XGBoost-based critically ill patient malnutrition risk prediction system

Abstract

The invention discloses an XGBoost-based critically ill patient dystrophy risk prediction system, and relates to the technical field of patient nutrition management, and the system comprises an information acquisition module, a data processing module and a risk prediction module. The information acquisition module is used for acquiring target physiological features of a target patient; the risk prediction module further comprises a model construction sub-module and a risk output sub-module; the model construction sub-module is used for acquiring a training data set and a target parameter value; constructing and training a risk prediction model according to the target parameter value and an XGBoost model; during training, calculating the difference between the minimum value of the objective function of the decision tree before updating and the minimum value of the objective function of the decision tree after to-be-updated, generating the decision tree according to the maximum difference value, and obtaining a leaf node weight according to the minimum objective function value of the generated decision tree; and the risk output sub-module is used for obtaining a target risk according to the output of the target physiological feature in the risk prediction model so as to realize automatic feature engineering and reduce the difficulty of model training.

Description

Technical Field

[0001] The present application relates to the technical field of patient nutrition management, and specifically to a malnutrition risk prediction system for critically ill patients based on XGBoost. Background Art

[0002] Critically ill patients are very prone to malnutrition due to their severe condition, metabolic disorders and long-term stress. Malnutrition not only affects the patient's immune function and increases the risk of infectious complications, but can also lead to problems such as delayed wound healing, prolong the patient's hospital stay, increase medical expenses, and even have an adverse effect on the patient's prognosis.

[0003] Commonly used clinical methods for assessing the risk of malnutrition in critically ill patients are mainly based on the subjective assessment of medical staff, such as the Subjective Global Assessment (SGA) and the Nutritional Risk Screening 2002 (NRS2002). The accuracy of the assessment not only depends on the professional level and clinical experience of medical staff, but also is greatly affected by subjective factors. In addition, fixed assessment indicators are difficult to adapt to patients with different physiological characteristics and / or disease characteristics. In particular, when assessing the risk of malnutrition in patients with special diseases and / or special patients, traditional assessment methods are difficult to operate and have low assessment accuracy.

[0004] At present, a prediction model for malnutrition in patients with nasopharyngeal carcinoma with application number CN202410365426.0 uses Logistic regression analysis to construct a risk prediction model to assess the risk of malnutrition in patients with nasopharyngeal carcinoma. However, there are differences in the technical level and equipment conditions of different medical institutions, which leads to significant differences in the collection of characteristic data of critically ill patients by various medical institutions. Before training the risk prediction model, it is necessary to manually screen the model independent variables from the many potential influencing factors that can be collected by the medical institutions. The feature engineering operation is difficult. Not only does it require manual adjustment and optimization of input features based on the specific situation of the medical institution, which increases labor costs, but it also requires a high level of data analysis from professionals. Especially in the absence of data science professionals, manual screening and adjustment are particularly difficult. Summary of the invention

[0005] The purpose of the present invention is to solve the technical problem of difficulty in feature engineering operation when building a malnutrition risk prediction model for critically ill patients, and provide a malnutrition risk prediction system for critically ill patients based on XGBoost, which realizes automated feature engineering through feature importance evaluation built into the risk prediction model.

[0006] The present invention seeks to protect a malnutrition risk prediction system for critically ill patients based on XGBoost, including an information acquisition module and a risk prediction module; The information acquisition module is used to obtain target physiological characteristics of the target patient; The risk prediction module also includes a model building submodule and a risk output submodule; the model building submodule also includes a parameter acquisition submodule, a model generation submodule and a model training submodule; the parameter acquisition submodule is used to obtain the training data set and target parameter value of the risk prediction model; the training data set includes all the physiological characteristics of patients to be screened; the model generation submodule is used to build a risk prediction model based on the target parameter value and the XGBoost model; the risk prediction model includes several decision trees; the model training submodule is used to generate each decision tree based on the training data set and the target parameter value, using the strategy of maximizing information gain; the information gain is obtained based on the difference between the minimum value of the objective function of the decision tree before updating and the minimum value of the objective function of the decision tree to be updated, and the weight of each leaf node is obtained according to the minimum value of the objective function of the generated decision tree; the risk output submodule is used to obtain the trained risk prediction model, and obtain the target risk of the target patient according to the output of the risk prediction model based on the target physiological characteristics.

[0007] In one embodiment of the present application, the information acquisition module divides the target physiological characteristics into historical observation characteristics and target observation characteristics according to whether the acquisition time is a preset observation time; the system also includes a feature prediction module, which is used to predict the predicted physiological characteristics of the preset observation time based on the historical observation characteristics of the target patient; the risk output submodule also includes a risk calculation submodule and a risk verification submodule; the risk calculation submodule is used to obtain the predicted risk based on the predicted physiological characteristics before the preset observation time; the risk verification submodule is used to calculate the feature similarity between the predicted physiological characteristics and the target observation characteristics at the preset observation time, and if the feature similarity is not less than the similarity threshold, the predicted risk is used as the target risk.

[0008] In one embodiment of the present application, if the feature similarity is less than the similarity threshold, the risk verification module is further configured to input the target observation feature into the risk calculation module and output the target risk.

[0009] In one embodiment of the present application, the risk verification module also includes screening target observation feature components from the target observation features according to the corresponding feature items of the intermediate nodes of all decision trees in the trained risk prediction model, and screening predicted physiological feature components from the predicted physiological features; and calculating the feature similarity based on the similarity between the predicted physiological feature components and the target observation feature components.

[0010] In one embodiment of the present application, the feature items corresponding to all intermediate nodes in the trained risk prediction model are recorded as a feature set, and the method for calculating the feature similarity includes: ; ; Wherein, m represents the number of all feature items in the feature set; α i represents the feature weight of the i-th feature item in the feature set, F 1，i represents the value of the i-th feature item of the target observation feature component in the feature set, F 2，i represents the value of the i-th feature item of the predicted physiological feature component in the feature set, N i It represents the difference between the maximum value and the minimum value of the i-th feature item in the feature set in the historical medical records.

[0011] In one embodiment of the present application, the risk verification module also includes obtaining a corresponding feature weight based on the proportion of the number of intermediate nodes corresponding to each feature item in the feature set to the total number of intermediate nodes in the corresponding risk prediction model.

[0012] In one embodiment of the present application, the proportion of randomly selected samples when training each decision tree is less than 1. Before training each decision tree, the model training module obtains the current hit probability of each sample data in the training data set, and increases the hit probability of the sample data predicted incorrectly by the previous decision tree.

[0013] This application has the following beneficial effects: 1. During the training process of the risk prediction model, the information gain of the greedy algorithm is used to automatically determine whether the leaf nodes in the current decision tree should continue to split and the specific splitting method to obtain the non-leaf nodes (i.e., intermediate nodes) of the decision tree, thereby realizing automated feature engineering. This system not only reduces labor costs and the difficulty of model training when training the risk prediction model, but also makes the risk prediction model obtained through training more in line with the current characteristics of medical institutions.

[0014] 2. The system predicts the target patient's physiological characteristics at the preset observation time in advance through the feature prediction module, and inputs the predicted physiological characteristics output by the feature prediction module into the risk prediction model to obtain the predicted risk in advance. When the patient's actual physiological characteristics at the preset observation time meet the requirements of the predicted physiological characteristics, the corresponding predicted risk is regarded as valid, so as to reduce the amount of calculation of the system's concurrent response at the preset observation time, especially in large-scale deployment and use, which reduces the server load, lowers the minimum requirements for system operation, and helps to optimize the system operation cost.

[0015] 3. The risk verification module reduces the misjudgment of malnutrition risk in target patients due to incorrect prediction results of the feature prediction model.

[0016] 4. The feature similarity calculated based on the similarity between the predicted physiological feature component and the target observed feature component not only reduces the computational complexity of the risk verification module, further reduces the computational complexity and system burden, but also reduces the prediction accuracy requirements for the feature prediction module.

[0017] 5. The difference between the maximum value and the minimum value of each feature item in the feature set in the historical medical records is used to obtain the gap between the target observed feature component and the predicted physiological feature component in the corresponding feature item, so as to reduce the impact of different dimensions between different feature items on the prediction validity.

[0018] 6. Giving higher weights to features with more corresponding intermediate nodes can not only be used to describe the importance of the corresponding feature items, but also when the value of the feature item with a larger feature weight changes, that is, when the value of the target observation feature component in the corresponding feature item is different from the value of the predicted physiological feature component in the corresponding feature item, it is more likely to affect the output result of the risk prediction model. The corresponding predicted risk should be identified as invalid first, so as to achieve the accuracy of the output target risk while reducing the calculation amount of the system concurrent response.

[0019] 7. As the number of decision trees generated increases, the decision trees to be trained gradually pay more attention to sample data of special conditions and / or special patients, thereby improving the prediction accuracy of special conditions and / or special patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0021] Figure 1 This is a schematic structural diagram of an implementable method of a critically ill patient malnutrition risk prediction system based on XGBoost involved in an embodiment of the present application; Figure 2 This is a schematic structural diagram of another possible implementation method of a critically ill patient malnutrition risk prediction system based on XGBoost involved in an embodiment of the present application; Figure 3 A schematic diagram of the target risk calculation process involved in the embodiment of the present application; Figure 4 This is a schematic diagram of the structure of an electronic device involved in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, with reference to the terms "one embodiment", "some embodiments", "implementation method", "embodiment", "illustrative embodiment", "example", "specific example" or "some examples", the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application for protection, but only indicates that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. And the specific features, structures or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0023] It should be noted that similar reference numerals and letters represent similar items in the following figures, so once an item is defined in one figure, it does not need to be further defined and explained in the subsequent figures. At the same time, in the description of this application, the terms "first", "second" and other relational terms are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0024] The present invention claims protection for a malnutrition risk prediction system for critically ill patients based on XGBoost, with reference to the attached Figure 1 As shown, it includes an information acquisition module, a data processing module and a risk prediction module.

[0025] It should be noted that the information acquisition module is used to obtain the physiological characteristics of the target patient, that is, the target physiological characteristics. The physiological characteristics include basic information, vital signs information, laboratory test indicators, food intake information and disease diagnosis information, of course, it may not be limited to this. The basic information includes age, gender, height, weight, past medical history and family medical history, of course, it may not be limited to this. The vital signs information includes heart rate, blood pressure, respiration and body temperature, of course, it may not be limited to this. The laboratory test indicators include blood routine, biochemical indicators and electrolytes, of course, it may not be limited to this. The food intake information includes food intake type, intake time, intake amount and food processing method, of course, it may not be limited to this. The disease diagnosis information includes the name of the disease, symptom information during the treatment process and historical medication information, of course, it may not be limited to this. The symptom information includes symptom content, duration, frequency and severity, of course, it may not be limited to this. The symptom content, for example, headache type is tingling, distending pain or other pain types, the area where the headache occurs, etc. The historical medication information includes the medication time during the treatment process, the drug name, dosage and medication method corresponding to each medication time, of course, it may not be limited to this. The administration methods include oral administration and intravenous injection, but are certainly not limited thereto.

[0026] It should be noted that the data processing module is used to pre-process the target physiological characteristics. The pre-processing includes data conversion, but it is not limited to this. The data conversion includes normalization processing and encoding processing, but it is not limited to this. Encoding processing includes, for example, encoding of disease names.

[0027] In this embodiment, the risk prediction module is used to input the pre-processed target physiological characteristics into a pre-trained risk prediction model. The risk prediction module includes a risk output submodule and a model construction submodule, but it is not limited to this. Among them, the model construction submodule is used to construct a risk prediction model, and the risk output submodule is used to obtain the trained risk prediction model, input the target physiological characteristics into the risk prediction model, and obtain the target risk of malnutrition in the target patient.

[0028] In this embodiment, the model building submodule also includes a parameter acquisition module, a model generation module and a model training module, but it may not be limited thereto. The parameter acquisition module is used to obtain a training data set and a target parameter value of a risk prediction model. The model generation module is used to build the risk prediction model according to the target parameter value and the XGBoost model. The model training module is used to train the risk prediction model according to the training data set and the target parameter value.

[0029] It should be noted that the training data set includes the physiological characteristics of all patients to be screened. The physiological characteristics of each critically ill patient in the medical institution's historical medical records and whether malnutrition occurs can be obtained to obtain the corresponding sample information; the physiological characteristics of the sample patients can also be obtained based on the existing technical level and equipment of the medical institution to obtain the corresponding sample information. All sample information constitutes the training data set.

[0030] It should be noted that the target parameter value includes the value of the hyperparameter preset when training the risk prediction model. The target parameter value can be obtained in a preset manner or according to user input, such as obtaining the target parameter value input by the user. If there is a target parameter value that has not been input, the default value is obtained. The target parameters include learning task parameters, learning rate, maximum depth of each tree, proportion of samples randomly drawn when training each tree, proportion of features randomly drawn when training each tree, minimum sample weight and required for node splitting, minimum loss reduction value for node splitting, penalty parameter of model complexity and performance evaluation index of the model, of course, it may not be limited to this.

[0031] In this embodiment, the proportion of randomly selected samples is less than 1 when training each decision tree. Before training each decision tree, the model training module obtains the current hit probability of each sample data in the training data set, and increases the hit probability of sample data that was predicted incorrectly by the previous decision tree. As the number of decision trees generated increases, the decision trees to be trained gradually increase their attention to sample data of special conditions and / or special patients, thereby improving the prediction accuracy of special conditions and / or special patients.

[0032] It should be noted that the learning task parameters include loss functions, but they are not limited to this. For example, when the learning task is a regression task, the optional loss functions include root mean square error, mean absolute error, and mean absolute percentage error; when the learning task is a classification task, the optional loss functions include cross entropy loss function and logarithmic loss.

[0033] In this embodiment, the learning task of the risk prediction model is a three-classification task, namely, a high-risk category, a medium-risk category, and a low-risk category. The high-risk category is used to describe that the patient has a high risk of malnutrition, and the medium-risk category is used to describe that the patient has malnutrition. The corresponding softmax function is selected for probability distribution calculation, and the cross entropy loss function is selected as the loss function of the decision tree. The risk prediction model includes several decision trees, and the output of the risk prediction model is obtained according to the output of all decision trees, which can be expressed as: ; It should be noted that Represents sample x iThe output of the risk prediction model, f k (x i ) represents the sample x i At the output of the kth decision tree, K represents the number of decision trees in the risk prediction model. The risk prediction model uses the Boosting algorithm to train each decision tree in turn, that is, the first decision tree f 1 (x i ) is used to output the prediction result of sample xi, and the second decision tree f 2 (x i ) is used to output sample x i In the first decision tree f 1 (x i ) is the error between the predicted result and the actual result, the third decision tree f 3 (x i ) is used to output sample xi in the second decision tree f 2 (x i ) is the difference between the predicted error and the true error, and so on. Calculate the sum of the output results of all decision trees to get the sample x i Therefore, when training the t-th decision tree of the risk prediction model, the output of the risk prediction model Equal to the output of the trained t-1 decision tree And the sum of the outputs of the t-th decision tree to be trained, that is: .

[0034] It should be noted that The value of is preset to 0, which means that when training the first decision tree of the risk prediction model, The value of is 0.

[0035] It should be noted that the decision tree objective function O(t) of the t-th decision tree includes: ; Where n represents the total number of samples in the training data set; L represents the loss function; y i Represents sample x i The true result is whether malnutrition occurs; Ω represents the complexity, which can be obtained according to the regularization term, that is: ; Among them, γ represents the penalty parameter of the number of leaf nodes of the decision tree, T represents the number of leaf nodes of the decision tree, and the more leaf nodes there are in the decision tree, the larger the corresponding penalty value; λ represents the L2 regularization coefficient, ω j Represents the weight of the j-th leaf node in the decision tree.

[0036] In this embodiment, since the first t-1 decision trees have completed training, the term related to the first t-1 decision trees in the objective function is a constant. Optimizing the decision tree objective function by second-order Taylor expansion, regularized expansion, and coefficient merging , that is, the objective function of the decision tree after the t-th decision tree is optimized: ; ; ; ; ; Among them, G j represents the cumulative sum of the first-order partial derivatives of the samples contained in the jth leaf node, H j represents the cumulative sum of the second-order partial derivatives of the samples contained in the jth leaf node, g i represents the first-order partial derivative of the i-th sample in the corresponding leaf node, h i Represents the second-order partial derivative of the i-th sample in the corresponding leaf node. The t-th decision tree with the best risk prediction model is trained by minimizing the value of the objective function. Therefore, the number of leaf nodes of the t-th decision tree with a known structure is fixed, and the decision tree needs to be optimized by optimizing the weights corresponding to all leaf nodes of the decision tree. The leaf node objective function f(ω) of the j-th leaf node j )include: ; Therefore, the leaf node objective function of the jth leaf node is Take the minimum value at When the weights of all current leaf nodes make the corresponding leaf node objective function f take the minimum value, the t-th decision tree with the current known structure has the lowest decision tree objective function. Take the minimum value.

[0037] In this embodiment, during the training of the risk prediction model, when the current depth of the kth decision tree is not greater than the preset depth threshold, a greedy algorithm is used to determine whether each current leaf node needs to be further split and how to split it. When other leaf nodes remain unchanged, the decision tree objective function of the jth leaf node of the current tth decision tree before splitting is recorded as O non (t), the objective function of the decision tree after the leaf node is split at the split point of the dth feature dimension is recorded as , then the information gain corresponding to the jth leaf node The calculation method is: ; Among them, G represents the sum of the first-order partial derivatives of the samples contained in the leaf node before splitting, G L It represents the sum of the first-order partial derivatives of the samples contained in the left node after the leaf node is split at the corresponding split point of the dth feature dimension, G R represents the sum of the first-order partial derivatives of the samples contained in the right node after the leaf node is split at the corresponding splitting point of the dth feature dimension, H represents the sum of the second-order partial derivatives of the samples contained in the leaf node before the split, H L It represents the sum of the second-order partial derivatives of the samples contained in the left node after the leaf node is split at the corresponding split point of the dth feature dimension, H R Represents the sum of the second-order partial derivatives of the samples contained in the right node after the leaf node is split at the corresponding splitting point of the d-th feature dimension.

[0038] It should be noted that if When the value of is greater than the preset splitting threshold, the corresponding splitting point is included in the candidate splitting point set; if When the value of is not greater than the preset splitting threshold, the corresponding splitting point is not included in the candidate splitting point set. The candidate splitting point set is obtained by screening all the splitting points of the j-th node of the current t-th decision tree in all feature dimensions. If the candidate splitting point set is an empty set, the leaf node is not split. If the candidate splitting point set is not an empty set, the leaf node continues to be split, and the splitting point corresponding to the maximum information gain in the candidate splitting point set is taken as the splitting method of the leaf node.

[0039] In this embodiment, the preset depth threshold and the preset splitting threshold can be obtained by presetting.

[0040] In this embodiment, the target patient's physiological characteristics can be acquired in real time to monitor the risk of malnutrition in the target patient in real time, and nutritional support examinations and treatments can be reasonably arranged according to the risk of malnutrition in the target patient, thereby improving the effective utilization of medical resources. During the training process of the risk prediction model, the information gain of the greedy algorithm is used to automatically determine whether the leaf nodes in the current decision tree should continue to split and the specific splitting method to obtain the non-leaf nodes (i.e., the intermediate nodes) of the decision tree, thereby realizing automated feature engineering. This system not only reduces labor costs and the difficulty of model training when training the risk prediction model, but also the risk prediction model obtained through training is more in line with the current characteristics of the medical institution.

[0041] In a feasible implementation, the target physiological characteristics include historical observation characteristics and target observation characteristics. The historical observation characteristics include the actual physiological characteristics of the target patient before the preset observation time during the current treatment. The target observation characteristics include the actual physiological characteristics of the target patient at the preset observation time. The actual physiological characteristics include the values ​​of the patient's physiological characteristics that can be directly detected by the existing professional technology and / or detection equipment of the medical institution, but it is certainly not limited to this.

[0042] In this embodiment, refer to the attached Figure 2 and attached Figure 3 As shown, the information acquisition module includes a target acquisition submodule and a reference acquisition submodule. The target acquisition submodule is used to acquire the target observation characteristics of the target patient. For example, if it is necessary to determine whether the target patient has a risk of malnutrition at a first time point, the target acquisition submodule acquires the physiological characteristics of the target patient at the preset observation point. The reference acquisition submodule is used to acquire the historical observation characteristics of the target patient.

[0043] It should be noted that the preset observation time can be obtained in a preset manner. For example, if the observation interval is preset to be observed once every 2 hours, it can be calculated from the start of monitoring the nutritional support of the target patient. The first preset observation time is the time when monitoring starts, and the corresponding physiological characteristics collected are the target observation characteristics of the first observation, and there is no corresponding historical observation characteristic; the second preset observation time is 2 hours after the start of monitoring, and the corresponding physiological characteristics collected are the target observation characteristics of the second observation, and the target observation characteristics of the first observation are updated to the historical observation characteristics of the second observation.

[0044] In this embodiment, the system further includes a feature prediction module, which is used to predict the predicted physiological characteristics of the target patient at the preset observation time based on the actual physiological characteristics of the target patient before the preset observation time.

[0045] It should be noted that the neural network model can be trained by taking the physiological characteristics of historical patients at different time points in the historical medical records, and the actual physiological characteristics of the target patient before the preset observation time are input into the trained neural network model to obtain the predicted physiological characteristics.

[0046] In this embodiment, the risk output submodule also includes a risk calculation submodule and a risk verification submodule. Among them, the risk calculation submodule is used to input the predicted physiological characteristics into the risk prediction model before the preset observation time to obtain the predicted risk of the target patient. Among them, the risk verification submodule is used to calculate the feature similarity between the predicted physiological characteristics and the actual physiological characteristics collected by the target acquisition submodule at the predicted observation time; compare the feature similarity with the similarity threshold; if the feature similarity is not less than the similarity threshold, the corresponding predicted risk is deemed valid, and the predicted risk is used as the target risk to reduce the amount of calculation of the system's concurrent response at the preset observation time, especially in large-scale deployment and use, reducing the server load, reducing the minimum requirements for system operation, and helping to optimize the system operation cost; if the feature similarity is less than the similarity threshold, the target observation feature is sent to the risk calculation submodule for input, and the target risk is output to reduce the misjudgment of the target patient's risk of malnutrition due to the erroneous prediction results of the feature prediction model.

[0047] It should be noted that the feature similarity can be calculated based on cosine similarity, Euclidean distance, etc. The similarity threshold can be obtained by presetting. For example, the similarity threshold is pre-set to 80%.

[0048] In this embodiment, the system predicts the physiological characteristics of the target patient at a preset observation time in advance through the feature prediction module, and inputs the predicted physiological characteristics output by the feature prediction module into the risk prediction model to obtain the predicted risk in advance. When the actual physiological characteristics of the patient at the preset observation time meet the requirements and the predicted physiological characteristics, the corresponding predicted risk is deemed valid to reduce the amount of calculation of the system's concurrent response at the preset observation time, especially in large-scale deployment and use, which reduces the server load, lowers the minimum requirements for system operation, and helps optimize the system operation cost.

[0049] In a possible implementation, refer to the attached Figure 2 As shown, the risk verification module also includes screening target observation feature components from the target observation features according to the feature items corresponding to the intermediate nodes of all decision trees in the currently trained risk prediction model, and screening predicted physiological feature components from the predicted physiological features, that is, the target observation feature components are the values ​​of the feature items corresponding to the intermediate nodes of all decision trees in the current risk prediction model of the target patient at the preset observation time, and the predicted physiological feature components are the values ​​of the feature items corresponding to the intermediate nodes of all decision trees in the current risk prediction model of the target patient output by the feature prediction module.

[0050] In this embodiment, the feature similarity is calculated based on the similarity between the predicted physiological feature component and the target observed feature component.

[0051] It should be noted that the intermediate nodes of the decision tree in the risk prediction model are the judgment basis of the corresponding decision tree. The structure of all decision trees in the trained risk prediction model is known, that is, the risk judgment basis of the current risk prediction model is known. When the difference between the predicted physiological characteristics and the target observed characteristics is more concentrated in the feature items corresponding to all intermediate nodes, the probability that there is a gap between the predicted risk and the actual risk is greater; when the difference between the predicted physiological characteristics and the target observed characteristics is more concentrated in the features other than the feature items corresponding to all intermediate nodes, the probability that there is a gap between the predicted risk and the actual risk is smaller. Therefore, the feature similarity calculated based on the similarity between the predicted physiological feature component and the target observed feature component not only reduces the calculation amount of the risk verification module, further reduces the calculation amount and system burden, but also reduces the prediction accuracy requirements for the feature prediction module.

[0052] In this embodiment, the feature items corresponding to all intermediate nodes in the risk prediction model are combined into a feature set, which is denoted as F. The method for calculating the feature similarity similar includes: ; Wherein, m represents the number of all feature items in the feature set; α i represents the feature weight of the i-th feature item, F 1，i represents the value of the i-th feature item of the target observation feature component in the feature set, F 2，i represents the value of the i-th feature item of the predicted physiological feature component in the feature set, N i It represents the difference between the maximum value and the minimum value of the i-th feature item in the feature set in the historical medical records.

[0053] It should be noted that the difference between the maximum value and the minimum value of each feature item in the feature set in the historical medical records is used to obtain the gap between the target observed feature component and the predicted physiological feature component in the corresponding feature item, so as to reduce the impact of different feature items on the prediction validity due to different dimensions.

[0054] It should be noted that the feature weights can be pre-set according to the feature importance.

[0055] In this embodiment, the feature weight α i The calculation methods include: ; Where M represents the number of all intermediate nodes in the risk prediction model, M iIt indicates the number of intermediate nodes corresponding to the i-th feature item of the feature set, that is, there are M in the risk prediction model. i The intermediate nodes are identified based on the i-th feature item of the feature set.

[0056] It should be noted that the trained risk prediction model has the characteristics of the medical institution itself. The intermediate nodes in the decision tree generated by the risk prediction model that serve as the basis for risk judgment are in line with the current professional and technical level and equipment characteristics of the medical institution. When a feature item appears in multiple intermediate nodes of multiple decision trees, it means that the feature item plays an important role in the decision-making process of the model. Giving higher weights to features with more corresponding intermediate nodes can not only be used to describe the importance of the corresponding feature item, but also when the value of the feature item with a larger feature weight changes, that is, the value of the target observed feature component in the corresponding feature item is different from the value of the predicted physiological feature component in the corresponding feature item, it is more likely to affect the output result of the risk prediction model. The corresponding predicted risk should be identified as invalid as a priority, so as to achieve the accuracy of the output target risk while reducing the computational complexity of the system concurrent response.

[0057] See attached Figure 4 As shown, an embodiment of the present application provides an electronic device, including: a processor and a memory, the processor and the memory are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanisms (not shown), the memory stores a computer program executable by the processor, and when the computing device is running, the processor executes the computer program to execute the system in any optional implementation of the above embodiments.

[0058] The embodiment of the present application provides a storage medium, and when the computer program is executed by the processor, the system in any optional implementation of the above embodiment is executed. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0059] In the embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the modules is only a logical function division, and can be implemented in another way. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some communication interface, system or unit, which can be electrical, mechanical or other forms.

[0060] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0062] Flowcharts are used herein to illustrate the steps of the method of the embodiments of the present disclosure. It should be understood that the preceding or following steps are not necessarily performed precisely in order. On the contrary, various steps may be evaluated in reverse order or simultaneously. At the same time, other operations may also be added to these processes.

[0063] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0064] The above is a detailed introduction to the critically ill patient malnutrition risk prediction system based on XGBoost. This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only an embodiment of this application, which is only used to help understand the critically ill patient malnutrition risk prediction system based on XGBoost of this application, and is not used to limit the scope of protection of this application; at the same time, for those skilled in the art, this application may have various changes and variations. Any modifications and equivalent substitutions made within the spirit and principles of this application should be included in the scope of protection of this application.

Claims

1. The malnutrition risk prediction system for critically ill patients based on XGBoost is characterized by: Including information acquisition module and risk prediction module; The information acquisition module is used to obtain target physiological characteristics of the target patient; The risk prediction module also includes a model building submodule and a risk output submodule; the model building submodule also includes a parameter acquisition submodule, a model generation submodule and a model training submodule; the parameter acquisition submodule is used to obtain the training data set and target parameter value of the risk prediction model; The training data set includes all the physiological characteristics of the patients to be screened; the model generation module is used to build a risk prediction model based on the target parameter value and the XGBoost model; the risk prediction model includes several decision trees; the model training module is used to generate each decision tree based on the training data set and the target parameter value using the strategy of maximizing information gain; The information gain is obtained based on the difference between the minimum value of the objective function of the decision tree before the update and the minimum value of the objective function of the decision tree to be updated. The weight of each leaf node is obtained based on the minimum value of the objective function of the generated decision tree. The risk output submodule is used to obtain the trained risk prediction model and obtain the target risk of the target patient based on the output of the risk prediction model based on the target physiological characteristics.

2. The system according to claim 1, characterized in that The information acquisition module divides the target physiological characteristics into historical observation characteristics and target observation characteristics according to whether the acquisition time is the preset observation time; the system also includes a feature prediction module, which is used to predict the predicted physiological characteristics of the preset observation time according to the historical observation characteristics of the target patient; The risk output submodule also includes a risk calculation submodule and a risk verification submodule; The risk calculation module is used to obtain the predicted risk based on the predicted physiological characteristics before the preset observation time; The risk verification module is used to calculate the feature similarity between the predicted physiological features and the target observed features at a preset observation time. If the feature similarity is not less than the similarity threshold, the predicted risk is used as the target risk.

3. The system according to claim 2, characterized in that If the feature similarity is less than the similarity threshold, the risk verification module is further used to input the target observation feature into the risk calculation module and output the target risk.

4. The system according to claim 2, characterized in that The risk verification module also includes filtering target observation feature components from target observation features and filtering predicted physiological feature components from predicted physiological features according to corresponding feature items of intermediate nodes of all decision trees in the trained risk prediction model; The feature similarity is calculated based on the similarity between the predicted physiological feature components and the target observed feature components.

5. The system according to claim 4, characterized in that The feature items corresponding to all intermediate nodes in the trained risk prediction model are recorded as feature sets, and the calculation method of feature similarity includes: ； ； Wherein, m represents the number of all feature items in the feature set; α i represents the feature weight of the i-th feature item in the feature set, F 1，i represents the value of the i-th feature item of the target observation feature component in the feature set, F 2，i represents the value of the i-th feature item of the predicted physiological feature component in the feature set, N i It represents the difference between the maximum value and the minimum value of the i-th feature item in the feature set in the historical medical records.

6. The system according to claim 5, characterized in that The risk verification module also includes obtaining a corresponding feature weight according to the proportion of the number of intermediate nodes corresponding to each feature item in the feature set to the total number of intermediate nodes in the corresponding risk prediction model.

7. The system according to any one of claims 1 to 6, characterized in that: When training each decision tree, the proportion of randomly selected samples is less than 1. Before training each decision tree, the model training module obtains the current hit probability of each sample data in the training data set, and increases the hit probability of the sample data predicted incorrectly by the previous decision tree.

Images