Back to Search
Start Over
Analysis of Machine Learning Techniques for Heart Failure Readmissions.
- Source :
- Circulation: Cardiovascular Quality & Outcomes; Nov2016, Vol. 9 Issue 6, p629-640, 12p
- Publication Year :
- 2016
-
Abstract
- <bold>Background: </bold>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.<bold>Methods and Results: </bold>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).<bold>Conclusions: </bold>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. [ABSTRACT FROM AUTHOR]
- Subjects :
- HEART failure
HEART failure treatment
ALGORITHMS
CHAOS theory
CLINICAL trials
COMPARATIVE studies
DATABASES
RESEARCH methodology
MEDICAL cooperation
META-analysis
RESEARCH
RESEARCH evaluation
RESEARCH funding
RISK assessment
STATISTICAL sampling
TELEMEDICINE
TIME
DATA mining
LOGISTIC regression analysis
EVALUATION research
RANDOMIZED controlled trials
PATIENT readmissions
DIAGNOSIS
Subjects
Details
- Language :
- English
- ISSN :
- 19417713
- Volume :
- 9
- Issue :
- 6
- Database :
- Supplemental Index
- Journal :
- Circulation: Cardiovascular Quality & Outcomes
- Publication Type :
- Academic Journal
- Accession number :
- 119523697
- Full Text :
- https://doi.org/10.1161/CIRCOUTCOMES.116.003039