• Bobak J Mortazavi, Nicholas S Downing, Emily M Bucholz, Kumar Dharmarajan, Ajay Manhapra, Shu-Xia Li, Sahand N Negahban, and Harlan M Krumholz.
• From the Section of Cardiovascular Medicine, Department of Internal Medicine (B.J.M., N.S.D., E.M.B., K.D., H.M.K.), Department of Psychiatry and the Section of General Medicine, Department of Internal Medicine (A.M.), and Robert Wood Johnson Foundation Clinical Scholars Program, Department of Internal Medicine, Yale School of Medicine, and Department of Health Policy and Management (H.M.K.), Yale School of Public Health, New Haven, CT; Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT (B.J.M., N.S.D., E.M.B., K.D., S.-X.L., H.M.K.); and Department of Statistics, Yale University, New Haven, CT (B.J.M., S.N.N.).
• Circ Cardiovasc Qual. 2016 Nov 1; 9 (6): 629-640.

BackgroundThe current ability to predict readmissions in patients with heart failure is modest at best. It is unclear whether machine learning techniques that address higher dimensional, nonlinear relationships among variables would enhance prediction. We sought to compare the effectiveness of several machine learning algorithms for predicting readmissions.Methods And ResultsUsing data from the Telemonitoring to Improve Heart Failure Outcomes trial, we compared the effectiveness of random forests, boosting, random forests combined hierarchically with support vector machines or logistic regression (LR), and Poisson regression against traditional LR to predict 30- and 180-day all-cause readmissions and readmissions because of heart failure. We randomly selected 50% of patients for a derivation set, and a validation set comprised the remaining patients, validated using 100 bootstrapped iterations. We compared C statistics for discrimination and distributions of observed outcomes in risk deciles for predictive range. In 30-day all-cause readmission prediction, the best performing machine learning model, random forests, provided a 17.8% improvement over LR (mean C statistics, 0.628 and 0.533, respectively). For readmissions because of heart failure, boosting improved the C statistic by 24.9% over LR (mean C statistic 0.678 and 0.543, respectively). For 30-day all-cause readmission, the observed readmission rates in the lowest and highest deciles of predicted risk with random forests (7.8% and 26.2%, respectively) showed a much wider separation than LR (14.2% and 16.4%, respectively).ConclusionsMachine learning methods improved the prediction of readmission after hospitalization for heart failure compared with LR and provided the greatest predictive range in observed readmission rates.© 2016 American Heart Association, Inc.

26 keywords...

hide…