A comparison of models for predicting early hospital readmissions

Risk sharing arrangements between hospitals and payers together with penalties imposed by the Centers for Medicare and Medicaid (CMS) are driving an interest in decreasing early readmissions. There are a number of published risk models predicting 30day readmissions for particular patient populations, however they often exhibit poor predictive performance and would be unsuitable for use in a clinical setting. In this work we describe and compare several predictive models, some of which have never been applied to this task and which outperform the regression methods that are typically applied in the healthcare literature. In addition, we apply methods from deep learning to the five conditions CMS is using to penalize hospitals, and offer a simple framework for determining which conditions are most cost effective to target.

[1]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[2]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[3]  Susan Hutfless,et al.  Mining high-dimensional administrative claims data to predict early hospital readmissions , 2014, J. Am. Medical Informatics Assoc..

[4]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[5]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[6]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[7]  Cole Erdmann,et al.  A Public-Private Partnership Develops and Externally Validates a 30-Day Hospital Readmission Risk Prediction Model , 2013, Online journal of public health informatics.

[8]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[9]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[10]  Amanda H. Salanitro,et al.  Risk prediction models for hospital readmission: a systematic review. , 2011, JAMA.

[11]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[12]  Rasmus Berg Palm,et al.  Prediction as a candidate for learning deep hierarchical models of data , 2012 .

[13]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[14]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[15]  Glenn Fung,et al.  Predicting Readmission Risk with Institution Specific Prediction Models , 2013, 2013 IEEE International Conference on Healthcare Informatics.

[17]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[18]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[19]  Saeid Eslami,et al.  Transitional care interventions prevent hospital readmissions for adults with chronic illnesses. , 2014, Health affairs.

[20]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[21]  Tong Zhang.  Statistical behavior and consistency of classification methods based on convex risk minimization , 2003 .

[22]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[23]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[24]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[25]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .