Trauma grade evaluation method, equipment and program product

Abstract

The invention relates to the field of intelligent medical treatment, in particular to a trauma grade evaluation method and device and a program product. The method includes: acquiring data of a trauma patient; transmitting the data to an evaluation model to obtain an evaluation result; a training process of the evaluation model comprises the following steps: acquiring a data set and a label of a trauma patient; the data set and the label are output to a neural network to be trained to obtain an evaluation model, parameter updating of the neural network comprises a first updating rule and a second updating rule, the neural network updates parameters by alternately executing the first updating rule and the second updating rule, and when the model performance of the neural network is lower than preset performance, the evaluation model is obtained. And suspending the iteration of the neural network through intermittent control, adjusting the proportion of the execution times of the first updating rule and the second updating parameter rule, and then carrying out iteration until the model is converged or the preset iteration times are executed. According to the method, the trauma degree of the patient can be efficiently and accurately given, and the method has good clinical value.

Description

Technical Field

[0001] The present application relates to the field of intelligent medical treatment, and specifically to a trauma level assessment method, device, program product and computer-readable storage medium. Background Art

[0002] With the rapid development of the transportation and automobile industry and the increase in infrastructure, the incidence of traumatic accidents has also been increasing year by year. Trauma is the main cause of death in people under 45 years old and the main cause of disability in people under 65 years old. Once trauma occurs, the injuries are complex, the disability rate and mortality rate are high, and it brings a heavy burden to society and families. According to epidemiological studies on emergency trauma patients, falling injuries and traffic injuries are the main causes of injury and death. After the trauma occurs, the probability of death risk of patients varies from person to person, and the proportion of patients with multiple injuries is large, which makes it difficult to quickly and accurately judge. If the probability of death risk of patients cannot be predicted quickly, it is possible to over-treat, and the treatment opportunity for curable patients may be missed, resulting in serious consequences. At present, the clinical estimation of the probability of death risk of trauma patients mainly relies on the clinical experience of doctors, and the probability of death risk of trauma patients is estimated based on the effect of medication or initial first aid. It is not only time-consuming, subjective and lagging, but also lacks consistency and accuracy due to individual differences. Summary of the invention

[0003] In view of the above problems, the present invention proposes a method for evaluating the trauma level, which specifically includes: Obtain data on trauma patients; The data is input into the evaluation model to obtain mild, moderate and severe evaluation results; wherein the training process of the evaluation model is: Obtain a dataset and labels of trauma patients; The data set and the label are input into a neural network for training to obtain an evaluation model, wherein the parameter update of the neural network includes a first update rule and a second update rule, and the neural network updates the parameters by alternately executing the first update rule and the second update rule. When the model performance of the neural network is lower than the preset performance, the iteration of the neural network is paused through intermittent control and the ratio of the execution times of the first update rule and the second update parameter rule is adjusted before iterating again until the model converges or the preset number of iterations is executed.

[0004] The first update rule and the second update rule include one or more of the following: batch gradient descent, stochastic gradient descent, momentum update; The first update rule and the second update rule also include rule update and chaos update; the rule update is to adjust parameters through non-gradient parameter update rules and based on Fourier transform; the chaos update is to generate a chaotic sequence through chaotic mapping and map it to the parameters to be updated to obtain updated parameters.

[0005] The chaotic mapping method is expressed as:

[0006] in, For the The chaotic variable of the iteration, For the The chaotic variable of the iteration, is the perturbation intensity; is the order of the chaotic sequence; is the chaos control parameter.

[0007] The training of the neural network also includes parameter optimization, and the parameter optimization algorithms include one or more of the following: ant colony optimization algorithm, genetic annealing algorithm, particle swarm optimization algorithm, whale optimization algorithm, gray wolf optimization algorithm, and Riemann geometry optimization algorithm; wherein the Riemann geometry optimization algorithm is a Riemann metric obtained by the gradient flow of the Riemann manifold in the parameter space, the Riemann gradient is calculated based on the Riemann metric, and then the optimized parameters are obtained by optimizing the parameters through the Riemann gradient.

[0008] The performance of the model is judged by the performance improvement rate. When the performance improvement rate meets the preset performance improvement rate, the model performance is judged to be excellent. When the performance improvement rate meets the preset performance improvement rate, the model performance is judged to be poor. When the model performance is poor, the iteration of the neural network is adjusted through intermittent control. The performance improvement rate is expressed as:

[0009] in, is the performance improvement rate, For the The loss function value of the iteration; For the The performance improvement rate of the iteration, is the performance change smoothing coefficient.

[0010] The method also includes data expansion, inputting the data set into a generative adversarial neural network for data expansion to obtain an expanded data set, and then inputting the expanded data set into the neural network for training; wherein the generator in the generative adversarial neural network adjusts the data by calculating the information entropy of the input data to obtain the adjusted data, and the generator generates data based on the adjusted data.

[0011] The method also includes recommending treatment plans, and providing corresponding treatment plans and treatment costs according to the mild, moderate and severe assessment results; the mild, moderate and severe levels are determined by encoding the data on the degree of trauma and determining the level based on the size of the encoded value.

[0012] An object of the present invention is to provide a computer program product, which includes a computer program or instructions, and the computer program or instructions are executed by a processor to implement the above-mentioned injury level assessment method.

[0013] An object of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program or instructions stored in the memory, wherein the computer program or instructions are executed by the processor to implement the above-mentioned trauma level assessment method.

[0014] An object of the present invention is to provide a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions are executed by a processor to implement the above-mentioned method for assessing the level of trauma.

[0015] Advantages of the present invention: 1. The present invention adaptively adjusts the execution times ratio of multiple parameter finer rules according to the changes in the performance of the neural network model during training of the neural network. This dynamic adjustment mechanism enables the model to better adapt to various data situations during the training process and optimize the network performance.

[0016] 2. The intermittent characteristics of chaotic systems are used in the parameter update rules of neural networks to optimize the weight and bias updates of neural networks. By alternately executing rule updates and chaotic updates, the exploration capability of parameter space is enhanced, helping the neural network avoid local optimality and improving global optimization performance.

[0017] 3. Define the Riemann metric tensor in the parameter space of the neural network, use the concept of Riemannian geometry to optimize the parameters, ensure that the update process follows the steepest descent path, and improve the optimization efficiency and model convergence.

[0018] 4. Generative adversarial networks are used for data augmentation. In the initialization phase of the generative adversarial network, the network parameters of the generator and the discriminator adopt a specific distribution to improve the diversity of the network when it starts, which helps to explore a wider range of data distributions and improve the diversity and quality of generated samples. The information entropy of the data is calculated to enhance the ability of the generative adversarial network to capture the characteristics of complex trauma patient data. By adjusting the information entropy contribution, the model can better adjust the information flow in the trauma patient data, thereby improving the details and quality of the generated data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A schematic flow chart of a method for assessing trauma level provided by an embodiment of the present invention; Figure 2 A schematic diagram of a trauma grade assessment system provided by an embodiment of the present invention; Figure 3 A schematic diagram of a trauma grade assessment device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0022] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The sequence numbers of the operations, such as S101, S102, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0023] Figure 1 A schematic diagram of a method for assessing trauma level provided by an embodiment of the present invention specifically includes: S101: Obtain data on trauma patients; In one embodiment, this embodiment only describes one data modality and data type. For relevant trauma patient data, the sample expansion model and deep learning model training of this application are also applicable. For example, the patient data may also include at least one of patient demographic data, admission diagnosis data, trauma degree data, multiple injury data, past medical history data, clinical treatment data, and surgical condition data. The specific introduction is as follows: Characteristics of patient demographic data, including: age and gender; The characteristic quantities of the admission diagnosis data include: whether the patient was in a coma before admission and the injury mechanism; The characteristic quantities of trauma degree data include: the severity of injury to the patient's fixed part; The characteristic quantities of multiple injury data include: whether the patient has multiple injuries; The characteristic quantities of medical history data include: hypertension, coronary heart disease, diabetes, myocardial infarction, peptic ulcer, anemia, and dyspnea; The characteristic quantities of clinical treatment data include: whether the patient is in a coma, whether he uses a ventilator, whether he needs a blood transfusion, whether he needs to be admitted to the intensive care unit for treatment, and whether he needs to use protein products; The characteristic quantities of surgical data include: surgical type, highest surgical level, number of surgeries, and surgical time.

[0024] Among them, the characteristic quantities of patient demographic data include: patient age, gender, etc.; The characteristic quantities of the patient's demographic data basically include age and gender. If the patient is a pregnant woman, the characteristic quantities of this data may also include the pregnancy status of the pregnant woman.

[0025] The characteristic quantities of the admission diagnosis data included: the patient was comatose before admission (1 = yes, 0 = no); Mechanism of injury (1 = traffic accident, 2 = fall, 3 = fall from height, 4 = being beaten by others, 5 = being assaulted by a sharp object or blunt object); The characteristic quantities of trauma severity data: injury location and severity, where the larger the coding value, the higher the severity of the injury; head injury (0 = no, 1 = first degree, 2 = second degree, 3 = third degree, 4 = fourth degree, 5 = fifth degree); facial injury (0=no, 1=first degree, 2=second degree); Neck injury (0=no, 1=first degree, 2=second degree); chest injury (0=no, 1=first degree, 2=second degree, 3=third degree); abdominal injury (0=no, 1=first degree, 2=second degree, 3=third degree); spinal injury (0=no, 1=first degree, 2=second degree); limb and pelvic ring injuries (0 = no, 1 = first degree, 2 = second degree, 3 = third degree); Characteristic quantity of multiple injury data: whether there is multiple injury (1=yes, 0=no); Characteristic quantities of medical history data: hypertension (1=yes, 0=no), coronary heart disease (1=yes, 0=no), diabetes (1=yes, 0=no), myocardial infarction (1=yes, 0=no), peptic ulcer (1=yes, 0=no), anemia (1=yes, 0=no), dyspnea (1=yes, 0=no), etc. Characteristic quantities of clinical treatment data: whether the patient is in coma (1=yes, 0=no), whether a ventilator is used (1=yes, 0=no), whether a blood transfusion is given (1=yes, 0=no), whether the patient is admitted to the intensive care unit for treatment (1=yes, 0=no), whether protein products are used (1=yes, 0=no), etc. The characteristic quantities of surgical data include: type of surgery, highest surgical level (1=level 1, 2=level 2, 3=level 3, 4=level 4), number of surgeries, surgical time, etc.

[0026] In a specific embodiment, if the collected data has missing values, outliers, etc., it is necessary to implement at least one method of missing value filling, normalization processing or feature transformation.

[0027] Missing value filling: The extracted treatment characteristic records of the patient data may be incomplete. This method is used to interpolate the missing characteristic values, where continuous characteristics are interpolated using the median value and categorical characteristics are interpolated using the highest frequency level.

[0028] Normalization processing: The extracted feature quantities are normalized and used as feature vectors for predicting the patients to be treated.

[0029] Feature transformation: Use transformation functions such as sin and tan to perform nonlinear transformation on the extracted feature quantities.

[0030] In a specific embodiment, as an optional implementation of the present application, the treatment data related to the trauma treatment decision is sorted in chronological order, and further includes: According to the time sequence, the treatment data related to the trauma treatment decision are divided into pre-treatment data and treatment data; The treatment data related to the trauma treatment decision are mainly divided into pre-treatment data and in-treatment data to facilitate observation of the corresponding patient data before and after the development of the disease.

[0031] The pre-treatment data are sorted and marked in chronological order to obtain the pre-treatment data of the patient; When a patient suffers trauma and has not yet received treatment, the patient's data up to the time of treatment can be processed for predictive analysis to obtain the patient's trauma condition progression in the untreated state. For example, the wound may aggravate the infection and cause the patient to remain in a coma. Medical staff can develop a treatment strategy suitable for the patient based on the patient's pre-treatment risk assessment report to minimize the deterioration of the condition.

[0032] The data during treatment are sorted and marked in chronological order to obtain the patient's treatment data.

[0033] After a trauma patient receives treatment, the patient data of the trauma patient will be accumulated and recorded, and the risk assessment report of the trauma patient's in-hospital treatment can be predicted according to a fixed time period. However, it should be noted that if new patient data is added during the treatment process, for example, no surgical treatment was performed before a certain treatment, but surgery is required due to the progression of the disease, then the newly added patient data is the surgical condition data.

[0034] For surgical data, the feature quantities related to the surgical situation are recorded. During the preset period of data extraction, if the newly added patient data is within the preset period, it is also extracted. The extracted data is used for disease risk probability prediction analysis to better meet the patient's disease development.

[0035] In a specific embodiment, as an optional implementation scheme of the present application, it also includes: the disease risk assessment report includes at least one of blood creatinine, urine volume, clinical test report, complications, vital signs, and medical scores.

[0036] In one embodiment, any one of the above-mentioned results can reflect the condition of the trauma patient to a large extent. Any one of the above-mentioned data can be input into a trained evaluation model to roughly determine the severity of the trauma patient's condition and make targeted recommendations on treatment plans for the trauma patient.

[0037] S102: inputting the data into an evaluation model to obtain mild, moderate, and severe evaluation results; Among them, the training process of the evaluation model is: Obtain a dataset and labels of trauma patients; The data set and the label are input into a neural network for training to obtain an evaluation model, wherein the parameter update of the neural network includes a first update rule and a second update rule, and the neural network updates the parameters by alternately executing the first update rule and the second update rule. When the model performance of the neural network is lower than the preset performance, the iteration of the neural network is paused through intermittent control and the ratio of the execution times of the first update rule and the second update parameter rule is adjusted before iterating again until the model converges or the preset number of iterations is executed.

[0038] In one embodiment, the preset performance is the performance in an existing evaluation model or a performance parameter set based on existing experience.

[0039] In one embodiment, the first update rule and the second update rule include one or more of the following: batch gradient descent, stochastic gradient descent, momentum update.

[0040] In one embodiment, the first update rule and the second update rule further include rule update and chaos update; the rule update is to adjust parameters through non-gradient parameter update rules and based on Fourier transform; the chaos update is to generate a chaotic sequence through chaotic mapping and map it to the parameters to be updated to obtain updated parameters.

[0041] The chaotic mapping method is expressed as:

[0042] in, For the The chaotic variable of the iteration, For the The chaotic variable of the iteration, is the perturbation intensity; is the order of the chaotic sequence; is the chaos control parameter.

[0043] In one embodiment, the training of the neural network also includes parameter optimization, and the parameter optimization algorithm includes one or more of the following: ant colony optimization algorithm, genetic annealing algorithm, particle swarm optimization algorithm, whale optimization algorithm, gray wolf optimization algorithm, and Riemann geometry optimization algorithm; wherein the Riemann geometry optimization algorithm is a Riemann metric obtained by the gradient flow of a Riemann manifold in a parameter space, the Riemann gradient is calculated based on the Riemann metric, and then the optimized parameters are obtained by optimizing the parameters through the Riemann gradient.

[0044] In one embodiment, the performance of the model is judged by the performance improvement rate. When the performance improvement rate meets the preset performance improvement rate, the model performance is judged to be excellent. When the performance improvement rate meets the preset performance improvement rate, the model performance is judged to be poor. When the model performance is poor, the iteration of the neural network is adjusted through intermittent control. The performance improvement rate is expressed as:

[0045] in, is the performance improvement rate, For the The loss function value of the iteration; For the The performance improvement rate of the iteration, is the performance change smoothing coefficient.

[0046] In one embodiment, the method also includes data expansion, inputting the data set into a generative adversarial neural network for data expansion to obtain an expanded data set, and then inputting the expanded data set into the neural network for training; wherein the generator in the generative adversarial neural network adjusts the data by calculating the information entropy of the input data to obtain the adjusted data, and the generator generates data based on the adjusted data.

[0047] In one embodiment, the method further includes recommending a treatment plan, and providing a corresponding treatment plan and treatment cost according to the mild, moderate, and severe assessment results; the mild, moderate, and severe levels are determined by encoding the data on the degree of trauma and determining the level based on the size of the coded value.

[0048] In a specific embodiment, the training data of the present invention is derived from the information system related to the hospital emergency center and general wards, including data from medical examination equipment such as X-ray machines, CT scans, and vital signs monitoring equipment. The data collection method adopts real-time digital transmission. The collected data is first transmitted to the data processing center through the internal network, and then converted into a unified JSON format and stored in a highly available distributed file system.

[0049] In a specific embodiment, the collected data is vector data, which may include the following attributes: Ra represents the patient's age, Da represents the patient's gender, Pa represents blood pressure, Ta represents body temperature, Ha represents heart rate, Ba represents respiratory rate, Sa represents blood oxygen saturation, Ia represents injury type, La represents injury location, and Oa represents surgical necessity.

[0050] It should be noted that this embodiment is only used to illustrate one data format and type of the present application. In actual applications, the attributes of the data are usually more than 10 attributes, and the number of attributes of the data may reach dozens or even hundreds.

[0051] Furthermore, the collected data is annotated. The annotating method of the present application is manual annotating. In one embodiment, the annotated categories include different disease levels, such as mild, moderate, and severe. Each level corresponds to a corresponding treatment plan, and each treatment plan includes a corresponding treatment cost assessment interval, such as: Mild: basic treatment, cost range is 1000-3000 yuan; Moderate: Intensive treatment, cost range is 3000-15000 yuan; Severe: Emergency surgery and intensive care, with costs ranging from more than 15,000 yuan.

[0052] In a specific embodiment, in some cases, the collection, acquisition, labeling and preprocessing of training data are time-consuming and labor-intensive, and insufficient training samples can easily lead to poor model generalization ability and affect the accuracy of the model. This application uses a generative adversarial network algorithm to generate samples and thus achieve data expansion. The training process of the generative adversarial network algorithm is as follows: 1. Initialize the network parameters of the generator and discriminator of the generative adversarial network. The generator is responsible for generating realistic trauma patient data, and the discriminator attempts to distinguish the generated trauma patient data from the real trauma patient data. In the initialization stage, the generator and the discriminator The network parameters are randomly set and are expressed as:

[0053]

[0054]

[0055]

[0056] In the formula, is the weight of the generator; is the weight of the discriminator; is the bias of the generator; is the bias of the discriminator; Indicates compliance with a specific distribution; is the output dimension of the generator; is the input dimension of the discriminator; Represents drawing values ​​from a uniform distribution.

[0057] 2. In the adversarial training stage, the generator and the discriminator conduct adversarial training. The generator tries to generate trauma patient data that can deceive the discriminator, and the discriminator strives to identify the generated trauma patient data and the real trauma patient data. In this way, the generator continuously learns how to improve the trauma patient data it generates to make it closer to the distribution of the real trauma patient data set. The adversarial loss function is used to constrain the process in the adversarial training stage. The adversarial loss function is expressed as:

[0058] In the formula, It is a sample of real trauma patient data; The distribution of the real trauma patient dataset; is a random noise distribution; is a random noise distribution Random noise extracted from is used to generate trauma patient data; express expectations; represents the discriminator function; represents a generator function; represents the discriminator; Represents a generator; It means that the loss of the constraint generator is the smallest and the loss of the discriminator is the largest.

[0059] In one embodiment, the decision mode of the discriminator function is expressed as:

[0060] In the formula, is the Sigmoid activation function; for The transpose of is the feature extraction function.

[0061] In this embodiment, the feature extraction function processes complex trauma patient data features through nonlinear transformation, and the implementation is expressed as follows:

[0062] In the formula, is the hyperbolic tangent function; is the first hyperbolic tangent parameter matrix, is the second hyperbolic tangent parameter matrix, and the first hyperbolic tangent parameter matrix and the second hyperbolic tangent parameter matrix are learnable parameter matrices, and parameter learning is performed by gradient descent; yes No. feature components; is the number of components of the feature vector of the real trauma patient data sample, corresponding to the projection dimension of the feature vector of the real trauma patient data sample in the feature space. Preferably, Set to 3.

[0063] In this embodiment, the calculation method of the generator function is expressed as:

[0064] In the formula, It is a stacked nonlinear activation function; is the number of eigenvector components of random noise, corresponding to the projection dimension of the eigenvector of random noise in the feature space; The generator corresponds to The weights of the eigenvector components of the random noise; The generator corresponds to The bias of the eigenvector component of the random noise. Preferably, Set to 3.

[0065] In this embodiment, the stacked nonlinear activation function averages the outputs of all activation functions to generate a more complex and delicate trauma patient data feature simulation. Assuming its input is y_cr, the calculation method is expressed as:

[0066] In the formula, It is the input of the stacked nonlinear activation function; The number of feature vector components that are the input to the stacked nonlinear activation function; is the first feature vector of the input of the cascaded nonlinear activation function Preferably, Set to 3.

[0067] 3. Calculate the information entropy of the data to enhance the ability of the generative adversarial network to capture the data characteristics of complex trauma patients. The calculation method is expressed as:

[0068]

[0069] In the formula, represents the information entropy function based on the second-order entropy contribution; is the composite information entropy function; represents a trauma patient dataset; The data are from the Trauma Patients Dataset; is the probability distribution of trauma patient data in the trauma patient dataset; is the scaling factor that adjusts the information entropy; is the set of noise variables input to the generator; is a coefficient that adjusts the contribution of the second-order entropy and is used to increase the complexity and sensitivity of the calculation to better adjust the information flow in the trauma patient data; is the weight matrix for trauma patient data.

[0070] In one embodiment, for trauma patient data, For The feature set extracted from is the weight matrix for trauma patient data, is the weight matrix of the trauma patient data. elements, corresponding to The Features , the adjustment of the weight matrix for trauma patient data is governed by the following optimization problem:

[0071] In the formula, Indicates that minimize; is the regularization parameter of the weight matrix of the trauma patient data, controlling the sparsity of the weights; are the labels for the training trauma patient data; and They are L1 and L2 norms, which are used to increase the generalization ability of the model and reduce overfitting.

[0072] Furthermore, to solve this optimization problem, the gradient descent method is used to update the weight matrix of trauma patient data, which is expressed as:

[0073] In the formula, For the The weight matrix of the trauma patient data for the iteration; For the The weight matrix of the trauma patient data for the iteration; is the adjusted learning rate of the weight matrix for the trauma patient data; is a sign function. Preferably, Set to 0.01, Set to 0.3.

[0074] 4. Optimize the loss function. The training process of the generator and the discriminator is constrained by a composite loss function to guide the generator to more accurately simulate the intrinsic characteristics and statistical properties of trauma patient data of each modality. The composite loss function uses a square term in a linear form for the adversarial loss term to increase the stability and noise resistance of adversarial learning. The calculation method is expressed as:

[0075] In the formula, is the weight coefficient controlling the adversarial loss; is the weight coefficient that controls the information entropy loss.

[0076] 5. The adversarial training process is iterative until the model converges, that is, the difference between the generated trauma patient data and the real trauma patient data is minimized. During this period, the parameters of the generator and the discriminator are continuously adjusted. The adjustment method is expressed as:

[0077]

[0078] In the formula, Indicates parameter update operation; Represents the parameters of the generator; represents the parameters of the discriminator; is the learning rate of the generative adversarial network; represents the gradient of the generator parameters; represents the gradient of the discriminator parameters.

[0079] In one embodiment, since traditional adversarial training usually uses a fixed learning rate for generating adversarial networks, which may lead to slow or unstable convergence during training, the present application uses a dynamic learning rate adjustment mechanism to dynamically adjust the learning rate according to the loss changes during model training to speed up convergence and improve model stability. The adjustment method is expressed as:

[0080]

[0081] In the formula, is the initial learning rate of the generative adversarial network, For the The learning rate of the generative adversarial network for the iteration; To control the sensitivity parameter of learning rate changes; is the difference between the loss of the previous iteration and the loss of the current iteration, For the The loss of the generative adversarial network at this iteration; For the The loss of the generative adversarial network at the iteration. Preferably, Set to 3.

[0082] 6. Repeat the above steps until the preset stop iteration condition is met, indicating that the model training is completed. In one embodiment, the preset stop iteration condition is reaching a preset maximum number of iterations. Preferably, the preset maximum number of iterations is set to 1000 times.

[0083] After the data expansion model training is completed, the trained data expansion model is used to increase the number of trauma patient samples. In one embodiment, assuming that the original collected trauma patient samples are 800, and the data expansion model expands and generates 200 trauma patient samples, the expanded trauma patient data set contains 1000 samples.

[0084] In a specific embodiment, the expanded set of trauma patients is input into a deep learning model for training the deep learning model. The deep learning model is a neural network model structure, specifically a 6-layer fully connected neural network, and the last layer of the neural network is a Softmax function, which is used to classify the features extracted from the trauma patient data to obtain different disease levels.

[0085] The training process of the fully connected neural network algorithm is as follows: 1. Randomly initialize the weights of the neural network and the bias of the neural network , set the initial number of rule update iterations and the number of chaotic update iterations In one embodiment, in order to increase the diversity of neural network parameter initialization, the combination of Sobol sequence and Halton sequence is used to generate low-discrepancy, high-dimensional initial parameters. Specifically, the Sobol sequence is set to , the Halton sequence is , then the initial weights and biases can be expressed as:

[0086]

[0087] In the formula, is the initial value of the neural network weight parameter; is the initial value of the neural network bias parameter; is the ratio of pi.

[0088] Furthermore, the process of Sobol sequence generation is expressed as:

[0089] In the formula, For the The binary digit of the bit, is the length of the Sobol sequence, For the The decimal value of the digit.

[0090] Furthermore, the calculation method of binary bits is expressed as:

[0091] In the formula, Represents the exclusive OR operation, For the Direction coefficient in each direction; is the number of directions of the binary bit, which is the same as the number of rows in the neural network weight matrix; For the The binary digit of the bit.

[0092] Furthermore, the process of generating Halton sequence is expressed as:

[0093] In the formula, For the prime binary digits; For the prime numbers; is the length of the Halton sequence, which is the same as the number of columns of the neural network weight matrix.

[0094] 2. Update the rules and execute the preset number of times The parameter update rule is based on non-gradient parameter update rules, and the parameter adjustment based on Fourier transform is used to capture the frequency characteristics of the parameter space. The weights and biases of the neural network in the iteration are and , then the rule update is expressed as:

[0095]

[0096] In the formula, and denote Fourier transform and inverse Fourier transform respectively; is the frequency component; For the The weights of the neural network in the intermediate feature domain of the iteration; For the The bias of the neural network in the intermediate feature domain of the iteration; is the first Fourier hyperparameter, is the second Fourier hyperparameter, is the third Fourier hyperparameter, is the fourth Fourier hyperparameter. Preferably, set ,

[0097] Furthermore, the parameters of the neural network in the intermediate feature domain are used to obtain new weights and biases through nonlinear mapping, which can be expressed as:

[0098]

[0099] In the formula, is the hyperbolic tangent function; is a nonlinearity control parameter, preferably, Set to 2.

[0100] 3. After the rules are updated, the chaos update phase begins and the The chaotic parameters are updated by using chaotic mapping to generate chaotic sequences, which are mapped to the parameter adjustment amount to update the weights and biases of the neural network nonlinearly. The chaotic mapping method is expressed as:

[0101] In the formula, For the The chaotic variable of the iteration, the initial value of the chaotic variable Pick The normalized value of For the The chaotic variable of the iteration; is the perturbation intensity; is the order of the chaotic sequence; is the chaos control parameter. Preferably, Set to , Set to 0.01, Set to 3.

[0102] Furthermore, chaotic variables are used to update the weights and biases of the neural network, which can be expressed as:

[0103]

[0104] In the formula, is the chaotic update step size, preferably, Set to 0.05.

[0105] In one embodiment, the calculation method of the initial value of the chaotic variable is expressed as:

[0106] In the formula, Take the maximum value function.

[0107] Furthermore, chaotic variables are used to update the weights and biases of the neural network, and the update method is expressed as:

[0108]

[0109]

[0110] In the formula, For the The adaptive weight coefficient of the iteration, For the Performance improvement rate per iteration; For the The weights of the neural network at the iteration, For the The bias of the neural network at this iteration; is the Riemann gradient learning rate; is the Riemann gradient of the weights of the neural network; is the Riemann gradient of the bias of the neural network; For the The loss function value of the iteration. Preferably, Set to 0.01.

[0111] 4. Using the parameter optimization method based on Riemannian geometry, according to the gradient flow on the Riemannian manifold and the geometric characteristics of the parameter space, the weights and biases of the neural network are optimized. By defining a suitable Riemannian metric in the parameter space, the parameter update process follows the steepest descent path, thereby improving the optimization efficiency and convergence. Specifically, the Riemannian metric tensor of the weights and biases of the neural network is defined in the parameter space, expressed as:

[0112] In the formula, is the Riemann metric tensor of the weights and biases of the neural network, is the first component of the Riemann metric tensor of the neural network weights and biases, is the second component of the Riemann metric tensor of the neural network weights and biases, is the third component of the Riemann metric tensor of the neural network weights and biases, The fourth component of the Riemann metric tensor for the weights and biases of the neural network.

[0113] Furthermore, the calculation method of each component is expressed as:

[0114]

[0115]

[0116] In the formula, is the Riemann regularization parameter; is the identity matrix, whose dimensions are or Preferably, Set to 0.01.

[0117] Furthermore, the Riemannian gradient is calculated on the Riemannian manifold, and the gradient calculation method is expressed as:

[0118]

[0119] In the formula, is the inverse matrix of the metric tensor; is the Riemann gradient of the neural network's loss function with respect to the weights; is the Riemann gradient of the loss function of the neural network with respect to the bias.

[0120] 5. Perform intermittent control and adaptively adjust the network according to the performance changes in the previous iterations and If the network performance is found to be improving slowly, the proportion of chaotic updates is increased to strengthen the exploration of parameter space; otherwise, the number of rule updates is increased to consolidate the existing optimization results. The performance change is measured by the performance improvement rate, which is calculated as follows:

[0121] In the formula, For the The loss function value of the iteration; For the The performance improvement rate of each iteration. is the performance change smoothing coefficient, which is used to smooth the performance to avoid the influence of excessive fluctuations. Set to 0.9.

[0122] Furthermore, the calculation method of the loss function value is expressed as:

[0123] In the formula, The number of samples entered for the current batch; is a neural network function, which obtains the classification label through the Softmax function; is the first input to the neural network samples; is the loss parameter adjustment factor. Preferably, Set to 0.1.

[0124] Furthermore, according to the performance improvement rate, the number of rule update iterations and the number of chaos update iterations are adjusted, which can be expressed as:

[0125] In the formula, Improve thresholds for performance; is the first adjustment step; is the second adjustment step. Preferably, Set to 0.01, Set to 1, Set to 2.

[0126] 6. Repeat the above steps until the preset stop iteration condition is met, indicating that the model training is completed. In one embodiment, the preset stop iteration condition is reaching a preset maximum number of iterations. Preferably, the preset maximum number of iterations is set to 1000 times.

[0127] In a specific embodiment, after the deep learning model for trauma patient condition assessment is trained, the trained deep learning model is used to process new samples to assess the condition of trauma patients and recommend corresponding treatment plans. The newly collected trauma patient data is input into the deep learning model for trauma patient condition assessment, which has been trained and optimized based on a large amount of historical data and can identify and extract the most critical information for condition assessment. The extracted features are classified by the Softmax function of the last layer of the model to obtain the condition level.

[0128] In a specific embodiment, the obtained disease level includes mild, moderate, and severe, each level corresponds to a corresponding treatment plan, and each treatment plan includes a corresponding treatment cost assessment range, such as: Mild: basic treatment, cost range is 1000-3000 yuan; Moderate: Intensive treatment, cost range is 3000-15000 yuan; Severe: Emergency surgery and intensive care, with costs ranging from more than 15,000 yuan.

[0129] In one embodiment, the trauma level assessment process of the present invention is: obtaining trauma data, clinical data, treatment data and other data of trauma patients, and inputting one or more of the above data into a trained assessment model to perform trauma level assessment to obtain an assessment result. According to different data types, different assessment models (and data expansion models) are trained accordingly. For the training of the assessment model, the training process includes any of the following: 1 The iteration of the neural network is controlled by an intermittent control mechanism, and the parameters of the neural network are updated using arbitrary update rules.

[0130] 2 The iteration of the neural network is controlled through an intermittent control mechanism, and the parameters of the neural network are updated using rule update + chaos update.

[0131] 3 The iteration of the neural network is controlled by an intermittent control mechanism. The parameters of the neural network are updated using arbitrary update rules, and the parameter selection is optimized through Riemannian geometry.

[0132] 4 The iteration of the neural network is controlled through an intermittent control mechanism. The parameter update of the neural network adopts rule update + chaotic update, and the parameter selection is optimized through Riemann geometry.

[0133] 5 The conventional generative adversarial network performs data expansion, controls the iteration of the neural network through an intermittent control mechanism, and updates the parameters of the neural network using arbitrary update rules.

[0134] 6. Data expansion is performed by optimizing the generative adversarial network generated by calculating the information entropy of the data. The iteration of the neural network is controlled by an intermittent control mechanism, and the parameters of the neural network are updated using arbitrary update rules.

[0135] 7. Data expansion is performed by optimizing the generative adversarial network generated by calculating the information entropy of the data. The iteration of the neural network is controlled by an intermittent control mechanism, and the parameters of the neural network are updated using rule update + chaotic update.

[0136] 8. Data expansion is performed by optimizing the generative adversarial network generated by calculating the information entropy of the data. The iteration of the neural network is controlled by an intermittent control mechanism. The parameters of the neural network are updated using rule update + chaotic update, and the parameter selection is optimized through Riemann geometry.

[0137] The disclosed embodiment of the present invention further provides a computer program product or system, including a computer program, which implements the steps of the above-mentioned trauma level assessment method when executed by a processor.

[0138] Figure 2 A schematic diagram of a trauma grade assessment system provided by an embodiment of the present invention specifically includes: Acquisition unit: acquires data of trauma patients; Evaluation unit: input the data into the evaluation model to obtain mild, moderate and severe evaluation results; wherein the training process of the evaluation model is: Obtain a dataset and labels of trauma patients; The data set and the label are input into a neural network for training to obtain an evaluation model, wherein the parameter update of the neural network includes a first update rule and a second update rule, and the neural network updates the parameters by alternately executing the first update rule and the second update rule. When the model performance of the neural network is lower than the preset performance, the iteration of the neural network is paused through intermittent control and the ratio of the execution times of the first update rule and the second update parameter rule is adjusted before iterating again until the model converges or the preset number of iterations is executed.

[0139] Figure 3 A schematic diagram of a trauma grade assessment device provided by an embodiment of the present invention specifically includes: A memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, any one of the above-mentioned trauma level assessment methods is executed.

[0140] The disclosed embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the above-mentioned methods for assessing the level of trauma is implemented.

[0141] The verification results of this verification embodiment show that assigning inherent weights to indications can improve the performance of the method relative to the default setting. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units. A person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above-mentioned embodiments may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0142] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be implemented by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned medium storage can be a read-only memory, a disk or an optical disk, etc.

[0143] The above is a detailed introduction to a computer device provided by the present invention. For a person skilled in the art, according to the concept of the embodiments of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for assessing trauma level, characterized in that: include: Obtain data on trauma patients; The data is input into the evaluation model to obtain mild, moderate and severe evaluation results; wherein the training process of the evaluation model is: Obtain a dataset and labels of trauma patients; The data set and the label are input into a neural network for training to obtain an evaluation model, wherein the parameter update of the neural network includes a first update rule and a second update rule, and the neural network updates the parameters by alternately executing the first update rule and the second update rule. When the model performance of the neural network is lower than the preset performance, the iteration of the neural network is paused through intermittent control and the ratio of the execution times of the first update rule and the second update parameter rule is adjusted before iterating again until the model converges or the preset number of iterations is executed.

2. The method for evaluating the injury level according to claim 1, characterized in that: The first update rule and the second update rule include one or more of the following: batch gradient descent, stochastic gradient descent, momentum update; The first update rule and the second update rule also include rule update and chaos update; the rule update is to adjust parameters through non-gradient parameter update rules and based on Fourier transform; the chaos update is to generate a chaotic sequence through chaotic mapping and map it to the parameters to be updated to obtain updated parameters.

3. The method for evaluating the injury level according to claim 2, characterized in that: The chaotic mapping method is expressed as: in, For the The chaotic variable of the iteration, For the The chaotic variable of the iteration, is the perturbation intensity; is the order of the chaotic sequence; is the chaos control parameter.

4. The method for assessing the level of injury according to claim 1, characterized in that: The training of the neural network also includes parameter optimization, and the parameter optimization algorithms include one or more of the following: ant colony optimization algorithm, genetic annealing algorithm, particle swarm optimization algorithm, whale optimization algorithm, gray wolf optimization algorithm, and Riemann geometry optimization algorithm; wherein the Riemann geometry optimization algorithm is a Riemann metric obtained by the gradient flow of the Riemann manifold in the parameter space, the Riemann gradient is calculated based on the Riemann metric, and then the optimized parameters are obtained by optimizing the parameters through the Riemann gradient.

5. The method for assessing the level of injury according to claim 1, characterized in that: The performance of the model is judged by the performance improvement rate. When the performance improvement rate meets the preset performance improvement rate, the model performance is judged to be excellent. When the performance improvement rate meets the preset performance improvement rate, the model performance is judged to be poor. When the model performance is poor, the iteration of the neural network is adjusted through intermittent control. The performance improvement rate is expressed as: in, is the performance improvement rate, For the The loss function value of the iteration; For the The performance improvement rate of the iteration, is the performance change smoothing coefficient.

6. The method for assessing the level of injury according to claim 1, characterized in that: The method also includes data expansion, inputting the data set into a generative adversarial neural network for data expansion to obtain an expanded data set, and then inputting the expanded data set into the neural network for training; wherein the generator in the generative adversarial neural network adjusts the data by calculating the information entropy of the input data to obtain the adjusted data, and the generator generates data based on the adjusted data.

7. The method for assessing the level of injury according to claim 1, characterized in that: The method also includes recommending treatment plans, and providing corresponding treatment plans and treatment costs according to the mild, moderate and severe assessment results; the mild, moderate and severe levels are determined by encoding the data on the degree of trauma and determining the level based on the size of the encoded value.

8. A computer program product comprising a computer program or instructions, characterized in that The computer program or instructions are executed by a processor to implement the injury level assessment method according to claims 1-7.

9. A computer device comprising a memory, a processor and a computer program or instruction stored in the memory, characterized in that: The computer program or instructions are executed by a processor to implement the injury level assessment method according to claims 1-7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instructions are executed by a processor to implement the injury level assessment method according to claims 1-7.

Images