In-hospital mortality prediction model of heart failure patients using imbalanced registry data: A machine learning approach

Articles in Press

Document Type : Article

Authors

1 Department of Biomedical Engineering, K. N. Toosi University of Technology, Tehran, P.O.BOX: 16315-1355, Iran

2 Heart Failure Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences, Isfahan, Iran

Abstract

Heart failure (HF) is a cardiac dysfunction disease with a high mortality rate that is mostly calculated via registry data. The objective of this work was to predict in-hospital mortality in patients hospitalized with HF utilizing their before-hospitalization registry data. The data include 3968 HF records extracted from Persian Registry Of cardio Vascular diseasE (PROVE)/HF registry.
We proposed a method that contains an imbalanced ensemble probabilistic model which using registry data predicts HF patients who die during hospitalization from those who survive. The suggested ensemble model uses machine learning models that several ones, namely Decision Tree, Random Forest, LDA, Logistic Regression, SVM, KNN, and XGBoost were evaluated. We also used feature importance analysis to find the important ones and reduce the complexity.
The results illustrated the proposed method can predict in-hospital mortality of HF patients using XGBoost that outperformed all others. Feature importance ranking obtained by XGBoost demonstrated that the proposed method can achieve an acceptable performance with the first 18 important features and XGBoost (accuracy: 76.4%±1.6%, sensitivity: 76.8%±6.9%, specificity: 76.4%±1.8%). Moreover, statistical analysis presented significant predictors of in-hospital mortality (P-value<0.01).
In conclusion the proposed method can effectively predict in-hospital mortality of HF patients using the imbalanced data.

Keywords

Scientia Iranica

Articles in Press, Accepted Manuscript
Available Online from 18 July 2023

Files

History

  • Receive Date: 22 December 2022
  • Revise Date: 17 May 2023
  • Accept Date: 18 July 2023

Share

How to cite

Statistics