A stacking-based model for predicting 30-day all-cause hospital readmissions of patients with acute myocardial infarction

Zhen Zhang,Hang Qiu,Weihao Li,Yucheng Chen

doi:10.1186/s12911-020-01358-w

Abstract

BackgroundAcute myocardial infarction (AMI) is a serious cardiovascular disease, followed by a high readmission rate within 30-days of discharge. Accurate prediction of AMI readmission is a crucial way to identify the high-risk group and optimize the distribution of medical resources.MethodsIn this study, we propose a stacking-based model to predict the risk of 30-day unplanned all-cause hospital readmissions for AMI patients based on clinical data. Firstly,we conducted an under-sampling method of neighborhood cleaning rule (NCR) to alleviate the class imbalance and then utilized a feature selection method of SelectFromModel (SFM) to select effective features. Secondly, we adopted a self-adaptive approach to select base classifiers from eight candidate models according to their performances in datasets. Finally, we constructed a three-layer stacking model in which layer 1 and layer 2 were base-layer and level 3 was meta-layer. The predictions of the base-layer were used to train the meta-layer in order to make the final forecast.ResultsThe results show that the proposed model exhibits the highest AUC (0.720), which is higher than that of decision tree (0.681), support vector machine (0.707), random forest (0.701), extra trees (0.709), adaBoost (0.702), bootstrap aggregating (0.704), gradient boosting decision tree (0.710) and extreme gradient enhancement (0.713).ConclusionIt is evident that our model could effectively predict the risk of 30-day all cause hospital readmissions for AMI patients and provide decision support for the administration.

Highlights

Acute myocardial infarction (AMI) is a serious cardiovascular disease, followed by a high readmission rate within 30-days of discharge
DT Decision tree, support vector machine (SVM) Support vector machine, random forest (RF) Random forest, extra trees (ET) Extra trees, gradient boosting decision tree (GBDT) Gradient boosting decision tree, ADB AdaBoost, bootstrap aggregating (Bagging) Bootstrap aggregating, Extreme gradient enhancement (XGB) Extreme gradient boosting were improved after neighborhood cleaning rule (NCR) treatment, in which SVM was greatly improved with statistically significant difference (p-value < 0.05), while the improvement of other models showed no statistically significant differences
For Area under the receiver operating characteristic curve (AUC), the stacking model improved nearly 1% compared with the best candidate model XGB

Summary

Introduction

Acute myocardial infarction (AMI) is a serious cardiovascular disease, followed by a high readmission rate within 30-days of discharge. Accurate prediction of AMI readmission is a crucial way to identify the high-risk group and optimize the distribution of medical resources. Several methods have been applied to predict the risk of readmission. Cotter et al [7] concluded that the LACE index performed poorly in predicting 30-day readmission with the area under the receiver operating characteristic curve (AUC) of 0.55, while that of the logistic regression (LR) model was 0.57. Regression analysis method is a process of estimating the probability of target variables given some linear combination of the predictors, and has been widely applied to predict the readmission risk [8, 9]. It is difficult to solve the nonlinear problem or multicollinearity among risk factors based on detailed clinical data

Methods

Results

Discussion

Conclusion