Predicting Risk of 30-Day Readmissions Using Two Emerging Machine Learning Methods

Decades-long research efforts have shown that Heart Failure (HF) is the most expensive diagnosis for hospitalizations and the most frequent diagnosis for 30-day readmissions. If risk stratification for readmission of HF patients could be carried out at the time of discharge from the index hospitalization, corresponding appropriate post-discharge interventions could be arranged to avoid potential readmission. We, therefore, sought to explore and compare two newer machine learning methods of risk prediction using 56 predictors from electronic health records data of 1778 unique HF patients from 31 hospitals across the United States. We used two approaches boosted trees and spike-and-slab regression for analysis and found that boosted trees provided better predictive results (AUC: 0.719) as compared to spike-and-slab regression (AUC: 0.621) in our dataset.