Predicting Adverse Outcomes in End Stage Renal Disease: Machine Learning Applied to the United States Renal Data System

Authors

Zeid Khitan, Joan C Edwards School of MedicineFollow
Alexis D. Jacob, University of Texas at SouthwesternFollow
Courtney Balentine, University of Texas at SouthwesternFollow
Adam N. Jacob, University of ToledoFollow
Juan R. Sanabria, Marshall Univerisity School of MedicineFollow
Joseph I. Shapiro, Marshall UniversityFollow

Author Credentials

Zeid Khitan MD Alexis D. Jacob MD Courtney Balentine MD Adam N. Jacob BS Juan R. Sanabria MD Joseph I. Shapiro MD

Keywords

machine learning, end stage renal disease, mortality, hemodialysis

Disciplines

Health and Medical Administration | Nephrology

Abstract

We examined machine learning methods to predict death within six months using data derived from the United States Renal Data System (USRDS). We specifically evaluated a generalized linear model, a support vector machine, a decision tree and a random forest evaluated within the context of K-10 fold validation using the CARET package available within the open source architecture R program. We compared these models with the feed forward neural network strategy that we previously reported on with this data set.

Recommended Citation

Khitan Z, Jacob AD, Balentine C, Jacob AN, Sanabria JR, Shapiro JI. Predicting Adverse Outcomes in End Stage Renal Disease: Machine Learning Applied to the United States Renal Data System. Marshall J Med. 2018; 4(4): 75 DOI: