Perioperative patient sample dataset equalization method and sample dataset acquisition system

Abstract

The application provides a perioperative patient sample dataset balancing method and a sample dataset acquisition system. The sample dataset balancing method comprises the following steps: S1, oversampling minority class label samples in a sample dataset of a perioperative patient to obtain synthetic samples, and generating a corresponding synthetic label set for the synthetic samples; the sample dataset comprises a plurality of samples and a sample corresponding classification label set; S2, adding the synthetic samples and the synthetic label set to the sample dataset to obtain a temporary sample dataset; and S3, cleaning the samples in the temporary sample dataset to obtain a balanced sample dataset. The minority class label samples in the sample dataset are oversampled to increase the number of minority class label samples, the majority class label samples and the minority class label samples are balanced, the noise samples are cleaned to improve the sample quality in the output balanced sample dataset, and the balanced sample dataset can improve the performance of a classification model during subsequent classification processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a perioperative patient sample dataset balancing method and a sample dataset acquisition system. BACKGROUND

[0002] Perioperative period refers to the whole process around the operation, from the patient deciding to accept the operation treatment to the operation treatment until the basic recovery, including the preoperative, intraoperative and postoperative period, specifically refers to from the time of determining the operation treatment to the end of the treatment related to the operation, the time is about 5-7 days before operation to 7-12 days after operation.

[0003] According to the data in the report World health statistics 2021 published by the World Health Organization (WHO), the global life expectancy has increased to 73.3 years, and it is estimated that there will be more than 1.5 billion elderly people in the world by 2050. The increasing elderly population around the world has been identified as the main group of the surgical operation market, and the prediction of risk events of elderly patients has become one of the hot research directions. Postoperative risk prediction for elderly surgical patient groups helps doctors develop treatment plans and reasonably allocate treatment resources, thereby reducing the probability of postoperative risk events. At present, some diagnostic tools can help hospitals provide comprehensive and reliable treatment for high-risk patients. For example, Chinese patents with publication numbers CN111009322A and CN114038565A have disclosed perioperative risk assessment based on a patient perioperative dataset using a prediction model. However, in the patient perioperative dataset, there is a problem of dataset label imbalance, which directly affects the performance of the perioperative prediction model. SUMMARY

[0004] The present application aims to solve the technical problems existing in the prior art and provide a perioperative patient sample dataset balancing method and a sample dataset acquisition system.

[0005] In order to achieve the above-mentioned purpose of the present application, according to the first aspect of the present application, a perioperative patient sample dataset balancing method is provided, comprising: step S1, using the MLSMOTE algorithm to oversample the minority class label samples in the sample dataset of the perioperative patient to obtain synthetic samples, and generating corresponding synthetic label sets for the synthetic samples, wherein the sample dataset comprises a plurality of samples and a sample corresponding classification label set; step S2, adding the synthetic samples to the sample dataset to obtain a temporary sample dataset; step S3, cleaning the samples in the temporary sample dataset to obtain a balanced sample dataset.

[0006] The technical scheme is: minority class label samples in the sample data set are oversampled to increase the number of minority class label samples, so as to balance the majority class label samples and the minority class label samples, in addition, noise samples generated in the process of generating the minority class label samples are cleaned in all samples, the sample quality in the output balanced sample data set is improved, the data is effectively enhanced, and when the balanced sample data set is used for subsequent classification processing, the performance effect of the classification model can be improved.

[0007] In order to achieve the above-mentioned purpose of the application, according to the second aspect of the application, the application provides a balanced device for a sample data set of a perioperative patient, comprising: a sample synthesis module, which uses an MLSMOTE algorithm to oversample minority class label samples in a sample data set of a perioperative patient to obtain synthetic samples, and generates a corresponding synthetic label set for the synthetic samples, wherein the sample data set comprises a plurality of samples and a sample corresponding classification label set; a temporary sample data set acquisition module, which adds the synthetic samples to the sample data set to obtain a temporary sample data set; and a cleaning module, which cleans the samples in the temporary sample data set to obtain a balanced sample data set.

[0008] The technical scheme is: minority class label samples in the sample data set are oversampled to increase the number of minority class label samples, so as to balance the majority class label samples and the minority class label samples, in addition, noise samples generated in the process of generating the minority class label samples are cleaned in all samples, the sample quality in the output balanced sample data set is improved, the data is effectively enhanced, and when the balanced sample data set is used for subsequent classification processing, the performance effect of the classification model can be improved.

[0009] In order to achieve the above-mentioned purpose of the application, according to the third aspect of the application, the application provides a sample data set acquisition system for a perioperative patient, comprising: a data acquisition module, which is used to acquire original perioperative feature data and cases of a plurality of patients; a classification label set acquisition module, which is used to acquire a classification label set based on a plurality of cases, wherein the classification label represents a risk event of a perioperative patient; a classification label association module, which is used to associate the original perioperative feature data of a patient with at least one classification label in the classification label set; a perioperative patient data dimension reduction device, which is used to perform dimension reduction processing on the original perioperative feature data of all patients to obtain corresponding perioperative feature data; a sample data set acquisition module, which uses the perioperative feature data of a patient as a sample, associates the sample with a corresponding classification label set of the original perioperative feature data, and acquires a sample data set of a perioperative patient; and a balanced device for a sample data set of a perioperative patient as described in the second aspect of the application, which is used to perform balanced processing on the sample data set.

[0010] The technical scheme is: a multi-classification label sample data set of patients in a perioperative period is constructed, the feature dimension of the samples in the data set is low and the features are those having great influence on subsequent classification, which can accelerate the efficiency of subsequent classification processing and model training; the number of minority class label samples is increased by a sample data set balancing device, so as to balance the majority class label samples and the minority class label samples, and the noise samples generated in the process of generating the minority class label samples by the MLSMOTE are cleaned in all samples, the quality of the samples in the output balanced sample data set is improved, the data is effectively enhanced, and when the balanced sample data set is used for subsequent classification processing, the performance effect of the classification model can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 FIG. 1 is a structural schematic diagram of a perioperative patient data dimension reduction device in embodiment 1 of the present application;

[0012] Figure 2 FIG. 2 is a structural schematic diagram of a perioperative patient sample data set acquisition system in embodiment 2 of the present application;

[0013] Figure 3 FIG. 3 is a flow schematic diagram of a sample data set balancing method in embodiment 3 of the present application;

[0014] Figure 4 FIG. 4 is a structural schematic diagram of a sample data set balancing device in embodiment 4 of the present application;

[0015] Figure 5 FIG. 5 is a structural schematic diagram of a sample data set acquisition system in embodiment 5 of the present application;

[0016] Figure 6 FIG. 6 is a flow schematic diagram of a perioperative patient data multi-label classification method in embodiment 6 of the present application;

[0017] Figure 7 FIG. 7 is a structural schematic diagram of a classification model in embodiment 6;

[0018] Figure 8 FIG. 8 is a preferred flow schematic diagram of a perioperative patient data multi-label classification method in embodiment 6;

[0019] Figure 9 FIG. 9 is a structural schematic diagram of a perioperative patient data multi-label classification device in embodiment 7 of the present application;

[0020] Figure 10 FIG. 10 is a structural schematic diagram of a perioperative patient risk event prediction system in embodiment 8 of the present application. DETAILED DESCRIPTION

[0021] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0022] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0023] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation", "connection" and "linking" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two components. They can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0024] Example 1

[0025] This embodiment discloses a perioperative patient data dimensionality reduction device, such as... Figure 1 As shown, the device includes:

[0026] The input module obtains the patient's original perioperative feature data containing multidimensional features, as well as the classification labels corresponding to the original perioperative feature data;

[0027] The initial dimensionality reduction module uses principal component analysis algorithm to reduce the dimensionality of the original perioperative feature data to obtain the first perioperative feature data.

[0028] The secondary dimensionality reduction module uses a genetic algorithm to reduce the dimensionality of the first perioperative feature data to obtain the perioperative feature data.

[0029] The output module outputs perioperative characteristic data.

[0030] In the embodiment, in order to better reflect the perioperative state of the patient, improve the accuracy of subsequent classification processing, and avoid the problem that postoperative patient data is not easy to collect and manage, preferably, the original perioperative feature data includes preoperative and intraoperative index data of the patient, such as blood pressure, heart rate, blood lipid before surgery, heart rate, blood pressure, blood loss, and operation duration during surgery. Unlike the existing part of the classification prediction model which only includes the preoperative basic condition of the surgical patient and does not consider the specific situation during the operation, numerous studies have confirmed that the intraoperative indicators such as heart rate, blood pressure, blood loss, and operation time are related to the postoperative situation of the patient, so the original perioperative feature data provided in the embodiment can improve the accuracy of the subsequent model in predicting postoperative events, and does not depend on postoperative patient index data.

[0031] In the embodiment, the classification label is used to represent the perioperative patient risk event, and the perioperative patient risk event preferably but not limited to includes unplanned readmission and death.

[0032] In the embodiment, in order to improve the richness of the data, the index data includes category data and numerical data, the category data is index data represented by categories, such as a lot, medium, and little for intraoperative blood loss, and the numerical data is index data represented by numerical values, such as blood pressure values.

[0033] In the embodiment, the original perioperative feature data can be the data of the patient with a known perioperative patient risk event, so the known perioperative patient risk event can be associated with the corresponding classification label of the original perioperative feature data. The original perioperative feature data can also be the data of the patient with an unknown perioperative patient risk event, and the corresponding classification label of the original perioperative feature data is set by an expert. The classification label corresponding to the original perioperative feature data can be one, two, or more.

[0034] In the embodiment, after the principal component analysis algorithm processing, the feature dimension of the first perioperative feature data is smaller than that of the original perioperative feature data, and the initial population of the genetic algorithm is constructed based on the first perioperative feature data.

[0035] In the embodiment, in order to further reduce the dimension of the first perioperative feature data by the genetic algorithm, preferably, the secondary dimension reduction module includes:

[0036] An initial population setting unit sets individuals based on the first perioperative feature data, the gene number of the individual is less than or equal to the total number of features in the first perioperative feature data, and a plurality of individuals form an initial population; the gene of the individual is a feature in the first perioperative feature data, and the gene number of each individual can be randomly set under the condition that the gene number of the individual is less than or equal to the total number of features in the first perioperative feature data;

[0037] The evolutionary iteration unit repeatedly performs the following processes until a termination condition is reached and outputs an individual with the maximum fitness when the termination condition is reached: obtaining the fitness of each individual in the current population; selecting part of the individuals in the current population as individuals of the next generation population based on the fitness of the individuals; and performing crossover operation and mutation operation on the individuals of the next generation population.

[0038] In the embodiment, the termination condition is preferably but not limited to that the number of evolutionary iterations reaches a preset maximum number of evolutionary iterations, or the maximum value of the fitness of the individuals in the evolutionary iterations no longer increases, or the increase amplitude of the maximum value of the fitness of the individuals in the evolutionary iterations is lower than an increase amplitude threshold. In each iteration, the fitness of the individuals in the current population is sorted from high to low, and part of the individuals with high ranks are selected as individuals of the next generation population. The crossover operation mainly exchanges the same gene sites of the paired parents, and obtains offspring after the exchange, which are used as individuals of the next generation population.

[0039] In the embodiment, to make the reduced perioperative feature data have more excellent performance in subsequent classification processing and improve the classification accuracy, preferably, the process of obtaining the fitness of the individual includes: obtaining original perioperative feature data of a plurality of patients and corresponding classification labels, performing dimensionality reduction processing on the plurality of original perioperative feature data according to the feature information of the individual to obtain a plurality of dimensionality reduction samples consistent with the feature of the individual; dividing the plurality of dimensionality reduction samples into a dimensionality reduction training set and a dimensionality reduction test set; constructing a dimensionality reduction multilayer perception neural network; training the constructed dimensionality reduction multilayer perception neural network using the dimensionality reduction training set to obtain a dimensionality reduction classification prediction model; testing the dimensionality reduction classification prediction model using the dimensionality reduction test set to obtain the accuracy of the model, and taking the accuracy as the fitness of the individual.

[0040] Embodiment 2

[0041] The embodiment discloses a perioperative patient sample data set obtaining system, which includes Figure 2As shown, the perioperative patient sample data set acquisition system comprises: a data acquisition module for acquiring original perioperative feature data and cases of a plurality of patients; the case data is generally text data, including doctor's diagnosis, medical history, postoperative follow-up records, etc.; a classification label set acquisition module acquires a classification label set based on a plurality of cases, and the classification label represents a perioperative patient risk event; a classification label association module is used to associate the original perioperative feature data of the patient with at least one classification label in the classification label set, so that the original perioperative feature data corresponds to a classification label set, and the classification label set comprises at least one classification label; and the perioperative patient data dimension reduction device provided in Embodiment 1 is used to perform dimension reduction processing on the original perioperative feature data of all patients to obtain corresponding perioperative feature data; a sample data set acquisition module takes the perioperative feature data of the patient as a sample, associates the corresponding classification label set of the original perioperative feature data of the sample, and obtains a sample data set of the perioperative patient.

[0042] In this embodiment, preferably, the classification label set acquisition module specifically performs: performing word segmentation processing on the patient cases to obtain at least one postoperative event result (the postoperative event result is the perioperative patient risk event), performing similar word comparison on the postoperative event results of a plurality of patients by using a trained CBOW model to obtain a plurality of similar postoperative event result sets, matching the similar postoperative event result sets with an event dictionary, searching for classification labels matched with the similar postoperative event result sets from the event dictionary, and the plurality of classification labels constitute the classification label set.

[0043] In this embodiment, the CBOW Multi-Word Context Model model of Word2Vec is trained on a large amount of medical corpus, and the text information corresponding to the case set in this embodiment is subjected to word segmentation processing by using the PKUSEG word segmentation tool (PKUSEG can segment words in multiple fields, including an independent model in the medical field) to obtain a plurality of postoperative event results. The event dictionary is preferably but not limited to the Chinese version ICD-11 event dictionary of the International Classification of Diseases published by the World Health Organization, and the event dictionary contains a plurality of classification labels. Whether the similar postoperative event result set matches the event dictionary is preferably but not limited to judged by semantic similarity. If the semantic similarity of the two is greater than a preset similarity threshold, it is considered that the two match, otherwise they do not match.

[0044] In this embodiment, preferably, to impute missing values ​​in the data and improve data quality, a missing value imputation device is also included. This device imputes missing values ​​in the patient's original perioperative characteristic data and inputs the imputed original perioperative characteristic data into a perioperative patient data dimensionality reduction device for dimensionality reduction. The missing value imputation device preferably, but not limited to, uses existing RandomForestRegressor imputation, MissForest imputation, Mean imputation, or Median imputation methods for imputation.

[0045] In this embodiment, more preferably, the missing data filling device performs missing data filling processing on the original perioperative feature data based on a Bayesian Gaussian process latent variable model.

[0046] In this embodiment, data imputation for missing values ​​inevitably introduces uncertainty into the original perioperative feature dataset. This embodiment uses a Bayesian Gaussian process latent variable model (BGPLVM) to impute missing values ​​for numerical features, specifically including:

[0047] First, the observed test data vector y is approximately calculated. * ∈R N×M The probability density p(y) * |Y)(where N is the total number of patient samples and M is the total number of features), and the observed value y * The variational distribution of the relevant latent variables is q(x) * Once the model parameters and latent variables are learned, BGPLVM can be used to estimate missing values. in It is a vector y * The values ​​that can be observed in These are the missing values ​​that need to be predicted. Given partially observed points y * This embodiment aims to reconstruct the lost parts. Missing data are filled by learning low-dimensional embeddings of observable variables on a small, complete dataset. BGPLVM is trained on the complete dataset D, introducing latent variables X and new test latent variables x. * As mentioned above A row vector representing the measurements of a single patient. Represents known observations. To represent missing values, y is obtained by maximizing the following probability density. * The corresponding hidden variable x * The Gaussian probability distribution.

[0048]

[0049] Next, by maximizing in To optimize the variational distribution q(x) using the variational lower bound. * ), keep apart from q(x) * All optimizations except for those for predicting missing values ​​remain unchanged. This invention employs the standard Gaussian process prediction method, while simultaneously taking the input x * Uncertainties were also taken into account, because x * There exists a distribution q(x) * Similar to the GP prediction format, in order to predict... This invention first predicts That is, with y * Corresponding implicit function value

[0050]

[0051] For x * Marginalization will produce a multivariate density that is not fully Gaussian dependent, but based on the squared exponential kernel, It can be analyzed and processed; in this invention, it is used... The mean and covariance are used; the mean provides an estimate of missing values, while the variance quantifies the uncertainty associated with the mean estimate. Using the BGPLVM model, the latent space and model hyperparameters learned on the training set are distributed to obtain the average estimate for each feature containing missing values.

[0052] In this embodiment, to facilitate data processing, it is further preferably included an encoding device for encoding the original perioperative characteristic data, and inputting the encoded data into the missing data filling device. The encoding device preferably, but is not limited to, using existing one-hot encoding rules.

[0053] In this embodiment, to facilitate data processing, it is further preferably included a normalization device for normalizing the original perioperative characteristic data after encoding processing, and inputting the normalized data into a missing data filling device. The normalization device preferably, but is not limited to, using the standard deviation normalization method for normalization processing.

[0054] Example 3

[0055] This embodiment provides a method for balancing sample datasets of perioperative patients, such as... Figure 3 As shown, the sample dataset balancing method includes:

[0056] Step S1, oversample the minority class label samples in the sample dataset of the perioperative patients to obtain synthetic samples, generate a corresponding synthetic label set for the synthetic samples, the sample dataset includes a plurality of samples and a classification label set corresponding to the samples; each sample represents a perioperative feature dataset of a patient, which can be original perioperative feature data or perioperative feature data obtained after dimensionality reduction of the original perioperative feature data in Embodiment 1, and the classification label association process of the sample has been described in detail in Embodiment 1, which will not be repeated here.

[0057] Step S2, add the synthetic samples and the synthetic label set to the sample dataset to obtain a temporary sample dataset;

[0058] Step S3, clean the samples in the temporary sample dataset to obtain a balanced sample dataset.

[0059] In this embodiment, the minority class label samples in the sample dataset of the perioperative patients can be oversampled by SMOTE or SVM SMOTE or BorderlineSMOTE or K-Means SMOTE or SMOTE-NC to obtain synthetic samples and generate a corresponding synthetic label set for the synthetic samples. Preferably, to improve the balancing effect, the MLSMOTE algorithm is used to oversample the minority class label samples in the sample dataset of the perioperative patients to obtain synthetic samples and generate a corresponding synthetic label set for the synthetic samples. The MLSMOTE algorithm is a multi-label synthetic minority oversampling technique (Multi label Synthetic Minority Over-sampling Technique, MLSMOTE), which is commonly used to handle data imbalance problems in multi-label classification tasks. Its generation process includes: selecting minority class labels using the imbalance rate (Imbalance Rate, IR); nearest neighbor search: once a sample belonging to a minority label is selected as a seed sample, its nearest neighbors are searched; feature set generation: after selecting a neighborhood, synthetic samples are obtained by interpolation; synthetic label set generation: synthetic samples require a synthetic label set.

[0060] In this embodiment, since the MLSMOTE and other oversampling synthetic minority class sample algorithms will generate some noise samples in the process of synthesizing minority label samples, it is necessary to clean these noise samples, so step S3 is set to improve the quality of the sample dataset.

[0061] In this embodiment, preferably, to quickly determine the minority class labels in the sample dataset, the ratio of the number of samples corresponding to each classification label to the total number of samples in the sample dataset is calculated, and the classification label with a ratio less than a ratio threshold is regarded as a minority class classification label, and the classification label with a ratio greater than or equal to the ratio threshold is regarded as a majority class classification label. The ratio threshold is preferably but not limited to less than 0.2.

[0062] In the embodiment, the number of samples to be generated for each minority class label is the oversampling rate of the minority class label. To better determine the oversampling rate of each minority class label so that the obtained balanced sample dataset performs better when applied to subsequent classification, preferably, in step S1, the oversampling rate of each minority class label is set based on a genetic algorithm, specifically including:

[0063] In step S11, the sample dataset includes W minority class labels, and the oversampling rates of the samples of the W minority class labels are W genes of an individual, W being a positive integer; each gene represents the oversampling rate of a minority class label, and an initial population is constructed using multiple individuals, the initial population including multiple initial individuals, and the values of the W genes of each initial individual are obtained by random selection, preferably, a value range can be set for the oversampling rate of each minority class label, and the values of the genes are randomly selected from the value range when the initial population is constructed, and the value range can be set as needed;

[0064] In step S12, the following evolutionary iteration process is repeatedly performed until a termination condition is reached: obtaining the fitness of each individual in the current population; selecting part of the individuals in the current population as individuals of the next generation population based on the fitness of the individuals; and performing crossover operation and mutation operation on the individuals of the next generation population;

[0065] In step S13, the individual with the maximum fitness when the termination condition is reached is output.

[0066] In the embodiment, the termination condition is preferably but not limited to that the number of evolutionary iterations reaches a preset maximum number of evolutionary iterations, or the maximum value of the fitness of the individuals in the evolutionary iterations no longer increases, or the increase amplitude of the maximum value of the fitness of the individuals in the evolutionary iterations is lower than an increase amplitude threshold. In each iteration, the fitness of the individuals in the current population is sorted from high to low, and part of the individuals ranked at the top are selected as the individuals of the next generation population.

[0067] In the embodiment, to make the obtained balanced sample dataset perform better when applied to subsequent classification, preferably, the process of obtaining the fitness of the individual includes:

[0068] The oversampling rate combination of the minority class labels is obtained based on the gene information of the individual; the oversampling rate combination includes the oversampling rates of all the minority class labels;

[0069] The minority class label samples in the sample dataset of the patients in the perioperative period are oversampled based on the oversampling rate combination of the minority class labels to obtain synthetic samples and a synthetic label set of the synthetic samples, the synthetic samples and the synthetic label set are added to the sample dataset to obtain a balanced sample set, and the balanced sample set is divided into a balanced training sample set and a balanced test sample set;

[0070] The balanced multi-layer perception neural network is constructed, the balanced multi-layer perception neural network is trained by using the balanced training sample set to obtain a balanced prediction classification model, the balanced prediction classification model is tested by using the balanced test sample set to obtain an accuracy rate of the balanced prediction classification model, and the accuracy rate is used as the fitness of the individual.

[0071] In the embodiment, to effectively remove the noise samples and improve the quality of the sample set, preferably, the step S3 is cleaning processing on each sample in the temporary sample data set, and the cleaning processing process includes:

[0072] In the step S31, a seed sample is selected from the temporary sample data set, k neighbor samples of the seed sample are selected, classification labels of the k neighbor samples form a neighbor classification label set, and k is a positive integer; each sample in the temporary sample data set can be sequentially selected as the seed sample.

[0073] In the step S32, the classification label set of the seed sample is predicted based on the neighbor classification label set by using a Bayesian conditional probability to obtain a predicted classification label set of the seed sample.

[0074] In the step S33, it is determined whether the predicted classification label set of the seed sample is same as the classification label set of the seed sample in the temporary sample data set, if yes, the seed sample is retained, and if no, the seed sample is deleted, and the seed sample is considered as a noise sample.

[0075] The cleaning process directly predicts the classification label set of the seed sample based on the neighbor classification label set of the seed sample by using the Bayesian conditional probability, compares and determines the obtained predicted classification label set and the true classification label set of the seed sample in the temporary sample data set, does not depend on the determination of the classifier, only depends on the determination of the data itself, reduces the operation amount, and improves the determination efficiency and accuracy.

[0076] In the embodiment, further preferably, in the step S31, the specific process of selecting the k neighbor samples of the seed sample includes:

[0077] The heterogeneous value difference metric HVDM of the seed sample and all or part of the samples in the temporary sample data set is obtained; HVDM is the abbreviation of Heterogeneous Value Difference Metric;

[0078] The heterogeneous value difference metric HVDM is corrected by using the global unbalanced weight of the samples in the temporary sample data set to obtain a corrected heterogeneous value difference metric.

[0079] The modified out-of-class value difference metrics of all samples in the temporary sample data set and the seed sample are sorted, and the first k samples with larger modified out-of-class value difference metrics are selected as the k neighbor samples of the seed sample. Preferably, the modified out-of-class value difference metrics can be sorted from high to low, and the first k samples with larger modified out-of-class value difference metric values are selected as the k neighbor samples of the seed sample.

[0080] The above process of selecting the k neighbor samples of the seed sample adopts a weighted KNN (Weighted kNN, WkNN) method to improve the quality of the synthetic samples. If the real minority class label samples in the sample data set are very scattered, that is, the space is sparse, the synthetic minority class samples in the execution process of the MLSMOTE algorithm and the like are still scattered and sparse, and in a local perspective, they are still not balanced. If kNN cleaning is directly used, the sparse minority class samples and the new minority class samples synthesized by MLSMOTE will be removed with a high probability, which cannot establish a proper classification boundary. Therefore, the distance weighting idea needs to be introduced to coordinate the kNN cleaning, that is, when facing sparse distributed samples, the local space density (that is, the out-of-class value difference metric HVDM and the global imbalance weight of the sample) is considered, and the small samples are retained as much as possible. The kNN cleaning mainly relies on the label set of the neighbor samples, so the distance calculation of the neighbor samples is particularly important when the data distribution is sparse, which is the main reason for adding distance weighting (that is, the global imbalance weight of the sample in the temporary sample data set is used to modify the out-of-class value difference metric HVDM). WkNN is used to clean the noise samples, changes the distance of the neighbor samples (the modified out-of-class value difference metric), that is, the local density is considered to represent the distance between samples.

[0081] In the embodiment, further preferably, the calculation formula of the out-of-class value difference metric HVDM of the seed sample and the samples in the temporary sample data set is:

[0082]

[0083] wherein f1 represents the feature vector of the seed sample; f2 represents the feature vector of any sample in the temporary sample data set except the seed sample; HVDM(f1, f2) represents the out-of-class value difference metric of the feature vectors f1 and f2; D(f1, f2) represents the distance between the feature vectors f1 and f2; n represents the feature dimension of the samples in the temporary sample data set; x represents the feature index; d x (f1, f2) represents the distance of the feature vector f1 and the feature vector f2 on the feature x, d x (f1, f2) is obtained by the following formula: C represents the number of categories of the feature x when the feature x is a category feature, and c represents the category index of the feature x. represents the number of samples in the temporary sample data set in which feature x belongs to feature vector f1 and the class feature of feature x is c; represents the number of samples in the temporary sample data set in which feature x belongs to feature vector f2 and the class feature of feature x is c; represents the number of samples in the temporary sample data set in which feature x belongs to feature vector f1; represents the number of samples in the temporary sample data set in which feature x belongs to feature vector f2; |f1-f2| represents the absolute value of the difference between feature vectors f1 and f2; σ x represents the standard deviation of feature x in the temporary sample data set.

[0084] In this embodiment, further preferably, the calculation formula of the modified heterogeneous value difference metric of the seed sample and the samples in the temporary sample data set is:

[0085]

[0086] wherein f1 represents the feature vector of the seed sample; f2 represents the feature vector of any sample in the temporary sample data set except the seed sample; HVDM(f1, f2) represents the heterogeneous value difference metric of feature vectors f1 and f2; D W (f1, f2) represents the modified heterogeneous value difference metric of feature vectors f1 and f2; n represents the feature dimension of the samples in the temporary sample data set; IW represents the global imbalance weight of the sample with feature vector f2, IW = IR nn / (IR + +IR - ), IR + represents the total imbalance rate of all minority class classification labels in the temporary sample data set, IR - represents the total imbalance rate of all majority class classification labels in the temporary sample data set, IR nn is the total imbalance rate of all classification labels in the classification label set of the sample with feature vector f2.

[0087] In the above noise sample removal process, Heterogeneous Value Difference Metric (HVDM) is used for distance measurement when WkNN calculates the distance, and the global imbalance weight IW of the sample is used as the weight coefficient to modify HVDM. For the temporary sample data set, the more the minority class labels contained in the classification label set, the larger IR nn will be, and for the temporary sample data set with sparse distribution of minority class label samples and large imbalance rate, the introduction of IW into HVDM distance can improve the density of minority class samples.

[0088] From the formula it can be seen that the weight coefficient The value of the weighted coefficient can scale the HVDM(f1, f2), and the more minority class labels in the label set of the neighbor sample, the smaller the weighted coefficient The more minority class labels in the label set of the neighbor sample, the smaller the weighted coefficient of the corresponding neighbor sample. When the IW of the neighbor sample set of the seed sample is larger, that is, the more minority class labels contained in the label set of the neighbor sample, the smaller the weighted coefficient of the corresponding neighbor sample The more minority class labels in the label set of the neighbor sample, the smaller the weighted coefficient of the corresponding neighbor sample. When the IW of the neighbor sample set of the seed sample is larger, that is, the more minority class labels contained in the label set of the neighbor sample, the smaller the weighted coefficient of the corresponding neighbor sample The more minority class labels in the label set of the neighbor sample, the smaller the weighted coefficient of the corresponding neighbor sample. When the IW of the neighbor sample set of the seed sample is larger, that is, the more minority class labels contained in the label set of the neighbor sample, the smaller the weighted coefficient of the corresponding neighbor sample

[0089] It can be seen that WkNN can help filter neighbor samples for samples with more minority class labels in the label set, taking into account the distribution of labels in the label set of the neighbor sample, so that samples with more minority class labels in the label set are closer to the seed sample, increasing the local minority class label density and reducing the majority class label density. The overall process is as follows: first, use MLSMOTE to oversample the minority class labeled samples to form a relatively balanced temporary new sample set with the original samples. In this new sample set, each sample is subjected to the WkNN process, that is, the k nearest neighbors are sorted based on the weighted HVDM, and then the label set of the seed sample is predicted according to the neighbor samples. If the predicted label set is the same as the seed label set, the sample is retained, otherwise it is deleted

[0090] Embodiment 4

[0091] The embodiment discloses a sample data set balancing device for a patient in a perioperative period, as shown in the figure, the sample data set balancing device comprises: Figure 4

[0092] The sample synthesis module oversamples the minority class label samples in the sample data set of the patient in the perioperative period to obtain synthetic samples, and generates corresponding synthetic label sets for the synthetic samples. The sample data set comprises a plurality of samples and a classification label set corresponding to the samples.

[0093] The temporary sample data set acquisition module adds the synthetic samples and the synthetic label sets to the sample data set to obtain a temporary sample data set.

[0094] The cleaning module cleans the samples in the temporary sample data set to obtain a balanced sample data set.

[0095] In the embodiment, preferably, the cleaning module comprises:

[0096] The neighbor sample acquisition unit selects a seed sample from the temporary sample data set, selects k neighbor samples of the seed sample, and the classification labels of the k neighbor samples form a neighbor classification label set. K is a positive integer. ​

[0097] a prediction classification label set acquisition unit, which predicts the classification label set of the seed sample based on the classification label set of the neighbor sample through Bayesian conditional probability, and obtains the prediction classification label set of the seed sample;

[0098] a cleaning unit, which judges whether the prediction classification label set of the seed sample is the same as the classification label set of the seed sample in the temporary sample data set, and if yes, the seed sample is kept, and if not, the seed sample is deleted.

[0099] In the embodiment, further preferably, the specific process in which the neighbor sample acquisition unit selects the k neighbor samples of the seed sample comprises:

[0100] obtaining the heterogeneous value difference measure HVDM of the seed sample and all or part of the samples in the temporary sample data set respectively;

[0101] correcting the heterogeneous value difference measure HVDM by using the global imbalance weight of the samples in the temporary sample data set to obtain a corrected heterogeneous value difference measure;

[0102] sorting the corrected heterogeneous value difference measures of all the samples in the temporary sample data set and the seed sample, and selecting the k samples with larger corrected heterogeneous value difference measures as the k neighbor samples of the seed sample.

[0103] The balancing effect of the sample data set balancing device provided in the embodiment is verified by experiment, and the results are as follows:

[0104]

[0105] IR represents the imbalance rate Imbalance Rate of the sample set, and the larger the IR, the more unbalanced the sample set. As can be seen from the experimental results in the above table, the maximum IR and the average IR of the balancing device provided in the embodiment are the smallest, and the interval between the maximum value and the average value of IR is narrowed, which indicates that the balancing of the sample set is better.

[0106] Embodiment 5

[0107] The embodiment also discloses a perioperative patient sample data set acquisition system. Compared with the embodiment 2, the embodiment adds a sample data set balancing device, i.e. the sample balancing processing is performed on the sample data set obtained after the dimension reduction in the embodiment 2. The structural schematic diagram of the device is as shown in Figure 5As shown, the method comprises: a data acquisition module, configured to acquire original perioperative feature data and cases of a plurality of patients; a classification label set acquisition module, configured to acquire a classification label set based on the plurality of cases, the classification label set representing a perioperative patient risk event; a classification label association module, configured to associate the original perioperative feature data of the patient with at least one classification label in the classification label set; a perioperative patient data dimension reduction device, configured to perform dimension reduction processing on the original perioperative feature data of all patients to obtain corresponding perioperative feature data; a sample data set acquisition module, configured to take the perioperative feature data of the patient as a sample, associate the sample with a corresponding classification label set of the original perioperative feature data, and obtain a sample data set of the perioperative patient; and a perioperative patient sample data set balancing device provided in Embodiment 4, configured to perform balancing processing on the sample data set.

[0108] In this embodiment, preferably, a missing value filling device is further included, configured to perform filling processing on missing values in the original perioperative feature data of the patient, and input the original perioperative feature data after the filling processing into the perioperative patient data dimension reduction device for dimension reduction processing.

[0109] Embodiment 6

[0110] This embodiment 6 discloses a perioperative patient data multi-label classification method, as shown in the method comprises: Figure 6 As shown, the multi-label classification method comprises:

[0111] Step A, acquiring patient feature data to be classified; the patient feature data to be classified is perioperative patient feature data, which can include multi-dimensional features. To improve the processability of the patient feature data to be classified, reduce the dimension, and improve the quality, the patient feature data to be classified can be sequentially subjected to encoding processing, normalization processing, and dimension reduction processing according to the feature dimension of the sample output by the perioperative patient data dimension reduction device provided in Embodiment 1, and the patient feature data to be classified after the dimension reduction processing is input into the trained classification model.

[0112] Step B, inputting the patient feature data to be classified into the trained classification model, and the classification model outputs a classification result, the classification result comprising one or more classification labels and a classification confidence of each classification label; the classification confidence of the classification label represents a probability that the patient feature data to be classified belongs to the classification label. The classification model comprises a classification ensemble model based on Stacking, a label association rule acquisition module, and a fusion module, the fusion module being configured to fuse a classification matrix output by the classification ensemble model and an association rule matrix output by the label association rule acquisition module to obtain the classification result, and the fusion manner is preferably but not limited to multiplying the classification matrix and the association rule matrix.

[0113] In the embodiment, preferably, a structure diagram of the classification model is as shown in Figure 7As shown, the classification ensemble model includes a first multi-classification model, a second multi-classification model, a third multi-classification model, and a logistic regression model; the first multi-classification model, the second multi-classification model, and the third multi-classification model respectively perform multi-label classification processing on the patient feature data to be classified to obtain first, second, and third primary classification results; and the logistic regression model processes the first, second, and third primary classification results to obtain a classification matrix.

[0114] In this embodiment, preferably, the first multi-classification model, the second multi-classification model, and the third multi-classification model are respectively a Ranking-SVM model, a classification multi-layer perception neural network model, and a Binary Relevance model. The Ranking-SVM model and the Binary Relevance model are relatively conventional base models in the Stacking ensemble, and the use thereof in model ensemble has high reliability. The classification multi-layer perception neural network model adopts a multi-layer perception neural network structure (i.e., an MLP network structure), can avoid overfitting problems, and has low complexity.

[0115] In this embodiment, preferably, the method further includes a step of constructing a sample data set of patients in a perioperative period, such as Figure 8 As shown, the step of constructing the sample data set of patients in the perioperative period is preferably but not limited to being constructed by using the system of Embodiment 2 or Embodiment 5.

[0116] In this embodiment, as shown in Figure 7 As shown, the training process of the classification ensemble model is as follows: a sample data set of patients in a perioperative period is constructed, each sample in the sample data set is associated with one or more classification labels, the sample data set is divided into a classification training set and a classification test set, and the association of the classification labels can be performed in an artificial manner; a classification ensemble model, i.e., the above-mentioned Stacking-based ensemble model, is constructed, which includes a first multi-classification model, a second multi-classification model, a third multi-classification model, and a logistic regression model; the classification ensemble model is trained by using the classification training set, and the trained classification ensemble model is tested and verified by using the classification test set. In the verification, RandomizedSearchCV and GridSearchCV are used to perform cross-validation on the training set, and the selection of hyperparameters is performed by using F1_Micro scores.

[0117] In this embodiment, as shown in Figure 7As shown, preferably, the association rule acquisition module performs the following steps: acquiring a sample data set of the perioperative patient, each sample in the sample data set being associated with more than one classification label; the sample data set is preferably but not limited to the sample data set of the perioperative patient acquired in Embodiment 2 or Embodiment 5, i.e., the standard patient data set. Association rule mining is performed on the classification labels in the sample data set to obtain an association rule matrix. The association rule matrix includes the association confidence between any two of the classification labels.

[0118] In this embodiment, as shown in Figure 7 , it is further preferred that, when the number of classification labels in the sample data set is small, specifically when the number is less than a number threshold, the classification labels in the sample data set are directly subjected to association rule mining by the FP-growth algorithm. First, a classification label matrix as shown in Figure 7 is established, in which the first row is the labels and the first column is the patient number; then, the FP-growth algorithm is used to perform association rule analysis and processing on the classification label matrix, and the association confidence between any two classification labels is output, with the association confidence taking a value in the range of 0 to 1. Based on these association confidences, an association rule matrix as shown in Figure 7 is established, in which the first row and the first column are both classification labels, and the elements in the matrix represent the association confidence between the classification labels in the row and the column of the element, as shown in Figure 7 , in which A(N-1) represents the association confidence between classification label N and classification label 1.

[0119] In this embodiment, preferably, when the number of classification labels in the sample data set is large, the correlation patterns between the classification labels are different, and direct association analysis may cause the frequent item set finding process to be complex and affect the accuracy of the association analysis. Specifically, when the number of classification labels is greater than or equal to a number threshold, the number threshold is preferably but not limited to 3 or 4 or 5. The steps of performing association rule mining on the classification labels in the sample data set to obtain an association rule matrix specifically include:

[0120] The classification labels in the sample data set are clustered to obtain more than one cluster; preferably but not limited to, the K-means++ algorithm is used for clustering processing; the classification labels in each cluster are subjected to association rule mining to obtain an association rule sub-matrix. In the fusion, the classification matrix is divided into more than one sub-classification matrix according to the clustering results, one cluster corresponds to one sub-classification matrix, the sub-classification matrix and the association rule sub-matrix corresponding to the cluster are multiplied to obtain the classification sub-result of the cluster, and all classification sub-results constitute the classification result.

[0121] In this embodiment, more preferably, the association rule submatrix is ​​obtained by mining association rules for the classification labels in each classification cluster using the FP-growth algorithm. The acquisition process is as follows: Figure 7 The process is consistent and has been explained in detail in the above preferred solutions, so it will not be repeated here.

[0122] Example 7

[0123] This embodiment discloses a multi-label classification device for perioperative patient data, such as... Figure 9 As shown, it includes: a data acquisition module for acquiring feature data of patients to be classified; a classification module for inputting the feature data of patients to be classified into a trained classification model, and the classification model outputs classification results, which include one or more classification labels and the classification confidence of each classification label; the classification model includes a stacking-based classification ensemble model, a label association rule acquisition module, and a fusion module, which is used to fuse the classification matrix output by the classification ensemble model and the association rule matrix output by the label association rule acquisition module to obtain the classification results.

[0124] In this embodiment, preferably, the classification ensemble model includes a first multi-classification model, a second multi-classification model, a third multi-classification model, and a logistic regression model; the first multi-classification model, the second multi-classification model, and the third multi-classification model respectively perform multi-label classification processing on the patient feature data to be classified to obtain a first primary classification result, a second primary classification result, and a third primary classification result; the logistic regression model processes the first primary classification result, the second primary classification result, and the third primary classification result to obtain a classification matrix.

[0125] In this embodiment, preferably, it also includes a classification ensemble model training module, which performs the following processes: constructing a sample dataset of perioperative patients, wherein each sample in the sample dataset is associated with more than one classification label, and dividing the sample dataset into a classification training set and a classification test set; preferably, but not limited to, constructing the sample dataset of perioperative patients using the system provided in Embodiment 2 or Embodiment 5; constructing a classification ensemble model; the classification ensemble model includes a first multi-class model, a second multi-class model, a third multi-class model, and a logistic regression model; training the classification ensemble model using the classification training set, and testing and verifying the trained classification ensemble model using the classification test set.

[0126] In the embodiment, the classification device builds a perioperative postoperative event multi-label classification integrated model combined with association rule analysis. Multiple postoperative risk events can occur after surgery. To predict postoperative multi-event outcomes, an integrated Ranking-SVM model, a multi-layer perception neural network model, and a Binary Relevance model are used to build a multi-label prediction model. To further improve the stability and accuracy of the model, association rules are integrated into the prediction model for optimization.

[0127] Embodiment 8

[0128] The embodiment discloses a perioperative patient risk event prediction system, as shown in Figure 10 The system comprises a data acquisition module for acquiring patient feature data to be classified; a classification module for inputting the patient feature data to be classified into a trained classification model, wherein the classification model outputs a classification result, the classification result comprises one or more classification labels and a classification confidence of each classification label, and each classification label corresponds to a perioperative patient risk event.

[0129] The classification model comprises a classification integrated model based on Stacking, a label association rule acquisition module, and a fusion module. The fusion module is used to fuse the classification matrix output by the classification integrated model and the association rule matrix output by the label association rule acquisition module to obtain the classification result. A conversion module converts the classification labels in the classification result into corresponding perioperative patient risk events to obtain a risk prediction result.

[0130] In the embodiment, preferably, the classification integrated model comprises a first multi-classification model, a second multi-classification model, a third multi-classification model, and a logistic regression model. The first multi-classification model, the second multi-classification model, and the third multi-classification model perform multi-label classification processing on the patient feature data to be classified to obtain a first primary classification result, a second primary classification result, and a third primary classification result, respectively. The logistic regression model processes the first primary classification result, the second primary classification result, and the third primary classification result to obtain a classification matrix.

[0131] In the embodiment, preferably, the system further comprises a classification integrated model training module, which performs the following processes: constructing a sample data set of perioperative patients, each sample in the sample data set being associated with one or more classification labels; dividing the sample data set into a classification training set and a classification test set; preferably, but not limited to, constructing the sample data set of perioperative patients by using the system provided in Embodiment 2 or Embodiment 5; constructing a classification integrated model; the classification integrated model comprises a first multi-classification model, a second multi-classification model, a third multi-classification model, and a logistic regression model; training the classification integrated model using the classification training set; and testing and verifying the trained classification integrated model using the classification test set.

[0132] In this embodiment, the system sample data set acquisition process provided in Embodiment 2 or Embodiment 5 is implemented to predict the risk events of patients (especially elderly surgical patients) during the perioperative period. On the basis of improving the missing and unbalanced data set, the association rule analysis is fused to build a postoperative event multi-label prediction model. Based on the patient case text, the postoperative event label is extracted, the CBOW label extraction model of Word2Vec is used, a large amount of medical related corpus is collected, the medical word vector model is trained, and the postoperative event label set (i.e. the classification label set) extraction is realized. Next, the missing data is filled based on the Bayesian Gaussian process latent variable model, and the label unbalanced data is processed based on the MLSMOTE, the weighted kNN (WKNN) and the genetic algorithm, and finally the feature dimension reduction model is built in combination with the principal component analysis PCA model and the genetic algorithm to provide the classification integrated model with higher relevance input.

[0133] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. A perioperative patient sample dataset equalization method, comprising: The method comprises the following steps: Step S1, using the MLSMOTE algorithm to oversample the minority class label samples in the sample data set of the perioperative patients to obtain synthetic samples, and generating a corresponding synthetic label set for the synthetic samples, wherein the sample data set comprises a plurality of samples and a classification label set corresponding to the samples; Step S2, adding the synthetic samples and the synthetic label set to the sample data set to obtain a temporary sample data set; Step S3, cleaning the samples in the temporary sample data set to obtain a balanced sample data set, wherein the step S3 is a cleaning process for each sample in the temporary sample data set, and the cleaning process comprises the following steps: Step S31, selecting a seed sample from the temporary sample data set, selecting k neighbor samples of the seed sample, and obtaining a neighbor classification label set comprising the classification labels of the k neighbor samples, wherein k is a positive integer; Step S32, predicting the classification label set of the seed sample based on the neighbor classification label set by using the Bayesian conditional probability to obtain a predicted classification label set of the seed sample; Step S33, determining whether the predicted classification label set of the seed sample is the same as the classification label set of the seed sample in the temporary sample data set, and if so, retaining the seed sample, and if not, deleting the seed sample; In the step S31, the specific process of selecting the k neighbor samples of the seed sample comprises the following steps: obtaining a heterogeneous value difference measure (HVDM) between the seed sample and all or part of the samples in the temporary sample data set; correcting the heterogeneous value difference measure (HVDM) by using the global imbalance weight of the samples in the temporary sample data set to obtain a corrected heterogeneous value difference measure; sorting the corrected heterogeneous value difference measures between all the samples in the temporary sample data set and the seed sample, and selecting the k samples with the largest corrected heterogeneous value difference measures as the k neighbor samples of the seed sample; wherein the calculation formula of the corrected heterogeneous value difference measure between the seed sample and the samples in the temporary sample data set is as follows: D W (f1,f2) = e (1-IW)n • HVDM(f1,f2); wherein f1 represents a feature vector of a seed sample; f2 represents a feature vector of any sample in the temporary sample dataset except the seed sample; HVDM(f1, f2) represents a heterogeneous value difference measure of the feature vectors f1 and f2; D W (f1, f2) represents a modified heterogeneous value difference measure of the feature vectors f1 and f2; n represents a feature dimension of a sample in the temporary sample dataset; IW represents a global imbalance weight of the sample with the feature vector f2, IW = IR nn / (IR + + IR - ), IR + represents a total imbalance rate of all minority class classification labels in the temporary sample dataset, IR - represents a total imbalance rate of all majority class classification labels in the temporary sample dataset, IR nn is a total imbalance rate of all classification labels in the classification label set of the sample with the feature vector f2.

2. The perioperative patient sample dataset equalization method of claim 1, wherein, In the step S1, the genetic algorithm is used to set an oversampling rate for each minority class label, and the specific process comprises the following steps: Step S11, setting W minority class labels in the sample data set, taking the oversampling rates of the samples of the W minority class labels as W genes of an individual, wherein W is a positive integer; constructing an initial population, wherein the initial population comprises a plurality of initial individuals, and the W gene values of each initial individual are obtained by random selection; Step S12, repeatedly executing the following evolutionary iteration process until a termination condition is reached: obtaining the fitness of each individual in the current population; selecting part of the individuals in the current population as individuals in the next generation population based on the fitness of the individuals; and performing a crossover operation and a mutation operation on the individuals in the next generation population; Step S13, outputting the individual with the maximum fitness when the termination condition is reached.

3. The perioperative patient sample dataset equalization method of claim 2, wherein, The process of obtaining the fitness of an individual comprises the following steps: obtaining a minority class label oversampling rate combination based on the gene information of the individual; and the oversampling rate combination comprises the oversampling rates of all the minority class labels. The minority class label samples in the sample data set of the perioperative patient are oversampled based on a minority class label oversampling rate combination to obtain synthetic samples and a synthetic label set of the synthetic samples, the synthetic samples and the synthetic label set are added to the sample data set to obtain a balanced sample set, and the balanced sample set is divided into a balanced training sample set and a balanced test sample set; A balanced multi-layer perception neural network is constructed, the balanced multi-layer perception neural network is trained by using the balanced training sample set to obtain a balanced prediction classification model, the balanced prediction classification model is tested by using the balanced test sample set to obtain an accuracy rate of the balanced prediction classification model, and the accuracy rate is taken as the fitness of the individual.

4. The perioperative patient sample dataset equalization method of claim 1, wherein, A calculation formula of a heterogeneous value difference metric HVDM of the seed sample and the samples in the temporary sample data set is: wherein f1 represents a feature vector of a seed sample; f2 represents a feature vector of any sample in the temporary sample dataset except the seed sample; HVDM(f1, f2) represents a heterogeneous value difference metric of the feature vector f1 and the feature vector f2; D(f1, f2) represents a distance between the feature vector f1 and the feature vector f2; n represents a feature dimension of a sample in the temporary sample dataset; x represents a feature index; d x (f1, f2) represents a distance of the feature vector f1 and the feature vector f2 on the feature x, d x (f1, f2) is obtained by the following formula: C represents the number of categories of the feature x when the feature x is a category feature, c represents the category index of the feature x, represents the number of samples in the temporary sample data set in which the feature x belongs to the feature vector f1 and the category feature of the feature x is c; represents the number of samples in the temporary sample data set in which the feature x belongs to the feature vector f2 and the category feature of the feature x is c; represents the number of samples in the temporary sample data set in which the feature x belongs to the feature vector f1; represents the number of samples in the temporary sample data set in which the feature x belongs to the feature vector f2; |f1-f2| represents the absolute value of the difference between the feature vectors f1 and f2; σ x represents the standard deviation of the feature x in the temporary sample data set.

5. A perioperative patient sample dataset equalization apparatus for implementing the perioperative patient sample dataset equalization method of any one of claims 1-4, characterized by, The method comprises the following steps: A sample synthesis module is configured to oversample the minority class label samples in the sample data set of the perioperative patient to obtain synthetic samples, and generate a corresponding synthetic label set for the synthetic samples, wherein the sample data set comprises a plurality of samples and a classification label set corresponding to the samples; A temporary sample data set acquisition module is configured to add the synthetic samples and the synthetic label set to the sample data set to obtain a temporary sample data set; A cleaning module is configured to clean the samples in the temporary sample data set to obtain a balanced sample data set.

Images