A method and system for predicting the risk of unplanned readmission

Abstract

This invention proposes a disease risk prediction method and system for unplanned readmission. This method constructs a dynamic classifier selection framework; sets binary variables representing medical diagnoses as rule sets, and uses these rule sets as extraction rules to extract several data subsets from a dataset; trains several base classifiers based on the data subsets to form a classifier pool; defines capability regions and meta-features, which are criteria for measuring the capability of each base classifier in the classifier pool within the capability regions; uses the base classifiers within the capability regions to extract meta-features from the dataset; trains the meta-classifier using the meta-features as the training set for the meta-classifier in the dynamic classifier selection framework; uses the meta-classifier to calculate the capability scores of each base classifier in the classifier pool; selects the base classifier with the highest capability score as the classifier ensemble pool; and predicts the samples to be predicted within the trained dynamic classifier selection framework. This method has high prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for predicting the risk of unplanned hospital readmission. Background Art

[0002] Cirrhosis is a serious condition and the common culprit for most chronic liver diseases, including chronic hepatitis B, hepatitis C, alcohol-related liver disease, and nonalcoholic fatty liver disease. Compared to other chronic conditions, chronic liver disease leads to higher hospitalization rates, longer hospital stays, and more readmissions. Studies have shown that readmission rates for patients with cirrhosis range from 10% to 50% within 7 to 90 days after discharge, with the majority of these readmissions being unplanned. A significant proportion of these unplanned readmissions are avoidable. Early identification of high-risk patients allows for proactive interventions, thereby improving healthcare outcomes.

[0003] In recent years, electronic health records (EHRs), or electronic medical records (EMRs), have been widely used in various clinical and research fields, and machine learning algorithms have achieved great success in mining EHR data. The various clinical indicators captured in EHRs, such as laboratory results and vital signs, provide data support for the development of cutting-edge predictive models that can provide useful guidance for clinical decision-making. For example, Kenneth Berman et al. conducted a study using data from inpatient hepatology departments at two large academic medical centers to conduct multivariate analysis to identify variables associated with 30-day readmission and investigate their association with 90-day mortality in patients with advanced liver disease. Chang Hu, Vikram Amjur et al. used logistic regression (LR), kernel support vector machines (SVM), and random forest classifiers (RF) to analyze the 30-day and 90-day readmissions of a cohort of hospitalized patients with cirrhosis from the North American Consortium for the Study of End-Stage Liver Disease (NACSELD). Various other machine learning methods, including Bayesian conditional probability, deep learning, gradient boosting, and novel ensemble methods, have also been used to develop risk prediction models for hospital readmission.

[0004] Although electronic health records provide rich information, the diversity of patients and data-related issues such as high dimensionality, incompleteness, sparsity, and temporal dynamics still pose many challenges that have not yet been fully addressed. A single machine learning model using the same feature set is usually not sufficient to effectively address the above challenges, so a multi-classifier system (MCS) is proposed.

[0005] Multi-classifier systems typically perform better than single models by combining the outputs of multiple base classifiers. The principle of this technique is that not every classifier is an expert on all unknown samples. Instead, each base classifier is an expert in a different local area in the feature space. The development of a multi-classifier system usually includes three key steps: classifier pool generation, classifier selection, and classifier aggregation. The goal of the classifier pool generation step is to create a diverse set of classifiers that can complement each other to reduce errors in prediction. In order to explore diversity, a common strategy is to train classifiers using a subset of instances or a subset of the feature space. Once the classifier pool is generated, the next key step is to select the appropriate base classifier for the specific task.

[0006] Dynamic Ensemble Selection (DES) is a class of ensemble learning techniques that performs on-the-fly selection of base classifiers during inference. Dynamic Ensemble Selection works by estimating the ability of classifiers in a pool of classifiers in a local region of feature space. This local region is typically defined by the neighborhood of a query example.

[0007] Heterogeneous classifiers can be selected and fused for unknown test instances at inference time. In particular, the META-DES framework assumes that the dynamic classifier selection problem can be viewed as a meta-problem. After generating a pool of classifiers, meta-features associated with different base classifiers are extracted using the training and dynamic selection datasets. These meta-features are then used to train a meta-classifier to estimate whether the base classifiers are able to correctly classify samples. When a new test instance is given, meta-features are extracted from the test instance and input to the trained meta-classifier to estimate the ability level of each base classifier. Based on these estimated abilities, the most capable classifiers are selected and fused for the final decision-making process.

[0008] It is worth noting that applying existing dynamic ensemble selection algorithms does not necessarily outperform state-of-the-art ensemble models in tabular data classification, and developing data-driven methods for tasks such as readmission risk prediction is challenging from multiple perspectives. First, due to the complexity and diversity of hospitalization and discharge processes, commonly used machine learning models struggle to achieve high accuracy in predicting readmission risk within a certain timeframe. Second, real-world electronic health record data has inherent limitations and quality issues, including incompleteness, sparsity, and temporal dynamics. Existing technologies are unable to overcome these problems. Summary of the Invention

[0009] In order to overcome the above-mentioned defects in the prior art, the purpose of the present invention is to provide a disease risk prediction method and system for unplanned readmission.

[0010] In order to achieve the above-mentioned object of the present invention, the present invention provides a disease risk prediction method for unplanned readmission, comprising the following steps:

[0011] Obtain disease datasets;

[0012] A dynamic selection classifier is constructed based on the DES framework. The dynamic selection classifier includes several basic classifiers and a meta-classifier. The dynamic selection classifier is trained based on the data set:

[0013] Setting a number of interpretable binary variables representing medical diagnoses as a rule set, and extracting the rule set from the data set into a number of data subsets as extraction rules;

[0014] Training the basic classifier based on the data subset to obtain a classifier pool;

[0015] defining a capability region and a criterion for measuring the capability of each basic classifier in the classifier pool within the capability region, wherein one of the criteria includes the binary variable, and the criterion is used as a meta-feature;

[0016] Extracting meta-features from a data set using the base classifier within the capability region;

[0017] Training the meta-classifier using the meta-features as a training set for training the meta-classifier;

[0018] Use the meta-classifier to calculate the ability score of each base classifier in the classifier pool when predicting each set of data;

[0019] The base classifier with the highest ability score is selected as the best classifier for predicting the corresponding data;

[0020] The prediction result of the best classifier is taken as the final prediction result.

[0021] This method has high prediction accuracy and also allows for the generation of classifier pools and dynamic selection of classifiers in an interpretable manner. In the dynamic classifier selection stage, the method selects the classifier with the highest ability score for prediction, and an optimal classifier is selected for each individual to predict the risk of readmission. When the selected base classifier itself is understandable and interpretable, its prediction can be directly explained and understood. For example, models such as logistic regression LR, decision tree DT, and K-nearest neighbor KNN are interpretable as base classifiers. If the base classifier is an uninterpretable model, SHAP can be used to explain the entire prediction result.

[0022] Optionally, part of the data in the data set is used as a training set, and a set of rules representing binary variables of medical diagnosis is extracted from each training sample, and all the rules form the rule set.

[0023] In an optional solution of the disease risk prediction method for unplanned readmission, the capability area includes a first capability area and a second capability area;

[0024] The first capability region is a neighborhood surrounding the predicted data sample, the data samples in the neighborhood are similar samples to the predicted data sample, and the first component feature is extracted in the first capability region;

[0025] The second capability area is based on medical diagnosis data containing the binary variable, and second component features are extracted within the second capability area.

[0026] In an optional solution of the disease risk prediction method for unplanned readmission, the first component features include a standard for measuring local accuracy within the first capability area, a degree of consensus within the first capability area, an overall accuracy within the first capability area, accuracy in the decision space, and a degree of confidence of an input sample;

[0027] The second component characteristics include local accuracy within a second capability region.

[0028] Optionally, the interpretable binary variable representing a medical diagnosis is the presence or absence of comorbidities and / or complications.

[0029] Local accuracy within the second capability area is interpreted based on the presence or absence of complications and / or comorbidities.

[0030] In an alternative embodiment of the disease risk prediction method for unplanned readmission, if there are multiple base classifiers with the same ability score, the prediction results of such base classifiers are aggregated using a majority voting rule.

[0031] In an optional solution of the disease risk prediction method for unplanned readmission, before training, the data set is preprocessed, including calculating the P value of each variable in the data set;

[0032] When setting a binary variable representing a medical diagnosis, the variable with a P value smaller than the set value was selected.

[0033] This option can reduce the indicators that have a negative impact on the prediction results, thereby further improving the prediction accuracy.

[0034] The present application also proposes a disease risk prediction system for unplanned readmission, comprising a data acquisition unit for acquiring a disease data set, a processing unit, and a storage unit;

[0035] The data acquisition unit is communicatively connected to the processing unit and sends the data set to the processing unit. The processing unit is communicatively connected to the storage unit, and the storage unit is used to store at least one executable instruction. The executable instruction enables the processing unit to perform operations corresponding to the above-mentioned method for predicting the disease risk of unplanned readmission, thereby predicting the disease risk of unplanned readmission.

[0036] The beneficial effects of the present invention are:

[0037] The present invention combines the diversity of disease data with the dynamic selection of basic classifiers, and the proposed dynamic selection classifier improves the performance of predicting the risk of readmission. The rule-based generation of data subsets (patient subgroups) allows for interpretable training of diversified classifiers to support patient subgroup-specific decision-making, that is, different patients are predicted using different models, for example, predicting whether they will be readmitted within 14 days and 30 days. Because different patients have different comorbidities and complications and the degree of their occurrence, the dynamic selection of the most appropriate model for each patient is enhanced by using the local accuracy within the second capability area extracted by the second capability area, which can achieve more accurate information acquisition for different patients; different patients may use different classifiers or classifier combinations. At this time, it is easier to achieve personalized predictions for patients, that is, select different classifiers according to different patient conditions, thereby obtaining more accurate clinical prediction results. By addressing the challenges associated with real-world data, the invention has contributed to the continued efforts of medical research, using the potential of real-world data to improve patient care and management, and is particularly suitable for identifying individuals at high risk of hospital readmission in patients with cirrhosis.

[0038] Among them, by using base classifiers trained on different data subsets, the characteristics of diverse feature selection of different base classifiers are utilized to address the problems of incompleteness and sparsity of electronic health record data. By using different data subsets and training each base classifier, the classifier pool can capture a wide range of patterns in electronic health record data, thereby enhancing overall prediction performance.

[0039] Furthermore, by generating a pool of classifiers to obtain the most capable classifier and leveraging the most capable classifier to improve performance, the training and dynamic selection of each base classifier becomes more interpretable and demonstrates its potential value in clinical settings. For example, interpretable rules used to generate data subsets for base classifier training can accurately describe the clinical characteristics of the data subset (patient subgroup), namely, whether comorbidities and / or complications develop during hospitalization. These rules provide insights into specific features or conditions that influence predictions, enabling clinicians to make informed decisions and tailor interventions for different patient subgroups. This allows clinicians to develop strategies based on the diverse circumstances of different patients, such as those with complications, those with comorbidities, those with both, and those with none. Furthermore, information such as the severity of each patient's condition is also available, creating a "tailored" approach. If multiple base classifiers are selected for prediction, analyzing the intersection of elements used by multiple rules can provide insights into characterizing the data subset (patient subgroup).

[0040] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0042] Figure 1 It is a schematic diagram of the framework for dynamic selection of classifiers;

[0043] Figure 2 This is the AUROC prediction curve for 14-day readmission;

[0044] Figure 3 This is the ROC prediction curve for 30-day readmission;

[0045] Figure 4 It is a SHAP summary diagram of the impact of input variables on the 14-day readmission rate;

[0046] Figure 5 This is a SHAP diagram showing different predictions for two different patients, where A indicates that the patient has not been readmitted, or the probability of readmission is 0.41, and B indicates that the patient has been readmitted, and the probability of occurrence is 0.80. DETAILED DESCRIPTION

[0047] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0048] In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal communication between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0049] Example 1

[0050] This embodiment uses liver cirrhosis as an example to provide a disease risk prediction method for unplanned readmission, including the following steps:

[0051] Obtain disease dataset

[0052] In this example, cirrhosis data were collected from six tertiary hospitals in Chongqing, China based on electronic health records. The initial inclusion cohort included 13,476 patient records hospitalized between January 2011 and June 2020. These patients were diagnosed with cirrhosis according to ICD-9 or ICD-10. To refine the cohort, the following exclusion criteria were used: (1) patients hospitalized for cancer, malignant tumors, tuberculosis, and HIV (1906 patients); (2) patients lost to follow-up or died during hospitalization (151 patients); (3) patients without any readmission records (7150 patients); (4) patients with more than 15% missing data (1113 patients). The final cohort consisted of 3307 patients with at least one readmission record. Considering the complexity of factors affecting cirrhosis and the dynamic nature of the disease process, this example recorded the patient's demographic, etiology, medical history, and clinical examination information within 24 hours of the first visit.

[0053] The final dataset contained 3,307 patients who were readmitted in this example. The dataset included 2 demographic variables, 5 etiological variables, 35 comorbidity variables, 39 examination variables, 10 surgical variables, 7 medication variables, 1 composite score variable, and 1 outcome variable. The dataset was preprocessed, including calculating the P value for each variable in the dataset. A complete list of indicators is shown in Table 1 in the Supplementary Materials. Of these patients, 1,121 (33.90%) were female and 2,186 (66.10%) were male, with a mean age of 55 years. Of these, 423 (12.79%) were readmitted within 14 days and 879 (26.58%) were readmitted within 30 days. The association between 14-day and 30-day readmission and a set of potential predictive factors was assessed by univariate analysis. The Mann-Whitney U test was applied to quantitative predictors, while the χ2 test was used for binary predictors. 2 The indicators of the selected variables were the same as those shown in Table 1.

[0054] Table 1: Characteristics of the 3307 patients readmitted

[0055]

[0056]

[0057]

[0058] Abbreviations: IQR: interquartile range. EMD, or electrolyte metabolism disorder, refers to an imbalance in the balance of electrolytes (such as sodium, potassium, calcium, and chloride), usually caused by electrolyte levels outside the normal range. INR: International Normalized Ratio (INR = PTpatient / PTcontrol) ISI, where PTpatient is the patient's prothrombin time, PTcontrol is the mean normal prothrombin time, and ISI is the International Sensitivity Ratio. The normal range of INR varies depending on the hospital, laboratory, and patient, ranging from 0.8 to 1.2. MELD: Model for End-Stage Liver Disease, MELD = 9.57*ln(creatinine) + 3.78*ln(bilirubin) + 11.20*ln(INR) + 6.43. The patient's serum creatinine value is in milligrams per deciliter (mg / dL), the patient's total bilirubin value is in millimoles per liter (mg / L), and the INR is the patient's International Normalized Ratio for coagulation. Higher values ​​indicate a higher risk level.

[0059] Use part of the dataset as a training set and part as a test set.

[0060] A dynamic selection classifier is constructed based on the DES framework. The dynamic selection classifier includes several basic classifiers and a meta-classifier. In this embodiment, the dynamic selection classifier is developed based on the deslib library.

[0061] like Figure 1 As shown in Figure 3, the framework for dynamically selecting classifiers focuses on two aspects: classifier pool generation and dynamic classifier selection.

[0062] Training phase

[0063] In this embodiment, several interpretable binary variables representing medical diagnoses are set as rule sets, and the rule sets are used as extraction rules to extract several data subsets from the training set.

[0064] When setting binary variables representing medical diagnoses, variables with a P value less than a set value in the data set are selected. In this embodiment, the set value is preferably, but not limited to, 0.001. Specifically, not all variables in Table 1, such as gender, presence of peritonitis, presence of hepatic encephalopathy, albumin count, red blood cell count, and total bilirubin, are used. Only variables with a P value < 0.001 are selected, and the binary variable is selected from these variables. Variables with a P value > 0.001 are not used in this embodiment.

[0065] During the training phase, a set of rules representing binary variables of medical diagnosis was extracted from each training sample in the training set using 5-fold cross validation. There can be overlap between these rules, that is, some features can be shared between different rules. In this embodiment, a total of 80 rules were extracted from the training set to form a rule set, ensuring that each rule covers at least 500 instances, that is, training samples. These rules serve as patterns to identify specific features or conditions in patient records. By using these rules, data subsets (SG1, SG2, ..., SG n ), which can also be called patient subgroups.

[0066] Interpretable binary variables representing medical diagnoses are preferably, but not limited to, the presence or absence of comorbidities and / or complications of the disease. For example, a rule may be: [(electrolyte metabolism disorder = True) and (hepatic encephalopathy = False)], or the presence or absence of other comorbidities and / or complications. These rules together constitute a rule set.

[0067] Based on the data subset, several basic classifiers are trained. The training process uses the PyCaret library to effectively train the basic classifiers and adjust the hyperparameters, and obtains a classifier pool C = {c1, c2, ..., c m},c1,c2,...,c m are the basic classifiers.

[0068] Basic classifiers include but are not limited to: Naive Bayes, K-nearest neighbor classifier, logistic regression, linear discriminant analysis, and quadratic discriminant analysis; and ensemble models: Random Forest classifier, Extreme Random Trees classifier, Adaptive Boosting classifier, Gradient Boosting classifier, Lightweight Gradient Boosting Machine, and Extreme Gradient Boosting.

[0069] By using different data subsets and training base classifiers, the classifier pool can capture broad patterns in electronic health record data, thereby enhancing the overall prediction performance.

[0070] Dynamically selecting a classifier is intended to find one or more basic classifiers from the classifier pool C to classify a given test sample. This is achieved in this embodiment by the following steps:

[0071] Define capability regions and criteria for measuring the capability of each basic classifier in the classifier pool within the capability region, one of these criteria being the aforementioned binary variable, and use all criteria as meta-features, i.e., the binary variable is also one of the meta-features; use the basic classifier within the capability region to extract meta-features in the training set.

[0072] Among them, the capability area includes the first capability area θ j and the second capability region θ j'. Define the second capability area θ j ' is to effectively incorporate complications and / or comorbidities to characterize patients with the disease (cirrhosis patients in this example) and to improve dynamic classifier selection.

[0073] First capability region θ j It is a neighborhood around the predicted data sample. The data samples in this neighborhood are similar samples to the predicted data sample. It aims to capture the similar sample features around this predicted data sample, so as to estimate the performance of the basic classifier in this specific area. Define the first ability region θ j Methods include but are not limited to: K nearest neighbor and clustering based on the entire feature space.

[0074] In the first capability region θ j The first set of meta-features is extracted from the first set of meta-features. The first set of meta-features includes a criterion f1 for measuring local accuracy within the first capability region, a degree of consensus f2 within the first capability region, an overall accuracy f3 within the first capability region, accuracy f4 in the decision space, and a degree of confidence f5 for the input sample. The method for extracting the first set of meta-features is to directly use the meta-classifier.

[0075] Second capability region θ j ' is the data containing the binary variable based on medical diagnosis, in the second capability area θ j '. The second component features include the local accuracy f6 within the second capability region. In this embodiment, the local accuracy f6 within the second capability region is the aforementioned binary variable, and the local accuracy f6 within the second capability region is interpreted according to the presence or absence of complications and / or comorbidities. Therefore, based on the second capability region θ of medical diagnosis j 'Focusing on complications and / or comorbidities, treating them as binary variables indicating the absence or presence of these conditions, local accuracy f6 within the second power region is used to focus on the subset of data (subgroup of patients) with specific complications and / or comorbidities.

[0076] The second capability area θ j 'Contains an equal number of positive and negative samples to give a balanced estimate of the performance of the base classifier.

[0077] The base classifier c i and data sample x j The extracted meta-feature is denoted as v ij ={f1,f2,f3,f4,f5,f6}.

[0078] Assign a label to each meta-feature: For each meta-feature, if the classifier c i Correctly classify the data sample, then its label is α ij =1; otherwise αij = 0. The meta-features are then used as a training set for training the meta-classifier to train the meta-classifier. In this embodiment, the meta-classifier is preferably, but not limited to, a classifier such as META-DES.

[0079] The trained meta-classifier is used to calculate the ability score of each base classifier in the classifier pool. The ability score is usually expressed as the probability estimated by the meta-classifier. The classifier with the highest ability score is selected as the classifier ensemble pool C that predicts the corresponding data. * When there is only one basic classifier with the highest ability score, the classifier integration pool C * There is only one basic classifier in the classifier, which is the best classifier and its prediction result is the final prediction result. When there are multiple basic classifiers with the highest ability scores, that is, the ability scores of multiple basic classifiers are the same and the highest, the classifier integration pool C * If there are multiple base classifiers in , the prediction results of these base classifiers are aggregated using the majority voting rule as the final prediction result.

[0080] Testing phase

[0081] Extract meta-features from the test set in the classifier pool C, and use the trained meta-classifier to calculate the ability scores of each basic classifier in the classifier pool when predicting the test sample, thus obtaining the classifier integration pool C. * When the classifier ensemble pool C * There is only one basic classifier in the classifier, which is the best classifier and its prediction result is used as the final prediction result. * If there are multiple base classifiers in , the prediction results of these base classifiers are aggregated using the majority voting rule as the final prediction result.

[0082] Prediction results

[0083] Unplanned readmissions within 14 and 30 days were assessed separately. The area under the receiver operating characteristic curve (AUROC) was Figure 2 and Figure 3 As shown, higher AUROC values ​​indicate stronger discriminatory power of the model. To avoid achieving high accuracy in imbalanced classification by simply predicting the majority class, a sensitivity-based threshold selection process was employed. The threshold used to calculate accuracy was selected to ensure a sensitivity greater than 0.5, indicating a focus on correctly identifying positive cases. Table 2 presents the mean scores and the range of maximum and minimum values ​​observed during cross-validation. The proposed method outperformed the baseline model in both accuracy and AUROC.

[0084] Table 2 Comparison of results of different prediction models

[0085]

[0086] The prediction results can be explained using interpretability techniques such as SHapley Additive exPlanations (SHAP). For example, Figure 4 showed that higher IBIL, D_TBIL, PT-INR, ascitic fluid concentrate, and lower D_ALB were associated with a better predicted outcome in the patient subgroup. Figure 5 Individual power plots are shown for (A) patients who were not readmitted and (B) patients who were readmitted. The model's predicted probability values, f(x), were 0.41 and 0.80 for Patient 1 and Patient 2, respectively. For Patient 1, TBA, PLT, glutathione, AST, and peritonitis negatively impacted the predicted outcome, while calcium and HGB positively impacted the outcome. For Patient 2, calcium, HGB, sex, EMD, autoimmune disease, D_TBIL, and D_Na positively impacted the predicted outcome, while glutathione negatively impacted the predicted outcome.

[0087] Example 2

[0088] This embodiment provides a disease risk prediction system for unplanned readmission, including a data acquisition unit for acquiring a disease data set, a processing unit, and a storage unit; the data acquisition unit is communicatively connected to the processing unit and sends the data set to the processing unit; the processing unit is communicatively connected to the storage unit, and the storage unit is used to store at least one executable instruction, which causes the processing unit to perform operations corresponding to the disease risk prediction method for unplanned readmission as described in Example 1, thereby predicting the disease risk of unplanned readmission.

[0089] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0090] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A disease risk prediction method for unplanned readmission, characterized in that: The following steps are involved: Obtain disease datasets; A dynamic selection classifier is constructed based on the DES framework. The dynamic selection classifier includes several basic classifiers and a meta-classifier. The dynamic selection classifier is trained based on the data set: Setting a number of interpretable binary variables representing medical diagnoses as a rule set, and extracting the rule set from the data set into a number of data subsets as extraction rules; Training the basic classifier based on the data subset to obtain a classifier pool; defining a capability region and a criterion for measuring the capability of each basic classifier in the classifier pool within the capability region, wherein one of the criteria includes the binary variable, and the criterion is used as a meta-feature; Extracting meta-features from a data set using the base classifier within the capability region; Training the meta-classifier using the meta-features as a training set for training the meta-classifier; Use the meta-classifier to calculate the ability score of each base classifier in the classifier pool when predicting each set of data; The base classifier with the highest ability score is selected as the best classifier for predicting the corresponding data; The prediction result of the best classifier is taken as the final prediction result.

2. The disease risk prediction method for unplanned readmission according to claim 1, characterized in that: Part of the data in the data set is used as a training set, and a set of rules representing binary variables of medical diagnosis is extracted from each training sample, and all the rules form the rule set.

3. The disease risk prediction method for unplanned readmission according to claim 1, characterized in that: The capability area includes a first capability area and a second capability area; The first capability region is a neighborhood surrounding the predicted data sample, the data samples in the neighborhood are similar samples to the predicted data sample, and the first component feature is extracted in the first capability region; The second capability area is based on medical diagnosis data containing the binary variable, and second component features are extracted within the second capability area.

4. The method for predicting the risk of unplanned hospital readmission according to claim 3, wherein: The first set of meta-features includes a standard for measuring local accuracy within the first capability area, a degree of consensus within the first capability area, an overall accuracy within the first capability area, accuracy in the decision space, and a degree of confidence in an input sample; The second component characteristics include local accuracy within a second capability region.

5. The disease risk prediction method for unplanned readmission according to claim 1, characterized in that: The interpretable binary variables representing medical diagnoses were the presence or absence of comorbidities and complications.

6. The method for predicting the risk of unplanned hospital readmission according to claim 4, wherein: Local accuracy within the second capability area was interpreted based on the presence or absence of complications and comorbidities.

7. The method for predicting the risk of unplanned hospital readmission according to claim 1, wherein: If there are multiple base classifiers with the same and highest ability scores, the prediction results of such base classifiers are aggregated using the majority voting rule as the final prediction result.

8. The method for predicting the risk of unplanned hospital readmission according to claim 1, wherein: SHAP was used to interpret the prediction results of the dynamic selection classifier.

9. The method for predicting the risk of unplanned hospital readmission according to claim 1, wherein: Before training, the data set is preprocessed, including calculating the P value of each variable in the data set; When setting a binary variable representing a medical diagnosis, the variable with a P value smaller than the set value was selected.

10. A disease risk prediction system for unplanned readmission, characterized in that: including a data acquisition unit, a processing unit, and a storage unit for acquiring a disease data set; The data acquisition unit is communicatively connected to the processing unit and sends the data set to the processing unit. The processing unit is communicatively connected to a storage unit, and the storage unit is used to store at least one executable instruction. The executable instruction enables the processing unit to perform an operation corresponding to the disease risk prediction method for unplanned readmission according to any one of claims 1 to 9, and predict the disease risk of unplanned readmission.

Images