The LightGBM machine learning model predicted hospital length of stay categories for heart failure patients with a micro-average ROC AUC of 0.78 and a mean accuracy of 61%.
Observational (n=2,008)
Can machine learning models accurately predict hospital length of stay categories in heart failure patients?
A machine learning model using admission clinical variables can predict hospital length of stay categories for heart failure patients with moderate accuracy, driven primarily by BNP, creatine kinase, and HDL cholesterol.
BACKGROUND Heart failure represents a significant global health burden, with prolonged length of stay (LoS) tied to increased mortality and costs. Accurate prediction of hospital LoS is crucial for improving resource allocation, lowering mortality and readmission rates, and enhancing patient care. OBJECTIVES This study leverages machine learning (ML) models to predict LoS categories (Short: 1-3 days; Medium: 4-7 days; Long: ≥8 days) for heart failure patients, with a goal of developing and benchmarking a predictive model. METHODS This was a retrospective analysis of 2,008 heart failure patients with 168 clinical variables available at the time of or shortly after admission. The analysis utilized a multiclass classification approach, with thirteen different ML models trained and validated using stratified 10-fold cross-validation. RESULTS Among the models evaluated, the LightGBM model demonstrated the highest performance, achieving a micro-average ROC AUC of 0.78 and a macro-average ROC AUC of 0.68, with mean accuracy of 61%. Feature importance analysis identified brain natriuretic peptide (BNP), creatine kinase, and high-density lipoprotein cholesterol as the top three variables influencing the prediction. CONCLUSIONS The model identifies key biomarkers to alert clinicians to patients requiring intensive care, potentially reducing hospital costs and improving resource allocation. The results further underscore the potential of machine learning to support clinical decision-making by establishing a strong performance baseline for heart failure care. Future work should focus on leveraging larger and diverse datasets and additional models to enhance predictive accuracy.
Souza et al. (2026) conducted an observational in Heart failure (n=2,008). Machine learning models (LightGBM) vs. Other machine learning models was evaluated on Prediction of hospital length of stay categories (Short: 1-3 days; Medium: 4-7 days; Long: ≥8 days). The LightGBM machine learning model predicted hospital length of stay categories for heart failure patients with a micro-average ROC AUC of 0.78 and a mean accuracy of 61%.