Predicting diabetes-related hospitalizations based on electronic health records
Open Access
- 25 November 2018
- journal article
- research article
- Published by SAGE Publications in Statistical Methods in Medical Research
- Vol. 28 (12) , 3667-3682
Abstract
Objective: To derive a predictive model to identify patients likely to be hospitalized during the following year due to complications attributed to Type II diabetes. Methods: A variety of supervised machine learning classification methods were tested and a new method that discovers hidden patient clusters in the positive class (hospitalized) was developed while, at the same time, sparse linear support vector machine classifiers were derived to separate positive samples from the negative ones (non-hospitalized). The convergence of the new method was established and theoretical guarantees were proved on how the classifiers it produces generalize to a test set not seen during training. Results: The methods were tested on a large set of patients from the Boston Medical Center – the largest safety net hospital in New England. It is found that our new joint clustering/classification method achieves an accuracy of 89% (measured in terms of area under the ROC Curve) and yields informative clusters which can help interpret the classification results, thus increasing the trust of physicians to the algorithmic output and providing some guidance towards preventive measures. While it is possible to increase accuracy to 92% with other methods, this comes with increased computational cost and lack of interpretability. The analysis shows that even a modest probability of preventive actions being effective (more than 19%) suffices to generate significant hospital care savings. Conclusions: Predictive models are proposed that can help avert hospitalizations, improve health outcomes and drastically reduce hospital expenditures. The scope for savings is significant as it has been estimated that in the USA alone, about $5.8 billion are spent each year on diabetes-related hospitalizations that could be prevented.Keywords
This publication has 31 references indexed in Scilit:
- Using data mining techniques to predict hospitalization of hemodialysis patientsDecision Support Systems, 2011
- Discovering the False Discovery RateJournal of the Royal Statistical Society Series B: Statistical Methodology, 2010
- Prediction Modeling Using EHR DataMedical Care, 2010
- Bayesian t tests for accepting and rejecting the null hypothesisPsychonomic Bulletin & Review, 2009
- Simultaneous Regression Shrinkage, Variable Selection, and Supervised Clustering of Predictors with OSCARBiometrics, 2008
- The control of the false discovery rate in multiple testing under dependencyThe Annals of Statistics, 2001
- Support-vector networksMachine Learning, 1995
- Long-Term Complications of Diabetes MellitusNew England Journal of Medicine, 1993
- Confidence intervals rather than P values: estimation rather than hypothesis testing.BMJ, 1986
- Algorithm AS 136: A K-Means Clustering AlgorithmJournal of the Royal Statistical Society Series C: Applied Statistics, 1979