Intelligent prediction and prevention method and system for pressure injury

Abstract

The invention relates to a pressure injury intelligent prediction and prevention method and system, and the method comprises the steps: determining target comprehensive monitoring data of a patient, the target comprehensive monitoring data comprising microenvironment data indicating body surface temperature, body surface humidity and pressure on a pressed part, and individual feature data indicating the gender, age and whether the patient suffers from diabetes; based on the comprehensive monitoring data, a machine learning model based on ensemble learning is adopted for analysis to obtain a risk score, the machine learning model comprises a plurality of basic learners, and each basic learner performs performance evaluation in advance based on a method of combining cross validation and feature importance evaluation; corresponding weights are distributed according to scores of the performance evaluation indexes, weighted average combination is carried out based on prediction results of all the basic learners, and a prediction result of the integrated model can be obtained; and performing quantitative evaluation on the pressure injury occurrence risk of the pressed part of the patient based on the risk score, and generating a risk report.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data analysis, and in particular to a method and system for intelligently predicting and preventing pressure injuries. Background Art

[0002] Pressure injury, also known as pressure sore, is a common complication caused by long-term pressure on local tissue, which leads to blood circulation disorders and nutrient deficiency, resulting in local tissue ulceration and necrosis. This injury not only increases the patient's pain and prolongs hospitalization, but may also cause serious consequences such as infection and sepsis, and even threaten the patient's life. During surgery, because the patient is in a specific position and often cannot move independently, it becomes a high-incidence period for pressure injuries.

[0003] Traditional pressure injury risk assessment mainly relies on the experience and intuition of medical staff, which is highly subjective and difficult to ensure the accuracy and consistency of the assessment. With the development of machine learning, relevant researchers have begun to explore the use of machine learning algorithms to predict and evaluate the risk of pressure injuries, such as using support vector machines, random forests and other algorithms to build prediction models. Although this method can learn the complex relationship between risk and multiple factors based on a large amount of historical data and improve the accuracy of prediction, a single algorithm often has limitations, such as overfitting, weak generalization ability, or poor adaptability to new data. Therefore, it is necessary to combine multiple machine learning algorithms from the perspective of ensemble learning to perform pressure injury risk assessment in order to improve the accuracy of pressure injury prediction. Summary of the invention

[0004] In order to improve the accuracy of pressure injury prediction, the purpose of the present invention is to provide a pressure injury intelligent prediction and prevention method and system, the technical scheme adopted is as follows:

[0005] In a first aspect, the present application discloses a method for intelligent prediction and prevention of pressure injuries, the method comprising:

[0006] S1. Determine the target comprehensive monitoring data of the patient, wherein the target comprehensive monitoring data includes microenvironment data indicating body surface temperature, body surface humidity, and pressure on the compressed part, and individual characteristic data indicating the patient's gender, age, and whether the patient suffers from diabetes;

[0007] S2. Analyze the target comprehensive monitoring data using a machine learning model based on ensemble learning to obtain a risk score, wherein the machine learning model includes multiple basic learners, each of which is pre-performance evaluated based on a method combining cross-validation and feature importance evaluation, and is assigned a corresponding weight according to the score of the performance evaluation index. After weighted average combination of the prediction results of all basic learners, the prediction result of the ensemble model can be obtained;

[0008] S3. Based on the risk score, a quantitative assessment is performed on the risk of pressure injury at the compressed part of the patient, and a risk report is generated.

[0009] Furthermore, in step S1, determining the target comprehensive monitoring data of the patient includes:

[0010] S11. Obtain the patient's initial comprehensive monitoring data;

[0011] S12, based on the initial comprehensive monitoring data, removing invalid data through multi-dimensional verification to obtain valid monitoring data, wherein the multi-dimensional verification includes a numerical range verification and a time continuity verification for microenvironment data, a data consistency verification and a logical rationality verification for individual feature data;

[0012] S13, based on the effective monitoring data, performing missing value checking and filling processing through a missing value prediction and filling model to obtain reliable monitoring data;

[0013] S14. Based on the reliable monitoring data, perform standardization processing on numerical data and categorical data to obtain target comprehensive monitoring data.

[0014] Furthermore, in step S13, the missing value prediction and filling model is composed of a mask-based adaptive convolutional neural network, a long short-term memory network, and a self-attention and cross-attention mechanism, wherein:

[0015] The mask-based adaptive convolutional neural network is used as a feature extractor, including a mask estimation module, a plurality of parallel adaptive convolutional layers, and a feature fusion and output module, wherein: the mask estimation module is used to generate a mask matrix corresponding to the input data based on context information, and the mask matrix marks the estimated position of missing values ​​in the data; each of the adaptive convolutional layers is used to select a corresponding weight adjustment strategy based on the mask matrix, in combination with the distribution characteristics of the estimated position of missing values ​​and the characteristics of the convolutional kernel itself, to dynamically adjust the weight of the convolutional kernel, so that when the convolutional kernel processes the estimated position of missing values ​​marked by the mask matrix, the weight of these positions can be reduced, thereby avoiding the negative impact of missing values ​​on feature extraction; the feature fusion and output module is used to fuse the features extracted from each adaptive convolutional layer and generate a final feature representation;

[0016] The long short-term memory network is used as a time series dependency capturer and feature fusion processor to process time series data using its memory capacity and time series analysis capabilities, further capture the time series dependencies in the data, and integrate the feature attributes associated with each time series monitoring value;

[0017] The self-attention and cross-attention mechanisms serve as information focusers and fusers. On the one hand, when processing the data at each time point, the model can calculate the correlation between the point and other points based on the contextual information of the entire time series, so that the model can more accurately identify which time points are most critical for predicting missing values, thereby enhancing the robustness of the long short-term memory network in capturing temporal dependencies. On the other hand, the model allows the model to simultaneously focus on the feature attribute information associated with each monitoring value when processing time series data, and by calculating the correlation between elements of time series data and feature attribute data, it helps the long short-term memory network to better integrate information between different data sources, thereby generating more comprehensive and accurate prediction results.

[0018] Furthermore, in step S2, the basic learner includes at least one of a decision tree, a support vector machine, a random forest, and a neural network.

[0019] Furthermore, for each basic learner, in step S2, the performance of each basic learner is evaluated based on a method combining cross-validation and feature importance evaluation, including:

[0020] S21, performing feature selection based on statistical analysis and correlation selection to obtain a preliminarily screened feature set;

[0021] S22, performing feature importance evaluation on each feature in the feature set after the preliminary screening by using a Lasso regression algorithm to obtain a feature importance evaluation result;

[0022] S23, according to the feature importance evaluation result, the most important target feature subset is screened out from the feature set after the preliminary screening by sorting and threshold method;

[0023] S24, according to the size of the target feature subset, select a K-fold cross-validation method to train and validate the basic learner, wherein, in each cross-validation cycle, K-1 pieces of training data are used for training, and the remaining 1 piece of data is used for validation;

[0024] S25. Repeat the cross-validation process K times to obtain K independent performance evaluation results, and obtain a robust estimate of the performance of the base learner based on the mean and standard deviation.

[0025] Furthermore, in step S2, each basic learner is assigned a corresponding weight according to the score of the performance evaluation index. After weighted average combination based on the prediction results of all basic learners, the prediction results of the integrated model can be obtained, including:

[0026] S26, calculating the weight of each learner by multi-objective optimization technology based on the performance evaluation index score of each base learner in the cross-validation process;

[0027] S27, for each sample to be predicted, use all basic learners to predict it and obtain respective prediction results;

[0028] S28. According to the determined weight of each learner, weighted averaging is performed based on the prediction results of each learner to obtain an integrated prediction result.

[0029] Furthermore, in step S27, after obtaining the prediction result, the method further includes:

[0030] S271, calculating the prediction accuracy and stability of each learner on the sample to be tested;

[0031] S272, when it is determined that the accuracy and / or stability of the corresponding learner is greater than a preset threshold, the weight of the learner is increased according to the set weight adjustment coefficient; otherwise, the weight of the learner is reduced;

[0032] S273. When it is determined that the accuracy of the corresponding learner drops below a preset threshold and / or the stability fluctuation exceeds a preset range, the weight of the learner is recalculated and adjusted according to the evaluation result to ensure the prediction performance and stability of the integrated model.

[0033] Furthermore, in step S3, the risk of pressure injury at the patient's compressed part is quantitatively assessed based on the risk score, and a risk report is generated, including:

[0034] S31. Classify the patient's risk score into different risk levels according to a preset risk score threshold range, and generate preventive measures suggestions corresponding to the risk level in combination with an intelligent preventive measures engine;

[0035] S32. Obtain the patient's basic information, risk score of the pressure site, risk level, recommended preventive measures for the risk level, and potential risk factors, and generate a risk report through an interactive report template generation system.

[0036] In a second aspect, the present application discloses a pressure injury intelligent prediction and prevention system, the system comprising a data acquisition module, a risk scoring module, and a risk quantification assessment module, wherein:

[0037] The data acquisition module is used to determine the target comprehensive monitoring data of the patient, wherein the target comprehensive monitoring data includes microenvironment data indicating body surface temperature, body surface humidity, and pressure on the compressed part, and individual characteristic data indicating the patient's gender, age, and whether or not the patient suffers from diabetes;

[0038] The risk scoring module is used to analyze the target comprehensive monitoring data using a machine learning model based on ensemble learning to obtain a risk score, wherein the machine learning model includes multiple basic learners, each of which is pre-performance evaluated based on a method combining cross-validation and feature importance evaluation, and is assigned a corresponding weight according to the score of the performance evaluation index. After weighted average combination of the prediction results of all basic learners, the prediction result of the ensemble model can be obtained;

[0039] The risk quantification assessment module is used to quantitatively assess the risk of pressure injury at the patient's compressed part based on the risk score and generate a risk report.

[0040] In a third aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the intelligent prediction and prevention method for pressure injuries.

[0041] The present invention has the following beneficial effects:

[0042] 1) By determining the target comprehensive monitoring data of the patient, including microenvironmental data (body surface temperature, body surface humidity, pressure on the compressed part) and individual characteristic data (gender, age, diabetes status), it is possible to achieve comprehensive monitoring of the risk of pressure injury at the compressed part of the patient;

[0043] 2) The use of machine learning models based on ensemble learning for analysis can fully utilize the advantages of multiple basic learners and combine the prediction results of each learner by weighted average, thereby improving the accuracy and stability of the overall prediction. In addition, the performance of the basic learners is evaluated in advance based on a method combining cross-validation and feature importance evaluation, and weights are assigned according to the scores of performance evaluation indicators, ensuring that the advantages and disadvantages of the learners are taken into account when the model is constructed, further improving the prediction performance;

[0044] 3) By quantitatively assessing the risk of pressure injuries in the compressed parts of patients, it can provide clear risk indicators for medical staff, helping them to take timely intervention measures to reduce the risk of pressure injuries in patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1A method flow chart of a method for intelligent prediction and prevention of pressure injuries provided by an embodiment of the present invention;

[0047] Figure 2 A system structure diagram of a pressure injury intelligent prediction and prevention system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a pressure injury intelligent prediction and prevention method and system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0049] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0050] The specific scheme of the intelligent prediction and prevention method and system for pressure injury provided by the present invention is described in detail below with reference to the accompanying drawings.

[0051] See also Figure 1 , which shows a method flow chart of a method for intelligent prediction and prevention of pressure injuries provided by an embodiment of the present invention, the method comprising:

[0052] Step S1, determining the target comprehensive monitoring data of the patient, wherein the target comprehensive monitoring data includes microenvironment data indicating body surface temperature, body surface humidity, and pressure on the compressed part, and individual characteristic data indicating the patient's gender, age, and whether or not he or she suffers from diabetes.

[0053] Step S2, based on the target comprehensive monitoring data, a machine learning model based on ensemble learning is used for analysis to obtain a risk score, wherein the machine learning model includes multiple basic learners, each basic learner is preliminarily evaluated for performance based on a method combining cross-validation and feature importance evaluation, and a corresponding weight is assigned according to the score of the performance evaluation index. After weighted average combination of the prediction results of all basic learners, the prediction result of the ensemble model can be obtained.

[0054] Step S3, quantitatively assessing the risk of pressure injury at the patient's compressed part based on the risk score, and generating a risk report.

[0055] As can be seen from the above, the intelligent prediction and prevention method for pressure injuries disclosed in the present application can achieve comprehensive monitoring of the risk of pressure injuries in the patient's compressed parts by determining the patient's target comprehensive monitoring data, including microenvironment data (body surface temperature, body surface humidity, pressure on the compressed parts) and individual characteristic data (gender, age, diabetes status); the machine learning model based on ensemble learning is used for analysis, which can make full use of the advantages of multiple basic learners and combine the prediction results of each learner by weighted average, thereby improving the accuracy and stability of the overall prediction. Moreover, the performance of the basic learner is evaluated in advance based on a method combining cross-validation and feature importance evaluation, and weights are assigned according to the scores of performance evaluation indicators, ensuring that the advantages and disadvantages of the learner are taken into account when the model is constructed, further improving the prediction performance; by quantitatively evaluating the risk of pressure injuries in the compressed parts of patients, it can provide medical staff with clear risk indicators, which helps them take timely measures to intervene and reduce the risk of pressure injuries in patients.

[0056] In one embodiment, in step S1, determining the target comprehensive monitoring data of the patient includes:

[0057] Step S11, obtaining the initial comprehensive monitoring data of the patient.

[0058] Step S12, based on the initial comprehensive monitoring data, invalid data is removed through multi-dimensional verification to obtain valid monitoring data, wherein the multi-dimensional verification includes a numerical range verification and a time continuity verification for microenvironment data, a data consistency verification and a logical rationality verification for individual feature data.

[0059] The numerical range check and time continuity check for microenvironment data include: 1) checking whether the microenvironment data falls within a reasonable physiological or equipment measurement range, and marking the data beyond the range as invalid data; 2) considering the importance of data integrity and quality assessment, the microenvironment data can be checked for temporal continuity to screen for invalid data.

[0060] Data consistency check and logic rationality check for individual characteristic data include: 1) Check whether individual characteristic data is consistent between different records or different data sources. Invalid data is marked for inconsistent data; 2) Check whether individual characteristic data is reasonable based on medical common sense and logical rules. For example, age should be a positive number, gender should be a valid option (male, female, etc.), and diabetes status should be consistent with other medical records of the patient.

[0061] In one embodiment, the screened invalid data may be displayed on a visual interface, and after further confirmation by the user, the invalid data may be removed or corrected.

[0062] Step S13, based on the effective monitoring data, missing value checking and filling processing are performed through a missing value prediction and filling model to obtain reliable monitoring data.

[0063] Specifically, this application will construct training data based on effective monitoring data in advance; the format of the training data is time series + feature attribute matrix; that is, the training data not only contains monitoring values ​​arranged in time series, but also contains feature attributes associated with each monitoring value (such as environmental parameters, equipment status, etc.), which help the model to more accurately predict and fill missing values. Afterwards, the training data will be input into the missing value prediction and filling model for model training.

[0064] Finally, the new valid monitoring data is processed based on the trained model. During the processing, the model will first check the location of missing values ​​in the data, then use the learned rules and patterns to predict these missing values, and give the corresponding filling method (that is, specific filling values ​​or filling strategies). In this way, the monitoring data processed by the model will become more complete and reliable, providing strong support for subsequent data analysis and decision-making.

[0065] Step S14, based on the reliable monitoring data, standardize the numerical data and the categorical data to obtain the target comprehensive monitoring data.

[0066] Specifically, for the numerical data of body surface temperature, it can be standardized according to the normal human body temperature range, for example, by subtracting the lowest value and dividing by the range difference, so as to convert it into a value between 0 and 1. For the numerical data of body surface humidity, it can also be converted into a relative humidity percentage in the same way. For the numerical data of the pressure received by the compressed part, it can be standardized according to the medically recommended range to ensure that the data is on a reasonable scale.

[0067] Specifically, for the categorical data of gender, one-hot coding can be used for standardization, such as "01" for female and "10" for male. For the categorical data of whether or not to have diabetes, considering that it is a binary categorical variable, binary coding can be used for standardization, such as "0" for no and "1" for yes. For the categorical data of age, label coding is used for standardization, such as for children aged 0-12, the label is defined as 0; for adolescents aged 13-18, the label is defined as 1; for adults aged 19-64, the label is defined as 2; for the elderly aged 65 and above, the label is defined as 3, so as to divide them into different age groups (such as children, adolescents, adults, and the elderly).

[0068] In the above embodiment, on the one hand, through multi-dimensional verification, invalid data can be effectively identified and removed, such as microenvironment data beyond a reasonable numerical range, data that is discontinuous in time, and inconsistent or logically unreasonable data in individual feature data. This ensures that the data relied on by subsequent analysis is accurate and reliable. On the other hand, using the missing value prediction and filling model, the missing values ​​in the effective monitoring data can be accurately predicted and filled. This reduces the information missing in the data, improves the integrity and availability of the data, and provides more comprehensive data support for subsequent data analysis. Finally, numerical data and categorical data are standardized so that data from different sources and scales can be converted into a unified format and standard. This helps to eliminate the heterogeneity between data and improve the consistency and comparability of data.

[0069] In one embodiment, in step S13, the missing value prediction and filling model is composed of a mask-based adaptive convolutional neural network, a long short-term memory network, and a self-attention and cross-attention mechanism, wherein:

[0070] The mask-based adaptive convolutional neural network serves as a feature extractor, and includes a mask estimation module, multiple parallel adaptive convolutional layers, and a feature fusion and output module, wherein: the mask estimation module is used to generate a mask matrix corresponding to the input data based on context information, and the mask matrix marks the estimated positions of missing values ​​in the data; each of the adaptive convolutional layers is used to dynamically adjust the weight of the convolutional kernel by selecting a corresponding weight adjustment strategy based on the mask matrix, combined with the distribution characteristics of the estimated positions of missing values ​​and the characteristics of the convolutional kernel itself, so that when the convolutional kernel processes the estimated positions of missing values ​​marked by the mask matrix, it can reduce the weight of these positions, thereby avoiding the negative impact of missing values ​​on feature extraction; the feature fusion and output module is used to fuse the features extracted from each adaptive convolutional layer and generate a final feature representation.

[0071] Specifically, the mask generation module first analyzes context information, including but not limited to the trend of the time series and the spatial distribution characteristics of the data. Based on these analyses, a mask matrix corresponding to the input data is generated. This mask matrix has the same shape as the input data, but each element in it indicates whether the data at the corresponding position is missing. The position of the missing value is marked as 0, and the position of the non-missing value is marked as 1.

[0072] Specifically, each adaptive convolution layer will first determine the distribution characteristics of the estimated position of the missing value based on the mask matrix, such as the density of the missing value, where the density of the missing value can reflect the severity and distribution of the missing data. After that, the weight adjustment strategy of the convolution kernel is determined in combination with the characteristics of the convolution kernel itself, such as shape and size. In this process, if the density of missing values ​​in a certain position range is large, and the position range is within the coverage range of the convolution kernel, the convolution kernel weight corresponding to the position range can be reduced to reduce the impact of the missing value on the convolution operation result. Finally, the convolution kernel with adjusted weights can be used to start traversing the input data and perform convolution operations. During the convolution operation, the adjusted convolution kernel will be more adapted to the distribution characteristics of the missing values ​​in the input data, so that the feature information of the data can be extracted more accurately, providing richer and more accurate input for subsequent network layers.

[0073] The long short-term memory network serves as a time series dependency capturer and feature fusion processor, and is used to utilize its memory capacity and time series analysis capabilities to process time series data, further capture the time series dependencies in the data, and integrate the feature attributes associated with each time series monitoring value.

[0074] Specifically, when processing composite data that includes monitoring values ​​arranged in time series and characteristic attributes associated with each monitoring value, the LSTM network not only focuses on the changing trend and periodicity of the time series data itself, but also fully considers the characteristic attributes such as environmental parameters and equipment status associated with each monitoring value. This also means that when predicting missing values, the model will comprehensively consider the changing trend and periodicity of the time series data, as well as the characteristic attributes such as environmental parameters and equipment status associated with each monitoring value.

[0075] The self-attention and cross-attention mechanisms serve as information focusers and fusers. On the one hand, when processing the data at each time point, the model can calculate the correlation between the point and other points based on the contextual information of the entire time series, so that the model can more accurately identify which time points are most critical for predicting missing values, thereby enhancing the robustness of the long short-term memory network in capturing temporal dependencies. On the other hand, the model allows the model to simultaneously focus on the feature attribute information associated with each monitoring value when processing time series data, and by calculating the correlation between elements of time series data and feature attribute data, it helps the long short-term memory network to better integrate information between different data sources, thereby generating more comprehensive and accurate prediction results.

[0076] Specifically, when the self-attention mechanism runs the model, it can more accurately identify which time points have a strong correlation between data changes and missing values ​​when processing data at each time point. By focusing on these key time points, the robustness of the long short-term memory network in capturing temporal dependencies is further enhanced, allowing the model to more accurately understand the dynamic changes of time series data. When the cross-attention mechanism runs the model, it can simultaneously focus on the feature attribute information related to each monitoring value when processing time series data. By integrating information across data sources, the model can generate more comprehensive and accurate prediction results.

[0077] In the above embodiment, based on the introduction of long short-term memory network, the model can use its memory capacity and time series analysis ability to process time series data and effectively capture the time series dependencies in the data. The introduction of self-attention mechanism allows the model to calculate the correlation based on the context information of the entire time series when processing the data at each time point, so as to more accurately identify the key time points and enhance the robustness of the model in capturing time series dependencies. The introduction of cross-attention mechanism promotes the information interaction between time series data and feature attribute data, helps the model better integrate information between different data sources, and improves the comprehensiveness and accuracy of the prediction results.

[0078] In one embodiment, in step S2, the basic learner includes at least one of a decision tree, a support vector machine, a random forest, and a neural network.

[0079] In one embodiment, for each base learner, in step S2, a performance evaluation is performed on each base learner based on a method combining cross-validation and feature importance evaluation, including:

[0080] Step S21, performing feature selection based on statistical analysis and correlation selection to obtain a preliminarily screened feature set.

[0081] Specifically, this application will calculate the correlation coefficient (such as the Pearson correlation coefficient) between each feature and the target variable, and sort them according to the absolute value of the correlation coefficient, so as to determine the first feature with high correlation with the target variable. Then, the correlation between the first feature and other features is calculated to avoid highly redundant features, and the second feature is obtained. After that, after verifying the significant relationship between the second feature and the target variable by combining statistical tests, those features that are highly correlated with the target variable and not highly redundant with other features are further screened out to form a preliminarily screened feature set.

[0082] It should be noted that the features here refer to the variables used to predict the target variable. Specifically, these features include microenvironmental data indicating body surface temperature, body surface humidity, and pressure on the pressure site, as well as individual characteristic data indicating the patient's gender, age, and whether or not they have diabetes. These features together constitute the input of the machine learning model, which is used to train the model to predict the target variable. The target variable refers to the variable predicted by the features. Specifically, the target variable here refers to the risk score for pressure sores.

[0083] Step S22, performing feature importance evaluation on each feature in the feature set after the preliminary screening by using the Lasso regression algorithm to obtain a feature importance evaluation result.

[0084] Specifically, the Lasso regression algorithm is used to compress feature coefficients by introducing L1 regularization terms, so that some unimportant feature coefficients become zero, while important feature coefficients are retained. After the calculation is completed, the importance of the feature is evaluated based on the absolute value of the remaining non-zero coefficients. Among them, the coefficient with a larger absolute value indicates that the feature has a higher contribution in the model, and has a greater predictive or explanatory effect on the target variable.

[0085] Step S23, based on the feature importance evaluation result, the most important target feature subset is screened out from the feature set after the preliminary screening by sorting and threshold method.

[0086] Specifically, based on the feature coefficients obtained by Lasso regression, the features in the feature set after the preliminary screening are sorted by absolute value. Then a threshold is set, and features with importance scores higher than the threshold are selected to construct the target feature subset, so that the selected features can be ensured to be both important and relatively few, which helps to reduce the complexity of the model and the risk of overfitting.

[0087] Step S24, according to the size of the target feature subset, select the K-fold cross-validation method to train and verify the basic learner, wherein, in each cross-validation cycle, K-1 pieces of training data are used for training, and the remaining 1 piece of data is used for verification.

[0088] Specifically, you first need to determine the value of K according to the size of the target feature subset (such as common choices are K = 5 or K = 10, which depends on the amount of data and computing resources, as well as the stability of the desired model performance evaluation), and then randomly divide the input data set into K parts. It should be noted that in each cross-validation cycle, K-1 parts of the data will be randomly selected to construct a training set, and the remaining 1 part of the data will be used as a validation set. After that, the training set can be used to train the current basic learner. This step involves parameter optimization and model fitting of the learner. After the training is completed, the validation set is used to evaluate the performance of the model. The indicators for verifying model performance include at least one of accuracy, recall, and F1 score.

[0089] Step S25, repeat the cross-validation process K times to obtain K independent performance evaluation results, and obtain a robust estimate of the performance of the base learner based on the mean and standard deviation.

[0090] Specifically, after each cross-validation cycle, the performance evaluation results of the model are recorded. After completing K cycles, the mean and standard deviation of all performance evaluation results are calculated. Among them, the mean provides an overall estimate of the model performance, while the standard deviation reflects the fluctuation range of the performance evaluation results. These statistics help us to have a more comprehensive understanding of the performance and stability of the model.

[0091] In the above embodiment, on the one hand, the preliminary screening based on statistical analysis and correlation selection can remove redundant and noise features, reduce the number of features, and improve the operating efficiency of the model. On the other hand, through the Lasso regression algorithm and feature importance evaluation, the most important features are further screened out to form a target feature subset. This helps to improve the interpretability and accuracy of the model, because fewer features usually mean less risk of overfitting. Finally, the basic learner is trained and verified using the K-fold cross-validation method to ensure the stability and generalization ability of the model on different data sets. Through K independent training and verification processes, a more comprehensive performance evaluation can be obtained, including the mean and standard deviation, so as to more accurately estimate the true performance of the model.

[0092] In one embodiment, in step S2, each basic learner is assigned a corresponding weight according to the score of the performance evaluation index, and the prediction result of the integrated model can be obtained by weighted average combination based on the prediction results of all basic learners, including:

[0093] Step S26, based on the performance evaluation index score of each base learner in the cross-validation process, the weight of each learner is calculated by using a multi-objective optimization technique.

[0094] Specifically, this application will construct a multi-objective optimization model, which takes the performance evaluation index score of each basic learner as input and the weight of the learner as output. By solving the multi-objective optimization model, a set of optimal solutions are obtained, which represent the learner weight distribution schemes that balance different performance indicators. After that, according to actual needs (such as giving priority to accuracy or recall rate, etc.), a suitable weight distribution scheme is selected from the optimal solution. Finally, the calculated weights are applied to each basic learner to construct the final integrated learning model. This model can combine the advantages of multiple learners to improve the accuracy and robustness of predictions.

[0095] Step S27: For each sample to be predicted, use all basic learners to predict it and obtain respective prediction results.

[0096] Specifically, the present application will obtain sample data to be predicted from actual application scenarios. Afterwards, for each sample data to be predicted, all basic learners will be used to predict it and obtain respective prediction results. Furthermore, the present application will also organize the prediction results of each basic learner into a unified form for subsequent weighted average calculation.

[0097] Step S28, according to the determined weight of each learner, weighted average is performed based on the prediction results of each learner to obtain an integrated prediction result.

[0098] Specifically, the present application will obtain the weight of the determined basic learner based on step S26. For each sample to be tested, a weighted average calculation will be performed based on the weight and prediction result of the basic learner, that is, the prediction result of each learner is multiplied by its corresponding weight, and then the weighted prediction results are added. Finally, the obtained weighted average is output as the prediction result of the integrated model, and it is interpreted or post-processed as needed.

[0099] In one embodiment, in step S27, after obtaining the prediction result, the method further includes:

[0100] Step S271, calculating the prediction accuracy and stability of each learner on the sample to be tested.

[0101] Step S272: when it is determined that the accuracy and / or stability of the corresponding learner is greater than a preset threshold, the weight of the learner is increased according to the set weight adjustment coefficient; otherwise, the weight of the learner is reduced.

[0102] Step S273, when it is determined that the accuracy of the corresponding learner drops below a preset threshold and / or the stability fluctuation exceeds a preset range, the weight of the learner is recalculated and adjusted according to the evaluation result to ensure the prediction performance and stability of the integrated model.

[0103] It should be noted based on steps S271 to S273 that the present application adjusts the weights of the basic learners in real time by monitoring the accuracy and stability of the prediction results. In the specific implementation, the present application will first calculate the prediction accuracy and stability of each learner on the sample to be tested, and obtain the following results: the accuracy of learner A is 90%, and the stability is 90%; the accuracy of learner B is 85%, and the stability is 80%; the accuracy of learner C is 80%, and the stability is 75%. Based on this evaluation result, you can choose to increase the weight of learner A with higher accuracy and better stability, and at the same time reduce the weight of learner C with lower accuracy and poorer stability. Among them, the weight adjustment strategy can be determined based on the set weight adjustment coefficient, which is proportional to the relative performance of the learner. For example, a benchmark coefficient (such as 1.0) can be set in advance. When the accuracy and / or stability of learner A is 10 percentage points higher than the average level (i.e., 90%-80%=10% and 90%-80%=10%), a proportional coefficient (such as 1.1 or higher, the specific value needs to be adjusted according to the actual application and effect) can be set, and the weight adjustment coefficient of learner A is equal to the benchmark coefficient multiplied by the square of the proportional coefficient to reflect its importance and contribution in the integrated model. On the contrary, for learner C, whose accuracy and stability are both lower than the average level, a decreasing proportional coefficient (such as 0.9 or lower) can be set, and the weight adjustment coefficient of learner C is equal to the benchmark coefficient multiplied by the square of the decreasing proportional coefficient. Through such a calculation method, it can be ensured that the weight adjustment coefficient is proportional to the relative performance of the learner, thereby achieving a reasonable adjustment of the learner weight.

[0104] In one embodiment, in step S3, the risk of pressure injury at the patient's pressure site is quantitatively assessed based on the risk score, and a risk report is generated, including:

[0105] Step S31, according to the preset risk score threshold range, the patient's risk score is divided into different risk levels, and combined with the intelligent preventive measures engine, preventive measures suggestions corresponding to the risk level are generated.

[0106] Specifically, the intelligent preventive measures engine has a built-in set of complete correspondences between risk levels and preventive measures, which are formulated based on extensive clinical research, expert consensus and practical experience. When the engine receives the patient's risk score, it will automatically compare the preset threshold range to determine the patient's risk level. Subsequently, the engine will further analyze the patient's individual characteristics (such as age, weight, medical history, type of surgery, etc.) and select the most suitable preventive measures recommendations for the patient from the preventive measures library. These recommendations not only take into account the risk level, but also fully consider the individual differences of patients, thereby ensuring the pertinence and effectiveness of preventive measures.

[0107] Step S32, obtaining the patient's basic information, the risk score of the pressure site, the risk level, the preventive measures recommended for the risk level, and the potential risk factors, and generating a risk report through an interactive report template generation system.

[0108] Specifically, the interactive report template generation system will first automatically collect and integrate key data such as the patient's basic information, risk score, risk level, preventive measures recommendations, and potential risk factors. Then, the preliminary structure of the report will be automatically generated based on the preset report template framework. These template frameworks contain all the information points required for the report and allow users to fine-tune them according to actual needs. During the report generation process, the system will use visualization methods such as charts, lists, and highlights to intuitively display the patient's risk status and preventive measures recommendations, enhancing the readability and comprehensibility of the report. In addition, the system also supports users to edit and customize reports through an interactive interface, such as adjusting the report layout, adding annotations or notes, etc., to meet the personalized needs of different users. Ultimately, the system will generate a complete, professional and easy-to-understand risk report to provide comprehensive decision-making support for medical staff.

[0109] Please refer to Figure 2 The present application discloses a pressure injury intelligent prediction and prevention system, the system comprising a data acquisition module, a risk scoring module, and a risk quantification assessment module, wherein:

[0110] The data acquisition module is used to determine the patient's target comprehensive monitoring data, which includes microenvironment data indicating body surface temperature, body surface humidity, and pressure on the compressed part, as well as individual characteristic data indicating the patient's gender, age, and whether he or she suffers from diabetes.

[0111] The risk scoring module is used to analyze the target comprehensive monitoring data using a machine learning model based on ensemble learning to obtain a risk score, wherein the machine learning model includes multiple basic learners, each basic learner is pre-performance evaluated based on a method combining cross-validation and feature importance evaluation, and a corresponding weight is assigned according to the score of the performance evaluation indicator. After weighted average combination of the prediction results of all basic learners, the prediction result of the ensemble model can be obtained.

[0112] The risk quantification assessment module is used to quantitatively assess the risk of pressure injury at the patient's compressed part based on the risk score and generate a risk report.

[0113] In one embodiment, the above modules are also used to implement the steps illustrated in any of the above method embodiments, which is not limited in this application.

[0114] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the intelligent prediction and prevention method for pressure injuries.

[0115] As can be seen from the above, the intelligent prediction and prevention system for pressure injuries disclosed in the present application can achieve comprehensive monitoring of the risk of pressure injuries in the patient's compressed parts by determining the patient's target comprehensive monitoring data, including microenvironment data (surface temperature, surface humidity, pressure on the compressed parts) and individual characteristic data (gender, age, diabetes status); the machine learning model based on ensemble learning is used for analysis, which can make full use of the advantages of multiple basic learners and combine the prediction results of each learner by weighted average, thereby improving the accuracy and stability of the overall prediction. Moreover, the performance of the basic learner is evaluated in advance based on a method combining cross-validation and feature importance evaluation, and weights are assigned according to the scores of performance evaluation indicators, ensuring that the advantages and disadvantages of the learner are taken into account when the model is constructed, further improving the prediction performance; by quantitatively evaluating the risk of pressure injuries in the compressed parts of patients, it can provide medical staff with clear risk indicators, which helps them take timely measures to intervene and reduce the risk of pressure injuries in patients.

[0116] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for intelligent prediction and prevention of pressure injuries, characterized in that: The method comprises: S1. Determine the target comprehensive monitoring data of the patient, wherein the target comprehensive monitoring data includes microenvironment data indicating body surface temperature, body surface humidity, and pressure on the compressed part, and individual characteristic data indicating the patient's gender, age, and whether the patient suffers from diabetes; S2. Analyze the target comprehensive monitoring data using a machine learning model based on ensemble learning to obtain a risk score, wherein the machine learning model includes multiple basic learners, each of which is pre-performance evaluated based on a method combining cross-validation and feature importance evaluation, and is assigned a corresponding weight according to the score of the performance evaluation index. After weighted average combination of the prediction results of all basic learners, the prediction result of the ensemble model can be obtained; S3. Based on the risk score, a quantitative assessment is performed on the risk of pressure injury at the compressed part of the patient, and a risk report is generated.

2. The method according to claim 1, characterized in that In step S1, determining the target comprehensive monitoring data of the patient includes: S11. Obtain the patient's initial comprehensive monitoring data; S12, based on the initial comprehensive monitoring data, removing invalid data through multi-dimensional verification to obtain valid monitoring data, wherein the multi-dimensional verification includes a numerical range verification and a time continuity verification for microenvironment data, a data consistency verification and a logical rationality verification for individual feature data; S13, based on the effective monitoring data, performing missing value checking and filling processing through a missing value prediction and filling model to obtain reliable monitoring data; S14. Based on the reliable monitoring data, perform standardization processing on numerical data and categorical data to obtain target comprehensive monitoring data.

3. The method according to claim 2, characterized in that In step S13, the missing value prediction and filling model is composed of a mask-based adaptive convolutional neural network, a long short-term memory network, and a self-attention and cross-attention mechanism, wherein: The mask-based adaptive convolutional neural network is used as a feature extractor, including a mask estimation module, a plurality of parallel adaptive convolutional layers, and a feature fusion and output module, wherein: the mask estimation module is used to generate a mask matrix corresponding to the input data based on context information, and the mask matrix marks the estimated position of missing values ​​in the data; each of the adaptive convolutional layers is used to select a corresponding weight adjustment strategy based on the mask matrix, in combination with the distribution characteristics of the estimated position of missing values ​​and the characteristics of the convolutional kernel itself, to dynamically adjust the weight of the convolutional kernel, so that when the convolutional kernel processes the estimated position of missing values ​​marked by the mask matrix, the weight of these positions can be reduced, thereby avoiding the negative impact of missing values ​​on feature extraction; the feature fusion and output module is used to fuse the features extracted from each adaptive convolutional layer and generate a final feature representation; The long short-term memory network is used as a time series dependency capturer and feature fusion processor to process time series data using its memory capacity and time series analysis capabilities, further capture the time series dependencies in the data, and integrate the feature attributes associated with each time series monitoring value; The self-attention and cross-attention mechanisms serve as information focusers and fusers. On the one hand, when processing the data at each time point, the model can calculate the correlation between the point and other points based on the contextual information of the entire time series, so that the model can more accurately identify which time points are most critical for predicting missing values, thereby enhancing the robustness of the long short-term memory network in capturing temporal dependencies. On the other hand, the model allows the model to simultaneously focus on the feature attribute information associated with each monitoring value when processing time series data, and by calculating the correlation between elements of time series data and feature attribute data, it helps the long short-term memory network to better integrate information between different data sources, thereby generating more comprehensive and accurate prediction results.

4. The method according to claim 1, characterized in that: In step S2, the basic learner includes at least one of a decision tree, a support vector machine, a random forest, and a neural network.

5. The method according to claim 1, characterized in that For each base learner, in step S2, the performance of each base learner is evaluated based on a method combining cross-validation and feature importance evaluation, including: S21, performing feature selection based on statistical analysis and correlation selection to obtain a preliminarily screened feature set; S22, performing feature importance evaluation on each feature in the feature set after the preliminary screening by using a Lasso regression algorithm to obtain a feature importance evaluation result; S23, according to the feature importance evaluation result, the most important target feature subset is screened out from the feature set after the preliminary screening by sorting and threshold method; S24, according to the size of the target feature subset, select a K-fold cross-validation method to train and validate the basic learner, wherein, in each cross-validation cycle, K-1 pieces of training data are used for training, and the remaining 1 piece of data is used for validation; S25. Repeat the cross-validation process K times to obtain K independent performance evaluation results, and obtain a robust estimate of the performance of the base learner based on the mean and standard deviation.

6. The method according to claim 5, characterized in that In step S2, each basic learner is assigned a corresponding weight according to the score of the performance evaluation index. After the prediction results of all basic learners are combined by weighted average, the prediction results of the integrated model can be obtained, including: S26, calculating the weight of each learner by a multi-objective optimization technique based on the performance evaluation index score of each base learner in the cross-validation process; S27, for each sample to be predicted, use all basic learners to predict it and obtain respective prediction results; S28. According to the determined weight of each learner, weighted averaging is performed based on the prediction results of each learner to obtain an integrated prediction result.

7. The method according to claim 6, characterized in that In step S27, after obtaining the prediction result, the method further includes: S271, calculating the prediction accuracy and stability of each learner on the sample to be tested; S272, when it is determined that the accuracy and / or stability of the corresponding learner is greater than a preset threshold, the weight of the learner is increased according to the set weight adjustment coefficient; otherwise, the weight of the learner is reduced; S273. When it is determined that the accuracy of the corresponding learner drops below a preset threshold and / or the stability fluctuation exceeds a preset range, the weight of the learner is recalculated and adjusted according to the evaluation result to ensure the prediction performance and stability of the integrated model.

8. The method according to any one of claims 1 to 7, characterized in that: In step S3, the risk of pressure injury at the patient's compressed part is quantitatively assessed based on the risk score, and a risk report is generated, including: S31. Classify the patient's risk score into different risk levels according to a preset risk score threshold range, and generate preventive measures suggestions corresponding to the risk level in combination with an intelligent preventive measures engine; S32. Obtain the patient's basic information, risk score of the pressure site, risk level, recommended preventive measures for the risk level, and potential risk factors, and generate a risk report through an interactive report template generation system.

9. An intelligent prediction and prevention system for pressure injuries, characterized in that: The system includes a data acquisition module, a risk scoring module, and a risk quantification assessment module, wherein: The data acquisition module is used to determine the target comprehensive monitoring data of the patient, wherein the target comprehensive monitoring data includes microenvironment data indicating body surface temperature, body surface humidity, and pressure on the compressed part, and individual characteristic data indicating the patient's gender, age, and whether or not the patient suffers from diabetes; The risk scoring module is used to analyze the target comprehensive monitoring data using a machine learning model based on ensemble learning to obtain a risk score, wherein the machine learning model includes multiple basic learners, each of which is pre-performance evaluated based on a method combining cross-validation and feature importance evaluation, and is assigned a corresponding weight according to the score of the performance evaluation index. After weighted average combination of the prediction results of all basic learners, the prediction result of the ensemble model can be obtained; The risk quantification assessment module is used to quantitatively assess the risk of pressure injury at the patient's compressed part based on the risk score and generate a risk report.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent prediction and prevention method for pressure injuries described in any one of claims 1 to 8 is implemented.

Images