Mortality prediction of inpatients with NSTEMI in a premier hospital in China based on stacking model.

BACKGROUND

Acute myocardial infarction (AMI) remains a leading cause of hospitalization and death in China. Accurate mortality prediction of inpatient is crucial for clinical decision-making of non-ST-segment elevation myocardial infarction (NSTEMI) patients.

METHODS

In this study, a total of 3061 patients between January 1, 2017 and December 31, 2022 diagnosed with NSTEMI were enrolled in this study. A new method based on Stacking ensemble model is proposed to predict the in-hospital mortality risk of NSTEMI using clinical data. This method mainly consists of three parts. Firstly, oversampling technique was used to alleviate the class imbalance problem. Secondly, the feature selection method of Recursive Feature Elimination (RFE) was selected for effective feature selection. Finally, a unique double-layer stacking model is designed to improve the performance of the algorithm. Seven classical artificial intelligence methods of Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), Adaptive Boosting (ADB), Extra Tree (ET), and Gradient Boosting Decision Tree (GBDT) were selected as candidate models for the base model of the first layer of the model, and extreme gradient enhancement (XGBOOST) was selected as the meta-model for the second layer.

RESULTS

Patient were divided into the surviving group and the death group, and a total of 57 clinical features showed statistically significant for the two groups and finally included in the subsequent model. The results show that the Area Under Curve (AUC) of the Stacking model proposed in this paper is 0.987, which is higher than that of LR (0.934), DT (0.946), SVM (0.942), RF (0.948), ADB (0.949), ET (0.938) and GBDT (0.920). At the same time, the proposed Stacking model has higher performance than each single model in terms of Accuracy, Precision, Recall and F1 evaluation indicators.

CONCLUSIONS

The Stacking model proposed in this paper can integrate the advantages of LR, DT, SVM, RF, ADB, ET and GBDT models to achieve better prediction performance. This model can provide valuable insights for physicians to identify high-risk patients more precisely and timely, thereby maximizing the potential for early clinical interventions to reduce the mortality rate.