Opportunities and challenges for reducing hospital revisits

Analysis of Machine Learning Techniques for Heart Failure Readmissions

BACKGROUND

The 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 RESULTS

Using 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).

CONCLUSIONS

Machine 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.

Heart Failure Readmission Reduction

Little is known regarding effectiveness of readmission reduction programs over time. The Heart Failure Management Program (HFMP) of St. John's Physician Group Practice (PGP) Demonstration provided an opportunity to assess outcomes over an extended period. Data from an electronic health record, an inpatient database, a disease registry, and the Social Security Death Master File were analyzed for patients admitted with heart failure (HF) for 5 years before (Period 1) and 5 years after (Period 2) inception of PGP. HF admissions decreased (Period 1, 58.3/month; Period 2, 52.4/month, P = .007). Thirty-day all-cause readmission rate dropped from Period 1 (annual average 18.8% [668/3545]) to year 1 of Period 2 (16.9% [136/804], P = .04) and remained stable thereafter (annual average 16.8% [589/3503]). Thirty-day mortality rate was flat throughout. HFMP was associated with decreased readmissions, primarily related to outpatient case management, while mortality remained stable.