A rapid triage method and medium for sudden mass incidents

Abstract

The present invention relates to a rapid triage method and medium for sudden mass incidents, and relates to the field of medical information technology. Based on intelligent wearable devices, vital sign data of each patient is collected, and based on image acquisition devices, external trauma information of patients with external trauma is collected, and the collected vital sign data and external trauma information are associated and uploaded with identity information; for any patient, based on the collected vital sign data, or, vital sign data and external trauma information, injury analysis is performed to obtain the injury level; based on the injury level of each patient, priority sorting and treatment are carried out; for any patient with multiple external traumas, based on the external trauma information, the severity ranking of external traumas is obtained, and priority sorting and treatment are carried out based on the severity ranking of external traumas, which can more accurately judge the severity of each patient's injury in sudden mass incidents and reduce the situation of delaying the condition due to untimely treatment.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and particularly to a method and medium for rapid triage and classification of emergency mass incidents. Background Art

[0002] In emergency mass incidents (such as natural disasters, large-scale accidents, etc.), the emergency department faces the urgent treatment of a large number of wounded. The types and injuries of the wounded are complex and variable. Traditional injury assessment and classification usually rely on manual judgment and subjective experience, which are prone to problems such as delayed judgment, misclassification, and uneven distribution of resources, affecting the treatment efficiency.

[0003] Existing injury classification methods mostly rely on simple manual assessment or data from biosensors. However, these methods are single, fail to effectively combine multiple data sources, and lack intelligent and automated decision support.

[0004] Therefore, there is an urgent need for an intelligent system that can efficiently and accurately classify the wounded and provide real-time decision support in emergency mass incidents. Especially in the emergency treatment of emergency mass incidents, it can improve the efficiency of treating the wounded, reduce waste of medical resources, and increase the success rate of rescue. Summary of the Invention

[0005] The technical problem to be solved by this application is to provide a method and medium for rapid triage and classification of emergency mass incidents, which have the characteristics of being able to more accurately judge the severity of the injuries of each patient in an emergency mass incident and reducing the delay of the condition due to untimely treatment.

[0006] In a first aspect, in one embodiment, a method for rapid triage and classification of emergency mass incidents is provided, including:

[0007] Collect the identity information of each patient;

[0008] Collect the vital sign data of each patient based on intelligent wearable devices, and associate and upload the collected vital sign data with the identity information;

[0009] Collect the external trauma information of patients with external trauma based on image acquisition devices, and associate and upload the collected external trauma information with the identity information; the external trauma information includes trauma image information and the human body position where the trauma is located;

[0010] For any patient, based on the collected vital sign data, or, vital sign data and external trauma information, perform injury analysis to obtain the injury level; perform priority sorting and treatment based on the injury level of each patient;

[0011] For any patient with multiple external traumas, obtain the ranking of the severity of external traumas based on the external trauma information, and perform priority-based treatment according to this ranking of the severity of external traumas.

[0012] In one embodiment, for any patient, based on the collected vital sign data, or vital sign data and external trauma information, perform injury analysis to obtain the injury level, including:

[0013] For any patient, when the collected data only includes vital sign data, based on the vital sign data, through the first injury level recognition model, identify the injury level of this patient; the first injury level recognition model is a neural network model trained in combination with the first loss function and used to identify the injury level based on the characteristics of vital sign data.

[0014] In one embodiment, for any patient, based on the collected vital sign data, or vital sign data and external trauma information, perform injury analysis to obtain the injury level, including:

[0015] For any patient, when the collected data includes both vital sign data and external trauma information, based on the vital sign data and external trauma information, through the second injury level recognition model, identify the injury level of this patient; the second injury level recognition model is a neural network model trained in combination with the second loss function and used to identify the injury level based on the characteristics of vital sign data and the characteristics of external trauma information.

[0016] In one embodiment, the method of identifying the injury level of any patient based on the vital sign data and external trauma information through the second injury level recognition model includes:

[0017] Identify the wound type, wound depth, and trauma range from the trauma image information in the external trauma information;

[0018] Based on the identified wound type, wound depth, and trauma range, combined with the body location where the trauma is located and the vital sign data, through the second injury level recognition model, identify the injury level of this patient.

[0019] In one embodiment, the injury levels from high to low include red, yellow, green, and black, where red indicates life danger and immediate emergency treatment is required; yellow indicates severe injury but no life danger; green indicates minor injury and stable vital signs; black indicates death or untreatable condition.

[0020] In one embodiment, for a patient whose injury level does not reach the preset injury level, within a preset time period, continuously collect the patient's vital sign data and obtain the injury level. If the injury level still does not reach the preset injury level when the collection duration meets the preset time period, then use the highest injury level obtained within the preset time period as the highest injury level for treatment.

[0021] In one embodiment, for a patient whose injury level reaches the preset injury level, give an alarm prompt.

[0022] In one embodiment, for any patient with multiple external traumas, obtain the ranking of the severity of external traumas based on the external trauma information, including:

[0023] Based on the trauma image information and the human body position information where the trauma is located, through a trauma severity recognition model, recognize the trauma severity of each trauma; the trauma severity recognition model is a neural network model trained in combination with a third loss function and recognizes the trauma severity based on the characteristics of the trauma image information and the human body position information where the trauma is located.

[0024] In one embodiment, the method of recognizing the trauma severity of each trauma based on the trauma image information and the human body position information where the trauma is located through a trauma severity recognition model includes:

[0025] For any one trauma, recognize the wound type, wound depth, and trauma range from the trauma image information in the external trauma information;

[0026] Based on the recognized wound type, wound depth, and trauma range, combined with the human body position where the trauma is located, through the trauma severity recognition model, recognize the trauma severity of the arbitrary trauma;

[0027] Based on the recognized trauma severity of each trauma, conduct a ranking of the severity of external traumas.

[0028] In a second aspect, in one embodiment, a computer-readable storage medium is provided. A program is stored in the medium, and the program can be loaded and executed by a processor to perform the rapid triage and classification method for sudden mass incidents described in any one of the above embodiments.

[0029] The beneficial effects of the present invention are:

[0030] Since the vital sign data of each patient is collected based on intelligent wearable devices, and the external trauma information of patients with external trauma is collected based on image acquisition devices, for any patient, the injury level is obtained through injury analysis based on the collected vital sign data, or the vital sign data and external trauma information. In this way, the injury level of each patient can be obtained more accurately, so that patients with a higher injury level can be treated preferentially, reducing the situation where patients with more serious conditions cannot receive timely treatment and their conditions are delayed. For patients with a lower injury level who do not meet the requirements for timely treatment or hospital treatment, the waste of medical resources can be reduced. For any patient with multiple external traumas, since the severity ranking of external traumas is obtained based on the external trauma information and priority treatment is carried out based on this severity ranking, it is possible to more accurately determine the part that needs to be treated preferentially in the case of a patient with multiple diseases or traumas, reducing the situation where more serious traumas cannot receive timely treatment and the condition is delayed. Description of the Drawings

[0031] Figure 1 is a schematic flowchart of a method for rapid triage and classification of sudden mass incidents according to an embodiment of the present application;

[0032] Figure 2 is a schematic flowchart of a method for identifying the injury level of any patient according to an embodiment of the present application;

[0033] Figure 3 is a schematic flowchart of a method for identifying the severity of each trauma according to an embodiment of the present application. Detailed Embodiments

[0034] The present invention will be further described in detail below in conjunction with the drawings through specific embodiments. Similar elements in different embodiments are denoted by related similar element numbers. In the following embodiments, many detailed descriptions are provided to enable a better understanding of the present application. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present application are not shown or described in the specification to avoid the core part of the present application being overwhelmed by excessive descriptions. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0035] In addition, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description may also be reordered or adjusted in a manner obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for clearly describing a certain embodiment and do not mean a necessary sequence, unless it is stated otherwise that a certain sequence must be followed.

[0036] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any sequential or technical meaning.

[0037] For the convenience of explaining the inventive concept of this application, the first aid techniques in sudden mass incidents are briefly described below.

[0038] If a sudden mass incident occurs, such as a natural disaster, a large-scale accident, etc., there are often a large number of injuries. In current sudden mass incidents, generally all the injured people are sent to the hospital for examination and treatment. However, the applicant has found in the research that, on the one hand, due to the shortage of medical resources, the people given priority for treatment are often those with severe trauma on the body surface or those whose physical condition is visually severely affected. However, the severity is often difficult to accurately judge from the surface condition. Therefore, there are often people with more serious conditions who cannot receive timely treatment and their conditions are delayed. On the other hand, some of the injured people may not be in serious condition and do not need to be sent to the hospital for emergency treatment, but due to the inability to accurately and quickly judge, medical resources are wasted. On the third hand, in the case of a patient with multiple diseases or traumas, it is often impossible to accurately judge which disease or trauma should be preferentially pretreated when the medical staff lack experience, which will also cause more serious traumas to not receive timely treatment and the condition to be delayed.

[0039] In view of this, the present application provides a rapid triage method and medium for sudden mass incidents. Based on intelligent wearable devices, vital sign data of each patient is collected, and based on image acquisition devices, external trauma information of patients with external trauma is collected. For any patient, based on the collected vital sign data, or vital sign data and external trauma information, injury analysis is performed to obtain the injury level. In this way, the injury level of each patient can be obtained more accurately, so that patients with a higher injury level can be given priority treatment, reducing the situation where patients with more serious conditions cannot receive timely treatment and their conditions are delayed. For patients with a lower injury level who do not meet the requirements for timely treatment or hospital treatment, waste of medical resources can be reduced. In addition, for any patient with multiple external traumas, the severity ranking of the external traumas is obtained based on the external trauma information, and priority treatment is carried out based on this severity ranking. In this way, in the case of a patient with multiple diseases or traumas, the part that needs to be treated first can be judged more accurately, reducing the situation where more serious traumas cannot receive timely treatment and the condition is delayed.

[0040] In one embodiment, the present application provides a rapid triage method for sudden mass incidents. Please refer to Figure 1 , including:

[0041] Step S10, collect the identity information of each patient.

[0042] In one embodiment, the identity information may include any combination of name, ID number, phone number, etc., which can represent the identity information of the patient.

[0043] Step S20, based on intelligent wearable devices, collect the vital sign data of each patient, and associate and upload the collected vital sign data with the identity information.

[0044] Those skilled in the art can understand that the intelligent wearable devices here can be various existing intelligent wearable devices that can collect vital sign data, such as intelligent bracelets, portable heart rate monitors, blood oxygen meters, etc. The collected vital sign data may include heart rate, blood pressure, blood oxygen saturation, body temperature, etc. The collected vital sign data is associated and uploaded with the identity information, so as to obtain the vital sign data of each identified patient.

[0045] Step S30, based on image acquisition devices, collect the external trauma information of patients with external trauma, and associate and upload the collected external trauma information with the identity information. Among them, the external trauma information includes trauma image information and the human body position where the trauma is located.

[0046] In one embodiment, the image acquisition device can be an intelligent image acquisition terminal with a camera such as a mobile phone or a tablet, or a dedicated device.

[0047] Based on the collected traumatic image information, the wound type, wound depth, and trauma scope can be obtained through image feature recognition. The wound type can include laceration, hemorrhagic trauma, open trauma, etc.

[0048] Step S40: For any patient, based on the collected vital sign data, or vital sign data and external trauma information, perform injury condition analysis to obtain the injury level; perform priority sorting and treatment based on the injury level of each patient.

[0049] The applicant found in the research that in sudden mass incidents, among the individual objects involved, some have obvious surface traumas, some do not have obvious surface traumas, and some do not show any trauma conditions or symptoms affecting vital signs in the early stage. Therefore, the situation that requires emergency treatment or intervention treatment is not discovered in time, resulting in irreparable situations without timely treatment.

[0050] In view of this, for each individual object in a sudden mass incident, collect its vital sign data. For example, for more than a dozen people involved in a car accident, collect the vital sign data of each person. For any one of them, if there is no obvious external trauma, only collect the vital sign data; if there is obvious external trauma, collect the external trauma information at the same time.

[0051] In one embodiment, for any patient, when the collected data only includes vital sign data, based on the vital sign data, through the first injury level recognition model, the injury level of the any patient is recognized. Among them, the first injury level recognition model is a neural network model trained in combination with the first loss function and used to recognize the injury level based on the vital sign data characteristics.

[0052] In one embodiment, the training method of the first injury level recognition model includes:

[0053] Step S110: Collect the vital sign data of multiple patients and label the vital sign data to clarify the injury level.

[0054] Widely collect vital sign data corresponding to various injury levels, such as heart rate, blood pressure, blood oxygen saturation, body temperature, etc. The data sources can be the hospital's electronic medical record system, the records of the emergency center, and relevant medical research databases, etc., to ensure that the data has sufficient diversity and representativeness.

[0055] According to professional medical standards and clinical experience, label the collected data with injury levels. The labeling process needs to involve professional medical staff or medical experts to ensure the accuracy of the labeling.

[0056] In one embodiment, the injury levels from high to low can include red, yellow, green, and black, where red indicates life-threatening and immediate emergency treatment is required; yellow indicates severe injury but no life-threatening; green indicates minor injury and stable vital signs; black indicates death or untreatable.

[0057] For the above red, yellow, green, and black injury levels, those skilled in the art can understand that they can be graded based on actual requirement standards. For example, for the red injury level, the applicable situations usually include cardiac arrest, severe airway obstruction, massive bleeding that cannot be controlled, severe craniocerebral injury with coma, severe chest trauma causing dyspnea, etc. If these situations are not treated in time, the injured may die within a short time. For the yellow injury level, the applicable situations can include multiple fractures, large-area burns without respiratory tract injury, severe soft tissue injury, etc. Such injured patients need to be treated within a certain time but can wait slightly to let the red-level injured receive treatment first. For the green injury level, common ones are mild abrasions, sprains, small-area superficial burns, etc. These injured patients can usually be simply treated on-site or further treated after the red and yellow injured are treated. For the black injury level, the applicable situations include when the injured has obvious signs of death, such as dilated and fixed pupils, lividity, and severe body destruction that cannot be effectively treated, etc., and will be marked as black. For such injured patients, the main thing is to identify their identities and perform subsequent processing rather than medical treatment.

[0058] Step S210, preprocess the labeled data, convert it into a format suitable for input to the first injury level recognition model, and obtain a data set.

[0059] Step S210 can include: cleaning the original data to remove duplicates, errors, and missing values. Then perform normalization or standardization processing to map data with different features to the same scale range to improve the training efficiency and stability of the model.

[0060] Step S310, divide the data set into a training set, a validation set, and a test set.

[0061] Step S410, construct the primary architecture of the first injury level recognition model, based on the preset training parameters, use the training set as the input of the primary architecture of the first injury level recognition model for training, evaluate the performance of the first injury level recognition model during training based on the validation set and adjust the hyperparameters, and evaluate the generalization ability of the first injury level recognition model based on the test set, so as to obtain the trained first injury level recognition model.

[0062] In one embodiment, the primary architecture of the first injury level recognition model can be constructed based on a multi-layer perceptron (MLP) and a long short-term memory network (LSTM), so as to obtain a more accurate injury level based on continuously collected real-time vital sign data.

[0063] In one embodiment, the first loss function can adopt a cross-entropy loss function.

[0064] In one embodiment, for any patient, when the collected data includes vital sign data and external trauma information, based on the vital sign data and external trauma information, through the second injury level recognition model, the injury level of the any patient is identified. Among them, the second injury level recognition model is a neural network model trained in combination with the second loss function and used to identify the injury level based on the characteristics of vital sign data and external trauma information.

[0065] In one embodiment, please refer to Figure 2 , based on the vital sign data and external trauma information, through the second injury level recognition model, the injury level of the any patient is identified, including:

[0066] Step S100, identify the wound type, wound depth, and trauma scope from the trauma image information in the external trauma information.

[0067] Based on the trauma image information, image recognition can be performed to obtain the wound type, wound depth, and trauma scope. Among them, the wound type can include laceration, hemorrhagic trauma, open trauma, etc.

[0068] Step S200, based on the identified wound type, wound depth, and trauma scope, combined with the human body position where the trauma is located and the vital sign data, through the second injury level recognition model, the injury level of the any patient is identified.

[0069] In one embodiment, the training method of the second injury level recognition model includes:

[0070] Step S120, collect the wound type, wound depth, trauma scope, human body position where the trauma is located, and vital sign data of multiple patients, and perform annotation to clarify the injury level.

[0071] Step S220, preprocess the annotated data and convert it into a format suitable for input to the second injury level recognition model to obtain a data set.

[0072] Step S220 may include: cleaning the original data to remove duplicates, errors, and missing values. Then perform normalization or standardization processing to map data of different features to the same scale range to improve the training efficiency and stability of the model.

[0073] Step S320: Divide the data set into a training set, a validation set, and a test set.

[0074] Step S420: Construct the primary architecture of the second injury level recognition model. Based on the preset training parameters, use the training set as the input of the primary architecture of the second injury level recognition model for training. Evaluate the performance of the second injury level recognition model during training based on the validation set and adjust the hyperparameters, and evaluate the generalization ability of the second injury level recognition model based on the test set, so as to obtain the trained second injury level recognition model.

[0075] In one embodiment, the primary architecture of the second injury level recognition model can be constructed based on a multi-branch convolutional neural network (CNN) and a recurrent neural network (RNN).

[0076] In one embodiment, the second loss function can be obtained by weighted summation of the classification loss and various auxiliary losses. Among them, the classification loss function can adopt the cross-entropy loss function, and the auxiliary loss functions can adopt the multi-modal consistency loss function and the position loss function. Introduce auxiliary losses for different modal data in the model to promote the fusion of multi-modal information by the model. For example, for wound features, trauma location features, and vital sign features, calculate their consistency losses in the feature space to enable the model to learn the associations between different modalities. Design a position constraint loss according to the potential relationship between the trauma location and the injury level. For example, traumas at certain key positions may have a greater impact on the injury level, and the loss function is used to constrain the model's learning of this position information.

[0077] Thus, since the vital sign data of each patient is collected based on the intelligent wearable device, and the external trauma information of patients with external traumas is collected based on the image acquisition device, for any patient, based on the collected vital sign data, or, the vital sign data and external trauma information, perform injury analysis to obtain the injury level, so that the injury level of each patient can be obtained more accurately. Thus, patients with a higher injury level can be given priority treatment, reducing the situation where patients with more serious conditions cannot receive timely treatment and their conditions are delayed. For patients with a lower injury level who do not meet the requirements for timely treatment or hospital treatment, the waste of medical resources can be reduced.

[0078] The applicant also found in the research that in sudden mass incidents, especially in car accident incidents, among the individual objects involved, some initially have stable vital sign data and it is difficult to find traumas on the body surface. However, as time goes by, it will endanger life, but is confused by the initial appearance and ignored, resulting in irreparable situations.

[0079] In view of this, for patients whose injury level does not reach the preset injury level, within the preset time period, continuously collect the vital sign data of the patients and obtain the injury level. If the injury level still does not reach the preset injury level when the collection duration meets the preset time period, then use the highest injury level obtained within the preset time period as the highest injury level for treatment.

[0080] For example, generally, yellow can be used as the preset injury level. For any patient, if the injury level obtained by analyzing the uploaded vital sign data, or the vital sign data and external trauma information, reaches yellow, corresponding treatment measures can be taken immediately (such as performing corresponding first aid on the spot immediately or sending the patient to the hospital for treatment). If the injury level obtained by analysis does not reach yellow, continuously collect the vital sign data within the preset time period and further analyze and obtain the injury level in real time. Once the preset injury level is reached, it is understood that treatment measures are taken to reduce the situation of being confused by the initial appearance and ignored.

[0081] Those skilled in the art can understand that the preset time period can be set according to actual needs. For example, it can be set to half an hour, one hour, etc.

[0082] In one embodiment, for patients whose injury level reaches the preset injury level, an alarm prompt is given to remind medical staff to take treatment measures in time.

[0083] Those skilled in the art can understand that in the case of extremely scarce medical resources, red can also be used as the preset injury level.

[0084] Step S50, for any patient with multiple external traumas, obtain the ranking of the severity of external traumas based on the external trauma information, and perform priority-based treatment according to the ranking of the severity of external traumas.

[0085] In one embodiment, for any patient with multiple external traumas, obtaining the ranking of the severity of external traumas based on the external trauma information includes: based on the trauma image information and the human body position information where the trauma is located, through the trauma severity recognition model, recognize the severity of each trauma. Among them, the trauma severity recognition model is a neural network model trained in combination with the third loss function and used to recognize the trauma severity based on the characteristics of the trauma image information and the human body position information where the trauma is located.

[0086] In one embodiment, please refer to Figure 3 , based on the trauma image information and the human body position information where the trauma is located, through the trauma severity recognition model, recognize the severity of each trauma, including:

[0087] Step S1000: For any trauma, identify the wound type, wound depth, and trauma scope from the trauma image information in the external trauma information.

[0088] Based on the trauma image information, image recognition can be performed to obtain the wound type, wound depth, and trauma scope. Among them, the wound type can include laceration, hemorrhagic trauma, open trauma, etc.

[0089] Step S2000: Based on the identified wound type, wound depth, and trauma scope, combined with the human body location where the trauma is located, use the trauma severity recognition model to identify the trauma severity of any one of the traumas.

[0090] In one embodiment, the training method of the trauma severity recognition model may include:

[0091] Step S130: Collect the wound type, wound depth, trauma scope, human body location where the trauma is located, and vital sign data of multiple patients, and perform annotation to clarify the trauma severity level.

[0092] Professional medical personnel grade and annotate the trauma severity according to clinical standards and experience, such as mild, moderate, and severe.

[0093] Step S230: Preprocess the annotated data and convert it into a format suitable for input to the trauma severity recognition model to obtain a data set.

[0094] In one embodiment, convert categorical data such as wound type and trauma location into numerical codes for convenient model processing. Perform normalization processing on numerical data such as wound depth and trauma scope, such as using min - max normalization to scale the data to the [0, 1] interval.

[0095] Step S230 may include: cleaning the original data to remove duplicate, incorrect, and missing values. Then perform normalization or standardization processing to map data of different features to the same scale range to improve the training efficiency and stability of the model.

[0096] Step S330: Divide the data set into a training set, a validation set, and a test set.

[0097] Step S430: Build the primary architecture of the trauma severity recognition model. Based on the preset training parameters, use the training set as the input of the primary architecture of the trauma severity recognition model for training. Evaluate the performance of the trauma severity recognition model during training based on the validation set and adjust the hyperparameters, and evaluate the generalization ability of the trauma severity recognition model based on the test set, so as to obtain a trained trauma severity recognition model.

[0098] Among them, the primary architecture of the trauma severity recognition model can be constructed based on the fully connected network and the convolutional neural network. The feature vectors of wound type, depth, range and wound location are spliced ​​in the input layer or hidden layer, allowing the model to learn multiple features at the same time and capture spatial features based on the convolutional neural network.

[0099] In one embodiment, the third loss function may adopt a cross entropy loss function.

[0100] Step S3000, sorting the severity of external injuries based on the identified severity of each injury.

[0101] In one embodiment, injuries of the same severity level but in different locations are ranked according to their impact, for example, head injuries are more severe than injuries near organs, and injuries near organs are more severe than bone injuries.

[0102] In this way, for any patient with multiple external traumas, the severity ranking of the external traumas is obtained based on the external trauma information, and priority treatment is performed based on the severity ranking of the external traumas. This allows for a more accurate determination of the areas that require priority treatment when a patient has multiple diseases or traumas, thereby reducing the situation where more serious traumas cannot be treated in time and the condition is delayed.

[0103] In one embodiment of the present application, a computer-readable storage medium is provided, on which a program is stored. The stored program includes a method that can be loaded by a processor and process any of the above embodiments.

[0104] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0105] The above uses specific examples to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art to which the present invention pertains, based on the idea of the present invention, several simple deductions, deformations or substitutions can also be made.

Claims

1. A rapid triage method for sudden mass incidents, characterized in that, include: Collect the identity information of each patient; Collect each patient's vital signs data based on smart wearable devices, and associate the collected vital signs data with identity information and upload them; Collecting external trauma information of patients with external trauma based on an image acquisition device, and associating the collected external trauma information with identity information and uploading the information; the external trauma information includes trauma image information and the human body location where the trauma is located; For any patient, based on the collected vital signs data, or vital signs data and external trauma information, injury analysis is performed to obtain the injury level; priority is determined based on the injury level of each patient; For any patient with multiple external injuries, the severity ranking of external injuries is obtained based on the external injury information, including: For any wound, the wound image information in the external wound information is identified to obtain the wound type, wound depth and wound range; Based on the identified wound type, wound depth and wound range, combined with the human body location of the wound, the severity of the wound of any one of the wounds is identified; Based on the severity of each identified injury, the severity of external injuries is ranked; Prioritization is performed based on this external trauma severity ranking; Among them, for traumas of the same severity level but in different locations, the severity of head trauma is higher than that of trauma near organs, and the severity of trauma near organs is higher than that of bone trauma.

2. The rapid triage method for sudden mass incidents according to claim 1, wherein The injury analysis for any patient based on the collected vital sign data, or the vital sign data and external trauma information, to obtain the injury level includes: For any patient, when the collected data only includes vital signs data, the injury level of the patient is identified based on the vital signs data through the first injury level identification model; the first injury level identification model is a neural network model trained in combination with the first loss function, which identifies the injury level based on the characteristics of the vital signs data.

3. The rapid triage method for sudden mass incidents according to claim 1, characterized in that The injury analysis for any patient based on the collected vital sign data, or the vital sign data and external trauma information, to obtain the injury level includes: For any patient, when the collected data includes vital signs data and external trauma information, the injury level of the patient is identified based on the vital signs data and the external trauma information through a second injury level identification model; the second injury level identification model is a neural network model trained in combination with the second loss function, which identifies the injury level based on the characteristics of the vital signs data and the external trauma information.

4. The rapid triage method for sudden mass incidents according to claim 3, characterized in that, The identification of the injury level of any patient based on the vital sign data and external trauma information through the second injury level identification model includes: Identify the wound image information in the external wound information to obtain the wound type, wound depth and wound range; Based on the identified wound type, wound depth and trauma range, combined with the human body location of the trauma and vital signs data, the injury level of any patient is identified through the second injury level identification model.

5. The rapid triage method for sudden mass incidents according to any one of claims 1 to 4, characterized in that, The injury levels from high to low include red, yellow, green, and black, where red indicates life-threatening and immediate emergency treatment is required; yellow indicates severe injury but no life threat; green indicates minor injury with stable vital signs; black indicates death or irreversible condition.

6. The rapid triage method for sudden mass incidents according to any one of claims 1 to 4, characterized in that, For patients whose injury levels do not reach the preset injury level, within the preset time period, continuously collect the vital sign data of the patients and obtain the injury level. If the preset injury level is still not reached when the collection duration meets the preset time period, then use the highest injury level obtained within the preset time period as the highest injury level.

7. The rapid triage method for sudden mass incidents according to claim 6, wherein For patients whose injury levels reach the preset injury level, give an alarm prompt.

8. The rapid triage method for sudden mass incidents according to claim 1, wherein For any patient with multiple external traumas, obtain the ranking of the severity of external traumas based on the external trauma information, including: Based on the trauma image information and the human body position information where the trauma is located, through the trauma severity recognition model, recognize the trauma severity of each trauma; the trauma severity recognition model is a neural network model trained in combination with the third loss function and used to recognize the trauma severity based on the characteristics of the trauma image information and the human body position information where the trauma is located.

9. The rapid triage method for sudden mass incidents according to claim 8, wherein, The method of recognizing the trauma severity of each trauma based on the trauma image information and the human body position information where the trauma is located through the trauma severity recognition model includes: For any one trauma, recognize the wound type, wound depth, and trauma range from the trauma image information in the external trauma information; Based on the recognized wound type, wound depth, and trauma range, combined with the human body position where the trauma is located, through the trauma severity recognition model, recognize the trauma severity of the said any one trauma; Based on the recognized trauma severity of each trauma, conduct a ranking of the severity of external traumas.

10. A computer-readable storage medium, characterized in that, The medium stores a program that can be loaded and executed by a processor to perform the rapid triage and classification method for sudden mass incidents as described in any one of claims 1 to 9.

Images