Wound nursing data intelligent analysis method, device, equipment and medium

Abstract

The invention relates to the technical field of medical data processing, and provides a wound nursing data intelligent analysis method and device, equipment and a medium, and the method comprises the steps: carrying out the preprocessing of wound nursing data collected by a medical sensor, and obtaining a data subset; acquiring a multi-source medical data set of other medical devices of the patient; processing various medical data through a wound feature extraction model to obtain a feature data set; fusing the feature data; generating severity and type of trauma assessment information based on the fusion data and the trauma assessment model set; and generating a personalized wound nursing scheme in combination with the wound nursing data, the evaluation model set and the evaluation information. The accuracy and efficiency of wound nursing can be improved.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing technology, and more specifically, to a method, device, equipment and medium for intelligent analysis of trauma care data. Background Art

[0002] In the field of modern medicine, trauma care is a crucial link. Its purpose is to promote patient recovery and reduce complications through accurate assessment and effective care of the patient's trauma. With the continuous development of medical technology, medical sensors and various medical devices are widely used in the monitoring and data collection of trauma patients. These devices can collect patients' physiological parameters, trauma site information and related data during treatment in real time, providing medical personnel with rich information resources. However, these data come from a wide range of sources, in various formats and in large amounts. How to effectively integrate and analyze these multi-source data to generate accurate trauma assessments and personalized care plans has become a major challenge facing current medical informatization.

[0003] Existing trauma care data processing methods mainly rely on the analysis of a single data source, such as physiological data or imaging examination results collected only by medical sensors. Although these methods can reflect the patient's trauma condition to a certain extent, due to the lack of comprehensive analysis of multi-source data, they are often unable to fully assess the severity and complexity of the patient's trauma. In addition, traditional trauma assessment methods mainly rely on the experience and subjective judgment of medical staff, lack objective and quantitative assessment criteria, and easily lead to inconsistency and deviation in assessment results. In the process of formulating trauma care plans, it is often impossible to provide targeted and personalized care measures due to the lack of accurate grasp of the patient's trauma condition.

[0004] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: first, the prior art cannot effectively integrate multi-source data from different medical devices, resulting in low data utilization and failure to give full play to the advantages of multi-source data; second, there is a lack of objective quantitative methods for trauma assessment, and it relies on the experience and judgment of medical staff, which is prone to subjectivity and inconsistency in the assessment results; finally, the existing trauma care plan formulation process lacks accurate analysis of the patient's trauma condition, making it difficult to generate personalized and targeted care plans, and unable to meet the actual needs of different patients. Summary of the invention

[0005] The present invention provides a method, device, equipment and medium for intelligent analysis of trauma nursing data.

[0006] In a first aspect of the present invention, a method, apparatus, device and medium for intelligent analysis of wound care data are provided, including:

[0007] Performing data preprocessing on the pre-collected trauma care data to obtain a data subset, wherein the trauma care data is data collected by a medical sensor based on the patient's trauma condition and the data accuracy meets the first condition;

[0008] For each piece of patient information in the patient information set corresponding to the data subset, obtaining a multi-source medical data set collected by other medical devices for the patient corresponding to the patient information and having data accuracy that meets different second conditions;

[0009] For each multi-source medical data set in the obtained multi-source medical data set group, each type of medical data in the multi-source medical data set is input into a pre-trained trauma feature information extraction model to obtain a feature data set;

[0010] For each feature data set in the obtained feature data set group, performing feature data fusion on each feature data in the feature data set to obtain fused feature data;

[0011] For each fused feature data in the obtained fused feature data set, generating, according to the fused feature data and the trauma assessment model set, the severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and the type information of each trauma assessment information in the trauma assessment information set;

[0012] A trauma care plan for the patient is generated according to the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

[0013] Further, the preprocessing of the wound care data to obtain a data subset includes: extracting key feature information of the wound care data;

[0014] Preprocessing the trauma care data according to the key feature information to obtain a preprocessed data set;

[0015] Preprocessed data satisfying a third condition is screened out from the preprocessed data set as a data subset to obtain the data subset.

[0016] Further, the generating of the patient's trauma care plan according to the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group includes: generating the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set corresponding to the trauma care data and the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set according to the trauma care data and the trauma assessment model set;

[0017] A trauma care plan for the patient is generated based on the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set, the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set, the severity of each trauma assessment information in the trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

[0018] Further, the generating, based on the trauma care data and the trauma assessment model set, the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set corresponding to the trauma care data and the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set includes: obtaining the priority of each trauma assessment model in the trauma assessment model set;

[0019] Selecting a trauma assessment model whose priority satisfies a fourth condition from the trauma assessment model set as a target trauma assessment model;

[0020] Inputting the trauma care data into a pre-trained target trauma assessment model to obtain severity of each first trauma assessment information in the first trauma assessment information set and type information of each first trauma assessment information in the first trauma assessment information set;

[0021] Inputting the trauma care data into each trauma assessment model in at least one trauma assessment model in the trauma assessment model set to output the severity of each second trauma assessment information in the second trauma assessment information set and the type information of each second trauma assessment information in the second trauma assessment information set, thereby obtaining the severity of each second trauma assessment information in the second trauma assessment information set group and the type information of each second trauma assessment information in the second trauma assessment information set group, wherein the at least one trauma assessment model is each trauma assessment model in the trauma assessment model set with the target trauma assessment model removed;

[0022] For each severity level of the first trauma assessment information, the following determination step is performed: determining whether there is a severity level that is the same as or similar to the severity level of the first trauma assessment information among the severity levels of the second trauma assessment information;

[0023] In response to determining that there is, selecting a severity that is the same as or close to the severity of the first trauma assessment information from the severity levels of the respective second trauma assessment information as a first target severity level, thereby obtaining at least one first target severity level;

[0024] determining a first number of first target severities corresponding to the at least one first target severity;

[0025] In response to determining that the first number is greater than or equal to a predetermined threshold, the severity of the first trauma assessment information is determined as the severity of preliminary trauma assessment information, and the type information of the first trauma assessment information is determined as the type information corresponding to the preliminary trauma assessment information.

[0026] Further, generating the severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and the type information of each trauma assessment information in the trauma assessment information set according to the fused feature data and the trauma assessment model set includes: inputting the fused feature data into a pre-trained target trauma assessment model to obtain the severity of each third trauma assessment information in the third trauma assessment information set and the type information of each third trauma assessment information in the third trauma assessment information set;

[0027] Inputting the fused feature data into each trauma assessment model in the at least one trauma assessment model to output the severity of each fourth trauma assessment information in the fourth trauma assessment information set and the type information of each fourth trauma assessment information in the fourth trauma assessment information set, and obtaining the severity of each fourth trauma assessment information in the fourth trauma assessment information set group and the type information of each fourth trauma assessment information in the fourth trauma assessment information set group;

[0028] For each severity level of the third trauma assessment information, the following determination step is performed: determining whether there is a severity level that is the same as or similar to the severity level of the third trauma assessment information among the severity levels of the fourth trauma assessment information;

[0029] In response to determining that there is, selecting a severity that is the same as or close to the severity of each third trauma assessment information from the severity of each fourth trauma assessment information as a second target severity, thereby obtaining at least one second target severity;

[0030] determining a second number of respective second target severities corresponding to the at least one second target severity;

[0031] In response to determining that the second number is greater than or equal to the predetermined threshold, the severity of the third trauma assessment information is determined as the severity of the trauma assessment information, and the type information of the third trauma assessment information is determined as the type information of the corresponding trauma assessment information.

[0032] Further, the generating of the patient's trauma care plan according to the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set, the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set, the severity of each trauma assessment information in the trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group includes: for each preliminary trauma assessment information in the preliminary trauma assessment information, performing the following generating steps to generate the nursing measures corresponding to the preliminary trauma assessment information: determining the type information of the preliminary trauma assessment information;

[0033] Determining the wound site or wound type corresponding to the type information;

[0034] Determine a trauma assessment information set in the trauma assessment information set group corresponding to the trauma site or trauma type as a target trauma assessment information set;

[0035] Determining whether there is trauma assessment information in the target trauma assessment information set having the same or related trauma site or trauma type as the preliminary trauma assessment information;

[0036] In response to determining presence, generating a care measure applicable to the patient's injury;

[0037] A trauma care plan for the patient is generated based on the various nursing measures obtained.

[0038] Furthermore, the method further comprises:

[0039] Obtaining the severity of each trauma assessment information corresponding to the trauma care plan;

[0040] According to the severity of each trauma assessment information, determine the trauma that needs to be treated first among the traumas to obtain a priority list;

[0041] Based on the priority list, the wound care regimen is optimized.

[0042] In a second aspect of the present invention, there is provided a device for intelligent analysis of wound care data, comprising:

[0043] A preprocessing unit is configured to perform data preprocessing on the pre-collected wound care data to obtain a data subset, wherein the wound care data is data collected by a medical sensor according to a patient's wound condition and the data accuracy meets a first condition;

[0044] The acquisition unit is configured to acquire, for each patient information in the patient information set corresponding to the data subset, a multi-source medical data set acquired by other medical devices for the patient corresponding to the patient information and having data accuracy meeting different second conditions;

[0045] An input unit is configured to input each type of medical data in the multi-source medical data set into a pre-trained trauma feature information extraction model for each multi-source medical data set in the obtained multi-source medical data set group, to obtain a feature data set;

[0046] A fusion unit is configured to perform feature data fusion on each feature data set in the obtained feature data set group to obtain fused feature data;

[0047] A first generating unit is configured to generate, for each fused feature data in the obtained fused feature data set, severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and type information of each trauma assessment information in the trauma assessment information set according to the fused feature data and the trauma assessment model set;

[0048] The second generating unit is configured to generate a trauma care plan for the patient based on the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

[0049] In a third aspect of the present invention, an electronic device is provided, comprising: at least one processor, a memory and an input-output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute any one of the methods described in the first aspect.

[0050] In a fourth aspect of the present invention, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer executes any one of the methods in the first aspect.

[0051] The above-mentioned embodiments of the present invention have at least the following beneficial effects: the present invention can integrate the wound care data collected by medical sensors and multi-source medical data of other medical devices, and construct more comprehensive patient wound feature information through data preprocessing, feature extraction and fusion processing. Multi-model collaborative analysis based on the wound assessment model set can accurately generate the severity and type of wound assessment information, providing a reliable basis for the formulation of subsequent nursing plans.

[0052] This method can combine the preliminary trauma assessment information with the assessment results after fusion of multi-source data to dynamically generate personalized trauma care plans. Through multi-model priority screening and result verification mechanism, the accuracy of trauma assessment can be improved, while ensuring the scientificity and pertinence of the care plan, and ultimately optimizing clinical decision-making efficiency and patient rehabilitation effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0054] Figure 1 A schematic diagram of a process flow of a method for intelligent analysis of wound care data provided by an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of the structure of a device for intelligent analysis of wound care data provided by an embodiment of the present invention;

[0056] Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0058] Those skilled in the art know that the embodiments of the present invention can be implemented as a device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0059] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0060] Reference below Figure 1 , Figure 1 The figure is a flow chart of a method for intelligent analysis of wound care data provided by an embodiment of the present invention. Figure 1 As shown, a method, device, equipment and medium for intelligent analysis of trauma care data include:

[0061] S1 performs data preprocessing on the pre-collected trauma care data to obtain a data subset, wherein the trauma care data is data collected by a medical sensor based on the patient's trauma condition and the data accuracy meets the first condition;

[0062] S2, for each patient information in the patient information set corresponding to the data subset, obtaining a multi-source medical data set collected by other medical equipment for the patient corresponding to the patient information, the data accuracy of which meets different second conditions;

[0063] S3, for each multi-source medical data set in the obtained multi-source medical data set group, inputting various types of medical data in the multi-source medical data set into a pre-trained trauma feature information extraction model to obtain a feature data set;

[0064] S4, for each feature data set in the obtained feature data set group, performing feature data fusion on each feature data in the feature data set to obtain fused feature data;

[0065] S5, for each fused feature data in the obtained fused feature data set, generating, according to the fused feature data and the trauma assessment model set, the severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and the type information of each trauma assessment information in the trauma assessment information set;

[0066] S6 generates a trauma care plan for the patient according to the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

[0067] It should be noted that the present invention proposes a method, device, equipment and medium for intelligent analysis of trauma care data, the core of which is to perform data preprocessing on pre-collected trauma care data to obtain a data subset. The trauma care data here refers to the data collected by medical sensors based on the patient's trauma condition. The accuracy of these data needs to meet certain conditions to ensure its reliability and effectiveness. The purpose of data preprocessing is to extract useful information from the original data, remove noise and redundant data, and thus improve the efficiency and accuracy of subsequent analysis. In this way, a high-quality data foundation can be provided for subsequent multi-source medical data fusion and trauma assessment.

[0068] Specifically, a data subset refers to a data set that meets specific conditions selected from the preprocessed data. These conditions can be set according to actual needs, such as data integrity and relevance. For each patient's information, it is also necessary to obtain a multi-source medical data set collected by other medical devices. The accuracy of this data may vary depending on the type of equipment and the purpose of collection. Multi-source medical data sets include but are not limited to physiological parameters, imaging data, laboratory test results, etc., which can reflect the patient's trauma from different angles. By inputting these multi-source medical data into a pre-trained trauma feature information extraction model, a feature data set can be obtained. The function of this model is to extract feature information related to trauma from complex medical data for more accurate subsequent analysis and evaluation.

[0069] Preferably, the construction of the trauma feature information extraction model can be achieved through machine learning or deep learning algorithms, such as convolutional neural networks (CNN) or long short-term memory networks (LSTM), which can automatically learn feature patterns in data. In terms of input parameters, the model needs to receive preprocessed multi-source medical data, which may include time series data (such as physiological parameters such as heart rate and blood pressure) and static data (such as imaging examination results). During the data preprocessing process, the data can be normalized to eliminate the dimensional differences between different data sources, while removing outliers and missing values ​​to ensure the integrity and consistency of the data. In addition, the feature data fusion step can use weighted averaging, principal component analysis (PCA) and other methods to effectively integrate feature data from different sources to generate fused feature data, providing more comprehensive input information for trauma assessment.

[0070] More specifically, the first condition refers to the specific standards that the trauma care data collected by medical sensors must meet in terms of accuracy, which is used to measure the reliability and validity of the data. In practical applications, it can be set as physiological parameter data collected by medical sensors, such as heart rate, blood pressure, etc., and its measurement error must be controlled within a certain range, for example, the heart rate measurement error does not exceed ±2 times / minute, and the blood pressure measurement error does not exceed ±5mmHg for systolic pressure and ±3mmHg for diastolic pressure. The first condition is to ensure that the subsequent analysis and evaluation based on these data can accurately reflect the patient's trauma. If the data accuracy is not up to standard, it may lead to deviations in the trauma assessment and affect the formulation of subsequent care plans.

[0071] The second condition is the requirements for data accuracy of multi-source medical data sets collected by other medical devices. Due to the different types of equipment and collection purposes, the data accuracy requirements are also different from the first condition of medical sensor data collection. Taking imaging equipment as an example, for X-ray images of fracture trauma, the image resolution must be able to clearly display key information such as fracture lines and bone fragment locations, such as a resolution of no less than 300dpi, and the grayscale value of the image must accurately reflect the density differences between bones and surrounding tissues. For laboratory test data, such as white blood cell counts in routine blood tests, the detection error must be controlled within the allowable range, for example, the error should not exceed ±0.5×10 9 / L. Because different medical devices have different functions and uses, only when the corresponding data accuracy is met can valuable information be provided for multi-source data fusion and trauma assessment.

[0072] In some embodiments, the preprocessing of the wound care data to obtain a data subset includes: extracting key feature information of the wound care data;

[0073] Preprocessing the trauma care data according to the key feature information to obtain a preprocessed data set;

[0074] Preprocessed data satisfying a third condition is screened out from the preprocessed data set as a data subset to obtain the data subset.

[0075] It should be noted that the present invention further refines the process of data preprocessing for trauma care data. Specifically, the goal of data preprocessing is to extract key feature information from the original trauma care data, and screen and process the data based on these key features, and finally obtain a data subset that meets specific conditions. The key feature information here refers to the core data that can effectively reflect the patient's trauma condition, such as trauma site, trauma degree, changes in physiological parameters, etc. By extracting and analyzing these key features, data that is valuable for trauma assessment can be more accurately screened out, thereby improving the efficiency and accuracy of the entire analysis method.

[0076] Specifically, extracting key feature information of trauma care data refers to identifying and extracting data features directly related to trauma assessment from the original data. These features may include, but are not limited to, physiological parameters of the trauma site (such as amount of bleeding, degree of pain), trauma type (such as cuts, fractures), and patients' vital signs (such as heart rate, blood pressure). Next, based on the key feature information, preprocessing the trauma care data refers to cleaning, normalizing, denoising and other operations on the data based on the extracted key features to remove irrelevant information and noise data and retain the parts that are useful for trauma assessment. Finally, screening out the preprocessed data that meets the third condition from the preprocessed data set as a data subset means further screening out high-quality data subsets from the preprocessed data based on pre-set screening conditions (such as data integrity, feature relevance, etc.), providing a basis for subsequent multi-source data fusion and trauma assessment.

[0077] The third condition is the screening criteria for selecting data subsets from the preprocessed data set. The data integrity can be set to be above 90%, that is, the proportion of missing values ​​in the data set does not exceed 10%; at the same time, the correlation coefficient of key features is greater than 0.8. For example, the correlation coefficient between the physiological parameters of the trauma site and the severity of the trauma must meet this requirement. When screening data, priority is given to retaining data with high integrity and key features that are closely related to trauma assessment.

[0078] Preferably, the extraction of key feature information can be achieved through feature selection algorithms, such as based on information gain, mutual information and other methods, to select the most valuable features for trauma assessment from a large amount of raw data. During the preprocessing process, the data can be normalized to unify data of different dimensions into the same range, such as normalizing all physiological parameters to the interval [0, 1] to facilitate subsequent analysis. At the same time, a filtering algorithm can be used to remove noise from the data, such as using a low-pass filter to remove high-frequency noise. The setting of the screening conditions can be flexibly adjusted according to actual needs, such as requiring the integrity of the data to reach more than 90%, and the correlation coefficient of the key features to be greater than 0.8, so as to ensure that the screened data subset can effectively support subsequent trauma assessment and nursing plan generation.

[0079] In some embodiments, generating the patient's trauma care plan according to the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group includes: generating the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set corresponding to the trauma care data and the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set according to the trauma care data and the trauma assessment model set;

[0080] A trauma care plan for the patient is generated based on the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set, the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set, the severity of each trauma assessment information in the trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

[0081] It should be noted that the present invention further clarifies how to generate a patient's trauma care plan based on trauma care data and a trauma assessment model set. Specifically, the process includes two main steps: first, generating preliminary trauma assessment information based on trauma care data and a trauma assessment model set, including information on the severity and type of the trauma; second, combining the preliminary trauma assessment information and the trauma assessment information obtained through multi-source medical data fusion to comprehensively generate a patient's trauma care plan. The preliminary trauma assessment information here refers to the preliminary trauma assessment results based on a single data source (such as trauma care data), while the trauma assessment information set refers to a more comprehensive trauma assessment result obtained through multi-source data fusion. By combining these two parts of information, a more accurate and personalized trauma care plan can be generated.

[0082] Specifically, trauma care data refers to patient trauma-related data collected by medical sensors, which can provide basic information for trauma assessment after preprocessing. The trauma assessment model set is a set of pre-trained models used to assess the severity and type of trauma. These models may include models based on statistical analysis, machine learning models, or deep learning models. When generating preliminary trauma assessment information, the trauma care data is input into the trauma assessment model set to obtain preliminary trauma severity and type information. The trauma assessment information set group is a more comprehensive trauma assessment result obtained through the fusion of multi-source medical data. These results include feature information extracted from multi-source data from different medical devices. By comprehensively considering the preliminary trauma assessment information and the trauma assessment information after the fusion of multi-source data, a trauma care plan that is more in line with the patient's actual situation can be generated.

[0083] Preferably, when generating preliminary trauma assessment information, the models in the trauma assessment model set can be prioritized, and the model with the highest priority can be selected as the target trauma assessment model. For example, the priority can be determined according to performance indicators such as the accuracy and recall rate of the model. After the trauma care data is input into the target trauma assessment model, the first trauma assessment information is obtained, including the severity and type information of the trauma. At the same time, the trauma care data is input into other models in the trauma assessment model set to obtain a second trauma assessment information set group. By comparing the information in the first trauma assessment information and the second trauma assessment information set group, the results with the same or similar severity as the first trauma assessment information are screened out, and their number is counted. If the number reaches a predetermined threshold, the severity and type information of the first trauma assessment information are determined as preliminary trauma assessment information. When generating a trauma care plan, the trauma site or trauma type can be determined according to the type information of the preliminary trauma assessment information, and then the trauma assessment information set related thereto can be found. If there is trauma assessment information with the same or related trauma site or trauma type as the preliminary trauma assessment information in the information set, a nursing measure suitable for the patient is generated. Finally, a trauma care plan for the patient is generated according to all nursing measures.

[0084] In some embodiments, generating, based on the trauma care data and the trauma assessment model set, the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set corresponding to the trauma care data and the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set includes: obtaining the priority of each trauma assessment model in the trauma assessment model set;

[0085] Selecting a trauma assessment model whose priority satisfies a fourth condition from the trauma assessment model set as a target trauma assessment model;

[0086] Inputting the trauma care data into a pre-trained target trauma assessment model to obtain severity of each first trauma assessment information in the first trauma assessment information set and type information of each first trauma assessment information in the first trauma assessment information set;

[0087] Inputting the trauma care data into each trauma assessment model in at least one trauma assessment model in the trauma assessment model set to output the severity of each second trauma assessment information in the second trauma assessment information set and the type information of each second trauma assessment information in the second trauma assessment information set, thereby obtaining the severity of each second trauma assessment information in the second trauma assessment information set group and the type information of each second trauma assessment information in the second trauma assessment information set group, wherein the at least one trauma assessment model is each trauma assessment model in the trauma assessment model set with the target trauma assessment model removed;

[0088] For each severity level of the first trauma assessment information, the following determination step is performed: determining whether there is a severity level that is the same as or similar to the severity level of the first trauma assessment information among the severity levels of the second trauma assessment information;

[0089] In response to determining that there is, selecting a severity that is the same as or close to the severity of the first trauma assessment information from the severity levels of the respective second trauma assessment information as a first target severity level, thereby obtaining at least one first target severity level;

[0090] determining a first number of first target severities corresponding to the at least one first target severity;

[0091] In response to determining that the first number is greater than or equal to a predetermined threshold, the severity of the first trauma assessment information is determined as the severity of preliminary trauma assessment information, and the type information of the first trauma assessment information is determined as the type information corresponding to the preliminary trauma assessment information.

[0092] It should be noted that the present invention further refines the process of how to generate preliminary trauma assessment information based on trauma care data and a trauma assessment model set. By obtaining the priority of each model in the trauma assessment model set and selecting a model whose priority meets specific conditions as the target trauma assessment model, the severity and type of trauma can be assessed more accurately. This method not only takes into account the performance differences of different models, but also further verifies and optimizes the accuracy of the assessment results by comparing the output results of multiple models. Finally, by screening and counting the assessment results that meet the conditions, the preliminary trauma assessment information is determined, providing a reliable basis for the subsequent generation of trauma care plans.

[0093] Specifically, the trauma assessment model set refers to a set of pre-trained models for assessing the severity and type of trauma. These models may be based on different algorithms, such as decision trees, support vector machines (SVMs), neural networks, etc., and each model has its own unique performance characteristics and applicable scenarios. Priority refers to the result of sorting models according to their accuracy, reliability or other performance indicators. Models with higher priorities are generally considered to be more reliable in assessing trauma. The target trauma assessment model is a model selected from the trauma assessment model set whose priority meets specific conditions (such as the highest priority) and is used to preliminarily assess the severity and type of trauma. After the trauma care data is input into the target trauma assessment model, the first trauma assessment information is obtained, including the severity and type information of the trauma. At the same time, the trauma care data is input into other models (i.e., at least one trauma assessment model) in the trauma assessment model set to obtain a second trauma assessment information set. By comparing the severity in the first trauma assessment information and the second trauma assessment information set, the results with the same or similar severity as the first trauma assessment information are screened out, and their number (i.e., the first number) is counted. If the first number is greater than or equal to the predetermined threshold, the severity and type information of the first trauma assessment information is determined as the preliminary trauma assessment information.

[0094] Preferably, the construction of the trauma assessment model set can be achieved by collecting a large amount of historical trauma data and training it using machine learning or deep learning algorithms. For example, a convolutional neural network (CNN) can be used to process imaging data, or a recurrent neural network (RNN) can be used to process time series data. During the model training process, the input parameters may include the patient's physiological parameters (such as heart rate, blood pressure), image data of the trauma site, laboratory test results, etc. For the setting of model priority, the model can be sorted according to performance indicators such as accuracy and recall rate on the validation set. For example, the model with the highest priority may be the model with the highest accuracy. During the screening and statistical process, a similarity threshold can be set, for example, the difference in severity is considered to be the same or similar within a certain range (such as ±10%). The predetermined threshold can be set according to actual needs, for example, it is set to 3, indicating that the result is determined as preliminary trauma assessment information only when the evaluation results of at least 3 models are consistent with the results of the target model.

[0095] The fourth condition is used to select the target trauma assessment model from the trauma assessment model set, based on the priority setting of the model. It can be defined as selecting the model with the highest priority from the trauma assessment model set as the target trauma assessment model. The model priority can be determined by sorting the model based on performance indicators such as accuracy and recall rate on a large number of historical trauma data validation sets. For example, in the validation of 1,000 trauma cases, models with an accuracy rate of more than 90% and a recall rate of more than 85% are arranged in order from high to low, and the model ranked first is selected as the target trauma assessment model that meets the fourth condition.

[0096] In some embodiments, generating the severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and the type information of each trauma assessment information in the trauma assessment information set according to the fused feature data and the trauma assessment model set includes: inputting the fused feature data into a pre-trained target trauma assessment model to obtain the severity of each third trauma assessment information in the third trauma assessment information set and the type information of each third trauma assessment information in the third trauma assessment information set;

[0097] Inputting the fused feature data into each trauma assessment model in the at least one trauma assessment model to output the severity of each fourth trauma assessment information in the fourth trauma assessment information set and the type information of each fourth trauma assessment information in the fourth trauma assessment information set, and obtaining the severity of each fourth trauma assessment information in the fourth trauma assessment information set group and the type information of each fourth trauma assessment information in the fourth trauma assessment information set group;

[0098] For each severity level of the third trauma assessment information, the following determination step is performed: determining whether there is a severity level that is the same as or similar to the severity level of the third trauma assessment information among the severity levels of the fourth trauma assessment information;

[0099] In response to determining that there is, selecting a severity that is the same as or close to the severity of each third trauma assessment information from the severity of each fourth trauma assessment information as a second target severity, thereby obtaining at least one second target severity;

[0100] determining a second number of respective second target severities corresponding to the at least one second target severity;

[0101] In response to determining that the second number is greater than or equal to the predetermined threshold, the severity of the third trauma assessment information is determined as the severity of the trauma assessment information, and the type information of the third trauma assessment information is determined as the type information of the corresponding trauma assessment information.

[0102] It should be noted that the present invention further refines the process of how to generate trauma assessment information based on the fused feature data and the trauma assessment model set. By inputting the fused feature data into the pre-trained trauma assessment model, more accurate trauma assessment results can be obtained, including information on the severity and type of trauma. In addition, by comparing the output results of multiple models, the accuracy of the assessment results is further verified and optimized. This method not only makes full use of the advantages of multi-source data fusion, but also improves the reliability of the assessment results by comparing multiple models, providing a more accurate basis for the subsequent generation of trauma care plans.

[0103] Specifically, the fused feature data refers to data that has been fused and processed. These data integrate feature information from multi-source data from different medical devices and can more comprehensively reflect the patient's trauma. The trauma assessment model set is a set of pre-trained models used to assess the severity and type of trauma. These models may be based on different algorithms, such as decision trees, support vector machines (SVMs), neural networks, etc. Each model has its own unique performance characteristics and applicable scenarios. The target trauma assessment model is a model selected from the trauma assessment model set that meets specific conditions in priority and is used to preliminarily assess the severity and type of trauma. After the fused feature data is input into the target trauma assessment model, the third trauma assessment information is obtained, including the severity and type information of the trauma. At the same time, the fused feature data is input into other models (i.e., at least one trauma assessment model) in the trauma assessment model set to obtain a fourth trauma assessment information set. By comparing the severity in the third trauma assessment information and the fourth trauma assessment information set, the results with the same or similar severity as the third trauma assessment information are screened out, and their number (i.e., the second number) is counted. If the second number is greater than or equal to the predetermined threshold, the severity and type information of the third trauma assessment information is determined as the final trauma assessment information.

[0104] Preferably, the construction of the trauma assessment model set can be achieved by collecting a large amount of historical trauma data and training it using machine learning or deep learning algorithms. For example, a convolutional neural network (CNN) can be used to process imaging data, or a recurrent neural network (RNN) can be used to process time series data. During the model training process, the input parameters may include the patient's physiological parameters (such as heart rate, blood pressure), image data of the trauma site, laboratory test results, etc. For the setting of model priority, the model can be sorted according to performance indicators such as accuracy and recall rate on the validation set. For example, the model with the highest priority may be the model with the highest accuracy. During the screening and statistical process, a similarity threshold can be set, for example, the difference in severity is considered to be the same or similar within a certain range (such as ±10%). The predetermined threshold can be set according to actual needs, for example, it is set to 3, indicating that when the evaluation results of at least 3 models are consistent with the results of the target model, the result is determined as the final trauma assessment information. In addition, in the process of feature data fusion, weighted average, principal component analysis (PCA) and other methods can be used to effectively integrate feature data from different sources to generate fused feature data, providing more comprehensive input information for trauma assessment.

[0105] In some embodiments, generating the patient's trauma care plan according to the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set, the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set, the severity of each trauma assessment information in the trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group includes: for each preliminary trauma assessment information in the preliminary trauma assessment information, performing the following generating steps to generate a nursing measure corresponding to the preliminary trauma assessment information: determining the type information of the preliminary trauma assessment information;

[0106] Determining the wound site or wound type corresponding to the type information;

[0107] Determine a trauma assessment information set in the trauma assessment information set group corresponding to the trauma site or trauma type as a target trauma assessment information set;

[0108] Determining whether there is trauma assessment information in the target trauma assessment information set having the same or related trauma site or trauma type as the preliminary trauma assessment information;

[0109] In response to determining presence, generating a care measure applicable to the patient's injury;

[0110] A trauma care plan for the patient is generated based on the various nursing measures obtained.

[0111] It should be noted that the present invention further clarifies how to generate a patient's trauma care plan based on the preliminary trauma assessment information and the trauma assessment information after fusion of multi-source data. The core of this process is to comprehensively consider the preliminary trauma assessment information and the trauma assessment information after fusion of multi-source data, and generate targeted and personalized nursing measures by analyzing the trauma type, trauma site and related assessment information. This method can make full use of the advantages of multi-source data to ensure the scientificity and effectiveness of the nursing plan, thereby better meeting the rehabilitation needs of patients.

[0112] Specifically, preliminary trauma assessment information refers to the trauma severity and type information initially generated based on trauma care data and trauma assessment model sets. This information provides a basic basis for the formulation of trauma care plans. Trauma assessment information set groups refer to more comprehensive trauma assessment results obtained through the fusion of multi-source medical data. These results include feature information extracted from multi-source data from different medical devices, which can more accurately reflect the patient's trauma condition. The target trauma assessment information set refers to a set of trauma assessment information related to the preliminary trauma assessment information. Through comparison and screening, trauma assessment information with the same or related trauma sites or trauma types as the preliminary trauma assessment information can be found. Based on this information, nursing measures suitable for patients can be generated, and ultimately a complete trauma care plan can be formed.

[0113] Preferably, in the process of generating a trauma care plan, the nursing measures corresponding to each preliminary trauma assessment information can be further refined. First, the trauma site or trauma type is determined according to the type information of the preliminary trauma assessment information. For example, if the preliminary trauma assessment information shows a fracture, the trauma site is determined to be a bone. Next, the trauma assessment information related to the trauma site or trauma type is screened out from the trauma assessment information set group as the target trauma assessment information set. For example, if the trauma site is the leg, the target trauma assessment information set may include leg imaging examination results, related physiological parameters, etc. Then, analyze whether there is trauma assessment information with the same or related trauma site or trauma type as the preliminary trauma assessment information in the target trauma assessment information set. For example, if the imaging examination results of a leg fracture in the target trauma assessment information set are consistent with the preliminary trauma assessment information, then nursing measures suitable for the patient are generated, such as fixation, analgesia, rehabilitation training, etc. Finally, a trauma care plan for the patient is generated based on all nursing measures to ensure the pertinence and personalization of the nursing plan.

[0114] In some embodiments, the method further comprises:

[0115] Obtaining the severity of each trauma assessment information corresponding to the trauma care plan;

[0116] According to the severity of each trauma assessment information, determine the trauma that needs to be treated first among the traumas to obtain a priority list;

[0117] Based on the priority list, the wound care regimen is optimized.

[0118] It should be noted that the present invention further expands the optimization steps after the trauma care plan is generated. After the trauma care plan is generated, the severity of the trauma assessment information is obtained, and the traumas that need to be treated first among the various traumas are determined according to these severities to form a priority list. Subsequently, the trauma care plan is optimized according to the priority list to ensure that severe traumas can be treated more efficiently during the actual care process, improve the care effect and the patient's recovery speed. This optimization process reflects the importance of dynamic assessment of the patient's trauma condition and personalized care, and further improves the scientificity and effectiveness of trauma care.

[0119] Specifically, the severity of trauma assessment information refers to the quantitative indicators of the severity of the patient's trauma obtained through the trauma assessment model. These indicators can be numerical, graded or other forms of expression to measure the urgency and severity of the trauma. The priority list is a ranked list generated according to the severity of the trauma assessment information, which clarifies which traumas need to be treated first. For example, the most severe trauma will be at the top of the list. When optimizing the trauma care plan, the order of care measures and resource allocation will be adjusted according to the priority list to ensure that the most serious trauma is given priority. For example, for traumas with high severity, surgery or emergency treatment may be given priority, while for traumas with lower severity, subsequent rehabilitation treatment or observation may be arranged.

[0120] Preferably, when generating a priority list, a severity threshold can be set, for example, the severity can be divided into three levels: high, medium, and low. For traumas with high severity, they are directly included at the top of the priority list; for traumas with medium severity, they are further sorted according to the specific situation; and for traumas with low severity, they are arranged in the follow-up care plan. When optimizing trauma care plans, the allocation of care resources can be adjusted according to the priority list. For example, for traumas with high priority, more medical staff and medical equipment can be deployed to ensure that patients can receive timely and effective treatment. At the same time, for traumas with lower priority, nursing time and resources can be reasonably arranged to avoid waste of resources. In addition, the priority list and care plan can be dynamically adjusted according to the actual situation of the patient and the availability of care resources to adapt to changing care needs.

[0121] The above-mentioned embodiments of the present invention have the following beneficial effects: the present invention can perform fusion analysis based on the wound care data collected by medical sensors and combined with the data of multi-source medical equipment, thereby improving the comprehensiveness and accuracy of wound assessment. Through data preprocessing, feature extraction and multi-model collaborative verification mechanism, the error risk of a single data source can be effectively reduced, while ensuring that key wound feature information is not omitted, providing a more reliable basis for subsequent nursing decisions.

[0122] This method can dynamically generate personalized trauma care plans, and significantly improve the credibility of evaluation results through priority screening and cross-validation of multi-model results. Combining preliminary evaluation with comprehensive judgment after fusion of multi-source data, it can optimize the pertinence and adaptability of nursing measures, ultimately achieving more accurate clinical intervention and improving the utilization efficiency of medical resources.

[0123] like Figure 2 As shown, in some embodiments, a device for intelligent analysis of trauma care data includes:

[0124] The preprocessing unit 201 is configured to perform data preprocessing on the pre-collected wound care data to obtain a data subset, wherein the wound care data is data collected by a medical sensor according to the patient's wound condition and the data accuracy meets the first condition;

[0125] The acquisition unit 202 is configured to acquire, for each patient information in the patient information set corresponding to the data subset, a multi-source medical data set acquired by other medical devices for the patient corresponding to the patient information and having data accuracy meeting different second conditions;

[0126] The input unit 203 is configured to input each type of medical data in the multi-source medical data set into a pre-trained trauma feature information extraction model for each multi-source medical data set in the obtained multi-source medical data set group, so as to obtain a feature data set;

[0127] The fusion unit 204 is configured to perform feature data fusion on each feature data set in the obtained feature data set group to obtain fused feature data;

[0128] The first generating unit 205 is configured to generate, for each fused feature data in the obtained fused feature data set, severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and type information of each trauma assessment information in the trauma assessment information set according to the fused feature data and the trauma assessment model set;

[0129] The second generating unit 206 is configured to generate a trauma care plan for the patient based on the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

[0130] It is understandable that the modules recorded in the trauma care data intelligent analysis device are similar to those in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the intelligent analysis method for wound care data are also applicable to the intelligent analysis device for wound care data and the modules contained therein, and will not be described in detail here.

[0131] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0132] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0133] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0134] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0135] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A method for intelligent analysis of trauma care data, characterized in that: include: Performing data preprocessing on the pre-collected trauma care data to obtain a data subset, wherein the trauma care data is data collected by a medical sensor based on the patient's trauma condition and the data accuracy meets the first condition; For each piece of patient information in the patient information set corresponding to the data subset, obtaining a multi-source medical data set collected by other medical devices for the patient corresponding to the patient information and having data accuracy that meets different second conditions; For each multi-source medical data set in the obtained multi-source medical data set group, each type of medical data in the multi-source medical data set is input into a pre-trained trauma feature information extraction model to obtain a feature data set; For each feature data set in the obtained feature data set group, performing feature data fusion on each feature data in the feature data set to obtain fused feature data; For each fused feature data in the obtained fused feature data set, generating, according to the fused feature data and the trauma assessment model set, the severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and the type information of each trauma assessment information in the trauma assessment information set; A trauma care plan for the patient is generated according to the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

2. The method according to claim 1, characterized in that The preprocessing of the wound care data to obtain a data subset includes: extracting key feature information of the wound care data; Preprocessing the trauma care data according to the key feature information to obtain a preprocessed data set; Preprocessed data satisfying a third condition is screened out from the preprocessed data set as a data subset to obtain the data subset.

3. The method according to claim 1, characterized in that The step of generating a trauma care plan for the patient according to the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group comprises: generating, according to the trauma care data and the trauma assessment model set, the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set corresponding to the trauma care data and the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set; A trauma care plan for the patient is generated based on the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set, the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set, the severity of each trauma assessment information in the trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

4. The method according to claim 3, characterized in that The step of generating, based on the trauma care data and the trauma assessment model set, the severity of each preliminary trauma assessment information in the preliminary trauma assessment information set corresponding to the trauma care data and the type information of each preliminary trauma assessment information in the preliminary trauma assessment information set comprises: obtaining the priority of each trauma assessment model in the trauma assessment model set; Selecting a trauma assessment model whose priority satisfies a fourth condition from the trauma assessment model set as a target trauma assessment model; Inputting the trauma care data into a pre-trained target trauma assessment model to obtain severity of each first trauma assessment information in the first trauma assessment information set and type information of each first trauma assessment information in the first trauma assessment information set; Inputting the trauma care data into each trauma assessment model in at least one trauma assessment model in the trauma assessment model set to output the severity of each second trauma assessment information in the second trauma assessment information set and the type information of each second trauma assessment information in the second trauma assessment information set, thereby obtaining the severity of each second trauma assessment information in the second trauma assessment information set group and the type information of each second trauma assessment information in the second trauma assessment information set group, wherein the at least one trauma assessment model is each trauma assessment model in the trauma assessment model set with the target trauma assessment model removed; For each severity level of the first trauma assessment information, the following determination step is performed: determining whether there is a severity level that is the same as or similar to the severity level of the first trauma assessment information among the severity levels of the second trauma assessment information; In response to determining that there is, selecting a severity that is the same as or close to the severity of the first trauma assessment information from the severity levels of the respective second trauma assessment information as a first target severity level, thereby obtaining at least one first target severity level; determining a first number of first target severities corresponding to the at least one first target severity; In response to determining that the first number is greater than or equal to a predetermined threshold, the severity of the first trauma assessment information is determined as the severity of preliminary trauma assessment information, and the type information of the first trauma assessment information is determined as the type information corresponding to the preliminary trauma assessment information.

5. The method according to claim 4, characterized in that The step of generating the severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and the type information of each trauma assessment information in the trauma assessment information set according to the fused feature data and the trauma assessment model set comprises: inputting the fused feature data into a pre-trained target trauma assessment model to obtain the severity of each third trauma assessment information in the third trauma assessment information set and the type information of each third trauma assessment information in the third trauma assessment information set; Inputting the fused feature data into each trauma assessment model in the at least one trauma assessment model to output the severity of each fourth trauma assessment information in the fourth trauma assessment information set and the type information of each fourth trauma assessment information in the fourth trauma assessment information set, and obtaining the severity of each fourth trauma assessment information in the fourth trauma assessment information set group and the type information of each fourth trauma assessment information in the fourth trauma assessment information set group; For each severity level of the third trauma assessment information, the following determination step is performed: determining whether there is a severity level that is the same as or similar to the severity level of the third trauma assessment information among the severity levels of the fourth trauma assessment information; In response to determining that there is, selecting a severity that is the same as or close to the severity of each third trauma assessment information from the severity of each fourth trauma assessment information as a second target severity, thereby obtaining at least one second target severity; determining a second number of respective second target severities corresponding to the at least one second target severity; In response to determining that the second number is greater than or equal to the predetermined threshold, the severity of the third trauma assessment information is determined as the severity of the trauma assessment information, and the type information of the third trauma assessment information is determined as the type information of the corresponding trauma assessment information.

6. The method according to claim 3, characterized in that The step of generating a trauma care plan for the patient according to the severity of each piece of preliminary trauma assessment information in the preliminary trauma assessment information set, the type information of each piece of preliminary trauma assessment information in the preliminary trauma assessment information set, the severity of each piece of trauma assessment information in the trauma assessment information set group, and the type information of each piece of trauma assessment information in the trauma assessment information set group comprises: for each piece of preliminary trauma assessment information in the preliminary trauma assessment information, performing the following generating steps to generate a nursing measure corresponding to the preliminary trauma assessment information: determining the type information of the preliminary trauma assessment information; Determining the wound site or wound type corresponding to the type information; Determine a trauma assessment information set in the trauma assessment information set group corresponding to the trauma site or trauma type as a target trauma assessment information set; Determining whether there is trauma assessment information in the target trauma assessment information set having the same or related trauma site or trauma type as the preliminary trauma assessment information; In response to determining presence, generating a care measure applicable to the patient's injury; A trauma care plan for the patient is generated based on the various nursing measures obtained.

7. The method according to claim 1, characterized in that The method further comprises: Obtaining the severity of each trauma assessment information corresponding to the trauma care plan; According to the severity of each trauma assessment information, determine the trauma that needs to be treated first among the traumas to obtain a priority list; Based on the priority list, the wound care regimen is optimized.

8. A trauma care data intelligent analysis device, characterized in that: include: A preprocessing unit is configured to perform data preprocessing on the pre-collected wound care data to obtain a data subset, wherein the wound care data is data collected by a medical sensor according to a patient's wound condition and the data accuracy meets a first condition; The acquisition unit is configured to acquire, for each patient information in the patient information set corresponding to the data subset, a multi-source medical data set acquired by other medical devices for the patient corresponding to the patient information and having data accuracy meeting different second conditions; An input unit is configured to input each type of medical data in the multi-source medical data set into a pre-trained trauma feature information extraction model for each multi-source medical data set in the obtained multi-source medical data set group, to obtain a feature data set; A fusion unit is configured to perform feature data fusion on each feature data set in the obtained feature data set group to obtain fused feature data; A first generating unit is configured to generate, for each fused feature data in the obtained fused feature data set, severity of each trauma assessment information in the trauma assessment information set corresponding to the fused feature data and type information of each trauma assessment information in the trauma assessment information set according to the fused feature data and the trauma assessment model set; The second generating unit is configured to generate a trauma care plan for the patient based on the trauma care data, the trauma assessment model set, the severity of each trauma assessment information in the obtained trauma assessment information set group, and the type information of each trauma assessment information in the trauma assessment information set group.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images