequence, and whether the clinical medical operation is compliant is determined according to the comparison result, which specifically includes executing the following steps in sequence:

[0027] comparing the medical actions of the elements in the action execution queue with the standard actions of the elements in the standard action execution queue to see whether they are the same;

[0028] If they are not the same, it is determined that the clinical medical operation is not in compliance with regulations;

[0029] If they are the same, compare the actual time intervals of the elements in the action execution queue with the standard time intervals of the elements in the standard action execution queue to see if they are within the tolerance range. If not within the tolerance range, determine that the clinical medical operation is non-compliant; or if within the tolerance range, compare the next elements in the action execution queue with the next elements in the standard action execution queue.

[0030] A second aspect of an embodiment of the present application provides an electronic device, including:

[0031] Memory for storing computer programs;

[0032] A processor is used to execute the method described in any one of the first aspects of the embodiments of the present application.

[0033] A third aspect of the embodiments of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method described in any one of the first aspects of the embodiments of the present application is implemented.

[0034] The method for evaluating the standardization of clinical medical operations provided by the embodiment of the present application includes first obtaining a video of a clinician performing a clinical medical operation on a patient, and then analyzing the video to obtain each medical action and the time when each medical action occurred in the clinical medical operation, and then determining whether the clinical medical operation is compliant through each medical action and the time when each medical action occurred in the clinical medical operation. Compared with the existing evaluation method that relies on the subjective identification of relevant personnel, this method provides a more objective evaluation method, and thus can improve the evaluation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application;

[0037] Figure 2 A flowchart of a method for evaluating the standardization of clinical medical operations provided in one embodiment of the present application;

[0038] Figure 3 A schematic diagram of the structure of a device for evaluating the standardization of clinical medical operations provided in one embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application. In the description of the present application, terms such as "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance or sequence.

[0040] As mentioned above, when evaluating the execution process of clinical medical operations, the existing evaluation methods usually rely on the subjective judgment of relevant personnel, resulting in poor evaluation results. Therefore, a more objective evaluation method needs to be provided.

[0041] Based on this, the embodiments of the present application provide a method, device, electronic device and storage medium for evaluating the standardization of clinical medical operations. Figure 1The electronic device 1 is a schematic diagram of a specific structure. The electronic device 1 includes: at least one processor 11 and a memory 12, Figure 1 A processor is used as an example. The processor 11 and the memory 12 may be connected via a bus 10, and the memory 12 stores instructions executable by the processor 11, and the instructions are executed by the processor 11, so that the electronic device 1 can execute all or part of the process of the method in the following embodiment.

[0042] In practical applications, the electronic device 1 can be used as a server-side electronic device, such as a server, etc. Of course, multiple electronic devices 1 can also be built into a cluster to serve as the server. Of course, the electronic device can also be a user-side electronic device, such as a mobile phone, computer, etc. of a user such as a clinician. In one embodiment, the electronic device 1 can be set up in a medical place such as a hospital, so that the method provided in the embodiment of the present application is executed by the electronic device 1 to evaluate the clinical medical operation process of the clinician.

[0043] like Figure 2 The figure shows a flow chart of a method for evaluating the standardization of clinical medical operation provided by an embodiment of the present application. Part or all of the steps of the method can be performed by Figure 1 The method is performed by the electronic device 1 shown in the figure, and comprises the following steps:

[0044] Step S21: Acquire a video of a clinician performing a clinical medical operation on a patient.

[0045] The clinical medical operation refers to the process of the relevant medical operation performed by the clinician on the patient, such as blood collection, drug injection, etc. In practical applications, there are usually relevant operation specifications for different clinical medical operations, which stipulate the various standard actions included in the relevant clinical medical operations. For example, according to the relevant operation specifications, the various standard actions included in blood collection include disinfection, tying a tourniquet, inserting a needle, drawing a blood sample, pulling out the needle, pressing a cotton swab, applying a Band-Aid, etc. These standard actions have a corresponding sequence, such as tying a tourniquet after disinfection, and then inserting a needle.

[0046] Among them, for the specific implementation of step S21, one way is to collect the video of the clinical medical operation process in real time through a camera. Specifically, for example, when the clinician performs clinical medical operations on the patient, the video can be taken through the mobile phone carried by the clinician himself, or a camera can be set up in a relevant place to collect the video of the clinical medical operation of the clinician, so as to obtain the video. Another way can also be to obtain the video from a video library. For example, when multiple clinicians perform clinical medical operations on different patients respectively, the corresponding videos are collected respectively at this time. These videos can be stored in the video library first, so that in step S21, the corresponding video can be obtained from the video library according to the order in which these videos are stored in the video library.

[0047] In one embodiment, for example, a camera may be installed in the blood collection area of ​​a medical facility, so that during the process of drawing blood from a patient, a clinician may use the camera to capture a video of the clinician drawing blood from the patient.

[0048] Step S22: Analyze the video to obtain various medical actions and the time when each medical action occurs in the clinical medical operation.

[0049] As mentioned above, different clinical medical operations usually have relevant operating specifications, which specify the various standard actions included in the relevant clinical medical operations.

[0050] Therefore, in order to conduct a normative evaluation of the clinical medical operation, in step S22 of the embodiment of the present application, it is necessary to parse the video to obtain the various medical actions that occurred in the clinical medical operation and the time when each medical action occurred. Among them, for the specific implementation of step S22, in actual application, the video can be parsed first to obtain various target images in the video, wherein the target image specifically includes an image of a designated medical article and an operated object, and then the various medical actions that occurred in the clinical medical operation and the time when each medical action occurred are determined through the various target images.

[0051] The designated medical items are specifically the medical items used in each standard action included in the operation specification of the clinical medical operation. For example, the medical items required to be used in each standard action included in blood collection include tourniquets, cotton swabs, needles, etc. Therefore, for blood collection, the designated medical items include blood bands and cotton swabs, etc. The operated object is specifically a specific part of the patient's body. For example, for blood collection, the operated object can be the patient's arm, finger, etc.

[0052] That is, in the specific implementation of step S22, each target image in the video is first obtained, and the target image specifically includes an image of a designated medical object and an operated object. For example, for blood drawing, the target image obtained from the video includes a designated medical object such as a blood strip or a cotton swab, and an operated object such as a patient's arm or finger.

[0053] In addition, in a specific implementation method of parsing the video to obtain each target image in the video, the video can be parsed by a neural network model to obtain each target image in the video. For example, the neural network model can be pre-trained, so that the video can be input into the neural network model, so that the neural network model parses the video and outputs each target image in the video. How to train the neural network model will be described later. Of course, another implementation method of parsing the video to obtain each target image in the video is to parse each frame image in the video separately, so as to obtain each target image from each frame image of the video.

[0054] Of course, when each target image is acquired, the timestamp of each target image in the video may also be recorded for subsequent determination of the time when each medical action occurs.

[0055] After acquiring each target image, one method is to directly determine each medical action occurring in the clinical medical operation and the time when each medical action occurs through each target image. Specifically, for example, for each target image, the relative posture (the relative posture includes the relative position as posture) of the specified medical object and the operated object in the target image is determined, and then whether a medical action has occurred is determined based on the relative posture. If so, the type of medical action that has occurred is further determined based on the type of the specified medical object.

[0056] It should be noted that a medical action is usually an action performed by a clinician on a specific part of a patient using a designated medical item. For example, when a clinician is performing disinfection, he or she usually needs to use a cotton swab to disinfect the patient's arm. Therefore, in the embodiment of the present application, each target image can be processed in the following manner to determine each medical action that occurs in the clinical medical operation and the time when each medical action occurs:

[0057] Specifically, the relative posture between the designated medical object and the operated object in the target image can be determined first, such as the tail of the cotton swab is close to the patient's arm, the needle is close to the patient's arm, etc., and then the relative posture can be used to determine whether a medical action has occurred. If it is determined that a medical action has occurred, it is necessary to further determine the type of medical action that has occurred. Specifically, the type of medical action that has occurred can be determined based on the type of the designated medical object. For example, if the designated medical object is a cotton swab, the type of medical action that has occurred is disinfection. If the designated medical object is a needle, the type of medical action that has occurred is acupuncture blood drawing. Of course, if it is determined that no medical action has occurred, the next target image can be processed accordingly.

[0058] In addition, if it is determined that a medical action has occurred, the time when the medical action occurred can be determined based on the timestamp of the target image in the video. For example, the timestamp can be directly used as the time of occurrence. Of course, if the video is edited, the time of occurrence can be calculated based on the timestamp.

[0059] It is mentioned above that after acquiring each target image, one method is to directly determine each medical action occurring in the clinical medical operation and the time when each medical action occurs through each target image. It should be further explained that in practical applications, in order to improve the accuracy of recognition, the target image can also be preprocessed first, and after the preprocessing, each medical action occurring in the clinical medical operation and the time when each medical action occurs can be determined through each preprocessed target image.

[0060] Among them, the preprocessing method can be to remove the background color of the target image inspection table, so that the designated medical objects and the operated objects can be more clearly displayed, and then the target image can be further annotated using a neural network model to further annotate the contours of the designated medical objects and the operated objects in the target image, so as to facilitate the subsequent more accurate determination of the various medical actions occurring in the clinical medical operation and the time of occurrence of each medical action based on the designated medical objects and the operated objects marked in the target image.

[0061] Step S23: Determine whether the clinical medical operation is compliant through each medical action in the clinical medical operation and the time when each medical action occurs.

[0062] After obtaining each medical action in the clinical medical operation and the time when each medical action occurs through the above-mentioned step S22, in this step S23, whether the clinical medical operation is compliant can be further determined through each medical action in the clinical medical operation and the time when each medical action occurs.

[0063] For example, the various medical actions occurring in the clinical medical operation and the time at which each medical action occurs can be used to judge whether the clinical medical operation complies with the corresponding operating specifications, thereby determining whether the clinical medical operation is compliant. For example, if it complies with the corresponding operating specifications, then the clinical medical operation can be determined to be compliant. Otherwise, if it does not comply with the corresponding operating specifications, then the clinical medical operation is determined to be non-compliant.

[0064] In actual applications, in order to facilitate the judgment of whether the clinical medical operation complies with the corresponding operation specifications through the various medical actions occurring in the clinical medical operation and the time when each medical action occurs, the operation specifications corresponding to the clinical medical operation can be obtained first, and the operation specifications include multiple standard actions. Then, the operation specifications corresponding to the clinical medical operation can be abstracted. Specifically, the sequence of each standard action in the operation specification and the reference time interval of adjacent standard actions can be obtained, and then the standard action execution queue of the operation specification is constructed according to the sequence of each standard action in the operation specification and the reference time interval of adjacent standard actions. The standard action execution queue includes multiple elements, each element consists of a standard action and the reference time interval between the standard action and the previous standard action. In addition, the standard action execution queue includes each element arranged in the sequence of corresponding standard actions.

[0065] For example, the operation specification corresponding to the clinical medical operation is operation specification A, which includes multiple standard actions, namely behavior_1, behavior_2, behavior_3, ..., behavior_n-1, behavior_n, where the time interval between behavior_2 and behavior_1 is t1, the time interval between behavior_3 and behavior_2 is t2 ..., and the time interval between behavior_n and behavior_n-1 is tn-1. Therefore, the standard action execution queue constructed for this operation specification is [{behavior_1, t0}, {behavior_2, t1}, {behavior_3, t2}, ..., {behavior_n, tn-1}]. In the standard action execution queue, for example, the element {behavior_n, tn-1} is composed of a standard action behavior_n, and the reference time interval tn-1 between the standard action behavior_n and the previous standard action behavior_n-1, and the elements in the standard action execution queue are arranged in the order of the corresponding standard actions, that is, behavior_1, behavior_2, behavior_3..., behavior_n-1, behavior_n. The standard action in the first element in the standard action execution queue is the first standard action behavior_1. Since behavior_1 has no previous standard action, the time interval between the first standard action and the previous standard action can be t0, and t0 can be 0 or other preset values, or a null value.

[0066] For example, if the clinical medical operation is specifically blood drawing, the corresponding operation specification is that the standard actions included in the operation specification include disinfection, tying a tourniquet, inserting a needle, drawing blood samples, pulling out the needle, pressing a cotton swab, applying a Band-Aid, etc., wherein the reference time interval between tying a tourniquet and disinfection is 5 seconds, the reference time interval between inserting a needle and tying a tourniquet is 10 seconds, the reference time interval between drawing blood samples and inserting a needle is 3 seconds, the reference time interval between pulling out the needle and drawing blood samples is 5 seconds, the reference time interval between pressing a cotton swab and pulling out the needle is 2 seconds, and the reference time interval between applying a Band-Aid and pressing a cotton swab is 3 seconds; the standard action execution queue of the operation specification constructed in this way is [{"disinfection", 0.0}, {"tying a tourniquet", 5.0}, {"inserting a needle", 10.0}, {"drawing blood samples", 3.0}, {"pulling out a needle", 5.0}, {"pressing a cotton swab", 2.0}, {"applying a Band-Aid", 3.0}].

[0067] In this way, in step S23, the sequence of each medical action and the time interval between adjacent medical actions can be determined according to the time when each medical action occurs. Then, based on the same principle as the above-mentioned standard action execution queue, an action execution queue can be constructed according to the sequence of each medical action and the time interval between adjacent medical actions. The action execution queue includes multiple elements, each element consists of a medical action and the actual time interval between the medical action and the previous medical action. In addition, the action execution queue includes elements arranged in the sequence of corresponding medical actions.

[0068] For example, the various medical actions in the clinical medical operation are behavior_1', behavior_2', behavior_3'..., behavior_n-1', behavior_n', and the occurrence time of each medical action is T1, T2, T3..., Tn-1, Tn respectively. In this way, the sequence of each medical action can be determined according to the occurrence time of each medical action, and after determining the sequence, the time interval between adjacent medical actions can be further calculated according to the occurrence time of each medical action, and then the action execution queue can be constructed according to the sequence of each medical action and the time interval between adjacent medical actions. For example, in this example, the action execution queue that can be constructed is [{behavior_1',t0'}, {behavior_2',t1'}, {behavior_3',t2'},..., {behavior_n',tn-1'}]. Among them, t1'=T2-T1; t2'=T3-T2; ... tn-1'=Tn-Tn-1.

[0069] After obtaining the action execution queue, each element in the action execution queue is compared with each element in the standard action execution queue in turn, so as to determine whether the clinical medicine operation is compliant according to the comparison result. For example, when comparing an element in the action execution queue with an element in the standard action execution queue, first compare the medical action of the element in the action execution queue to see if it is the same as the standard action of the element in the standard action execution queue. If not, it means that the two do not match, and then it can be determined that the clinical medicine operation is not compliant; on the contrary, if they are the same, then further compare the actual time interval of the element in the action execution queue with the standard time interval of the element in the standard action execution queue, and whether the two are within the tolerance range, such as determining the ratio of the actual time interval to the standard time interval, and then determining whether the two are within the tolerance range according to the ratio, of course, it can also be determined whether it is within the tolerance range according to the difference between the two, at this time, if it is not within the tolerance range, it can be determined that the clinical medicine operation is not compliant, if it is within the tolerance range, then further compare the next element. Among them, the tolerance range can usually be set according to actual needs, and this is not limited here.

[0070] The method for evaluating the standardization of clinical medical operations provided by the embodiment of the present application includes first obtaining a video of a clinician performing a clinical medical operation on a patient, and then analyzing the video to obtain each medical action and the time when each medical action occurred in the clinical medical operation, and then determining whether the clinical medical operation is compliant through each medical action and the time when each medical action occurred in the clinical medical operation. Compared with the existing evaluation method that relies on the subjective identification of relevant personnel, this method provides a more objective evaluation method, and thus can improve the evaluation effect.

[0071] For the neural network model mentioned in the embodiments of the present application, in practical applications, it can be pre-trained in the following manner: first construct a training set, including data collection and labeling. Specifically, a large number of images and videos containing clinical medical operations can be collected, and the corresponding data can be obtained from them for labeling. Of course, image enhancement and segmentation can also be performed to increase data diversity and improve image quality.

[0072] After constructing the training set, you can choose a suitable pre-trained model, such as Faster R-CNN, Mask R-CNN, YOLO, U-Net, etc.; then use the samples in the training set to train the pre-trained model, including optimizing the model parameters through back propagation and gradient descent, training the segmentation model according to pixel-level annotation, and learning the classification of each pixel; after the training is completed, further use the validation set to evaluate the model performance, check the accuracy, recall rate, F1 score and other indicators, adjust the model hyperparameters, and perform tuning to improve performance; then perform model testing, specifically, the model can be tested on an independent test set to evaluate its performance in the actual scene. According to the test results, the model is further adjusted and improved to obtain the final neural network model in the embodiment of the present application. Of course, in the actual application of the neural network model, the neural network model can also be continuously optimized and improved according to actual needs.

[0073] Based on the same inventive concept as the method for evaluating the standardization of clinical medical operations provided in the embodiment of the present application, the embodiment of the present application also provides an evaluation device for the standardization of clinical medical operations. For any details not described in detail in the embodiment of the device, reference may be made to the corresponding contents of the method embodiment. Figure 3 The specific structural diagram of the device 30 is shown, and the device 30 includes: a video acquisition unit 301, a video analysis unit 302 and a compliance judgment unit 303, wherein:

[0074] The video acquisition unit 301 is used to acquire a video of a clinician performing a clinical medical operation on a patient;

[0075] A video parsing unit 302, configured to parse the video to obtain various medical actions and occurrence times of various medical actions in the clinical medical operation;

[0076] The compliance judgment unit 303 is used to determine whether the clinical medical operation is compliant through various medical actions occurring in the clinical medical operation and the time when each medical action occurs.

[0077] The device 30 provided in the embodiment of the present application is adopted. Since the device 30 adopts the same inventive concept as the method provided in the embodiment of the present application, on the premise that the method can solve the technical problem, the device 30 can also solve the technical problem, which will not be repeated here.

[0078] In addition, in actual applications, the technical effects achieved by combining the device 30 with specific hardware equipment, cloud technology, etc. are also within the scope of protection of the present application. For example, different units in the device 30 are deployed in different nodes in the distributed cluster in a distributed cluster manner, or some units are deployed in a cloud server, etc., to improve efficiency and reduce costs.

[0079] The method of parsing the video to obtain various medical actions and the time when each medical action occurs in the clinical medical operation may specifically include:

[0080] By parsing the video, each target image in the video is obtained, wherein the target image is specifically an image including a designated medical object and an operated object; the designated medical object is specifically a medical object used in each standard action included in the operation specification of the clinical medical operation; the operated object is specifically a specific part of the patient's body;

[0081] Each medical action occurring in the clinical medical operation and the time at which each medical action occurs are determined through each target image.

[0082] Among them, parsing the video to obtain each target image in the video can specifically include: parsing the video through a neural network model to obtain each target image in the video.

[0083] Wherein, determining each medical action occurring in the clinical medical operation and the time when each medical action occurs by each target image may specifically include: processing each target image in the following manner to determine each medical action occurring in the clinical medical operation and the time when each medical action occurs:

[0084] Determining the relative position of the designated medical object and the operated object in the target image;

[0085] determining whether a medical action has occurred according to the relative posture;

[0086] If yes, the type of the medical action that has occurred is determined according to the type of the designated medical article, and the time of occurrence of the medical action that has occurred is determined according to the timestamp of the target image in the video.

[0087] Wherein, determining whether the clinical medical operation is compliant through each medical action occurring in the clinical medical operation and the time when each medical action occurs may specifically include:

[0088] By determining whether the clinical medical operation complies with the corresponding operation specification through each medical action occurring in the clinical medical operation and the time when each medical action occurs, it is determined whether the clinical medical operation complies with the regulations.

[0089] Among them, judging whether the clinical medical operation complies with the corresponding operation specification by means of each medical action occurring in the clinical medical operation and the time when each medical action occurs may specifically include:

[0090] According to the occurrence time of each medical action, determine the sequence of each medical action and the time interval between adjacent medical actions;

[0091] According to the sequence of each medical action and the time interval between adjacent medical actions, an action execution queue is constructed, wherein the action execution queue includes a plurality of elements, each element being composed of a medical action and an actual time interval between the medical action and a previous medical action; and each element included in the action execution queue is arranged according to the sequence of the corresponding medical actions;

[0092] Compare each element in the action execution queue with each element in the standard action execution queue in turn, and determine whether the clinical medical operation is compliant based on the comparison results; wherein the standard action execution queue includes multiple elements, each element consists of a standard action and a reference time interval between the standard action and the previous standard action; and, each element included in the standard action execution queue is arranged in the order of the corresponding standard actions.

[0093] The device 30 may also include a standard action execution queue construction unit, which is used to obtain the operation specifications corresponding to the clinical medical operation, wherein the operation specifications include multiple standard actions; obtain the sequence of each standard action in the operation specifications and the reference time interval between adjacent standard actions; and construct the standard action execution queue of the operation specifications based on the sequence of each standard action in the operation specifications and the reference time interval between adjacent standard actions.

[0094] The steps of sequentially comparing each element in the action execution queue with each element in the standard action execution queue and determining whether the clinical medical operation is compliant according to the comparison result specifically include sequentially performing the following steps:

[0095] comparing the medical actions of the elements in the action execution queue with the standard actions of the elements in the standard action execution queue to see whether they are the same;

[0096] If they are not the same, it is determined that the clinical medical operation is not in compliance with regulations;

[0097] If they are the same, compare the actual time intervals of the elements in the action execution queue with the standard time intervals of the elements in the standard action execution queue to see if they are within the tolerance range. If not within the tolerance range, determine that the clinical medical operation is non-compliant; or if within the tolerance range, compare the next elements in the action execution queue with the next elements in the standard action execution queue.

[0098] An embodiment of the present invention further provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing all or part of the process of the method in the above embodiment described in any one of the first aspects of the embodiments of the present application.

[0099] The embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program implements all or part of the process of the method in the above embodiment when executed by a processor. The storage medium may be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD). The storage medium may also include a combination of the above-mentioned types of memory.

[0100] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for evaluating the standardization of clinical medical operations. It is characterized in that include: Obtain videos of clinicians performing clinical medical operations on patients; By parsing the video, each medical action occurring in the clinical medical operation and the time when each medical action occurs are obtained; Whether the clinical medical operation is compliant is determined through various medical actions occurring in the clinical medical operation and the time when each medical action occurs.

2. The method according to claim 1, It is characterized in that By parsing the video, various medical actions and the time of occurrence of each medical action in the clinical medical operation are obtained, specifically including: By parsing the video, each target image in the video is obtained, wherein the target image is specifically an image including a designated medical object and an operated object; the designated medical object is specifically a medical object used in each standard action included in the operation specification of the clinical medical operation; the operated object is specifically a specific part of the patient's body; Each medical action occurring in the clinical medical operation and the time at which each medical action occurs are determined through each target image.

3. The method according to claim 2, It is characterized in that The video is parsed to obtain each target image in the video, specifically including: the video is parsed through a neural network model to obtain each target image in the video.

4. The method according to claim 2, It is characterized in that Determining each medical action occurring in the clinical medical operation and the time when each medical action occurs by each target image specifically includes: processing each target image in the following manner to determine each medical action occurring in the clinical medical operation and the time when each medical action occurs: Determining the relative position of the designated medical object and the operated object in the target image; determining whether a medical action has occurred according to the relative posture; If yes, the type of the medical action that has occurred is determined according to the type of the designated medical article, and the time of occurrence of the medical action that has occurred is determined according to the timestamp of the target image in the video.

5. The method according to claim 1, It is characterized in that Determining whether the clinical medical operation is compliant by means of various medical actions occurring in the clinical medical operation and the time at which each medical action occurs, specifically includes: By determining whether the clinical medical operation complies with the corresponding operation specification through each medical action occurring in the clinical medical operation and the time when each medical action occurs, it is determined whether the clinical medical operation complies with the regulations.

6. The method according to claim 5, It is characterized in that Judging whether the clinical medical operation complies with the corresponding operation specification by means of each medical action occurring in the clinical medical operation and the time at which each medical action occurs, specifically includes: According to the occurrence time of each medical action, determine the sequence of each medical action and the time interval between adjacent medical actions; According to the sequence of each medical action and the time interval between adjacent medical actions, an action execution queue is constructed, wherein the action execution queue includes a plurality of elements, each element being composed of a medical action and an actual time interval between the medical action and a previous medical action; and each element included in the action execution queue is arranged according to the sequence of the corresponding medical actions; Compare each element in the action execution queue with each element in the standard action execution queue in turn, and determine whether the clinical medical operation is compliant based on the comparison results; wherein the standard action execution queue includes multiple elements, each element consists of a standard action and a reference time interval between the standard action and the previous standard action; and, each element included in the standard action execution queue is arranged in the order of the corresponding standard actions.

7. The method according to claim 6, further comprising: include: Acquiring an operation specification corresponding to the clinical medical operation, wherein the operation specification includes a plurality of standard actions; Obtaining the sequence of each standard action in the operation specification and the reference time interval between adjacent standard actions; According to the sequence of each standard action in the operation specification and the reference time interval between adjacent standard actions, a standard action execution queue of the operation specification is constructed.

8. The method according to claim 6, It is characterized in that Comparing each element in the action execution queue with each element in the standard action execution queue in turn, and determining whether the clinical medical operation is compliant according to the comparison result, specifically includes executing the following steps in turn: comparing the medical actions of the elements in the action execution queue with the standard actions of the elements in the standard action execution queue to see whether they are the same; If they are not the same, it is determined that the clinical medical operation is not in compliance with regulations; If they are the same, compare the actual time intervals of the elements in the action execution queue with the standard time intervals of the elements in the standard action execution queue to see if they are within the tolerance range. If not within the tolerance range, determine that the clinical medical operation is non-compliant; or if within the tolerance range, compare the next elements in the action execution queue with the next elements in the standard action execution queue.

9. An electronic device, It is characterized in that include: Memory for storing computer programs; A processor, configured to execute the blocking cause locating method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the blocking cause locating method according to any one of claims 1 to 8 is implemented.