Poster Abstract: A Machine Learning Approach to Identify High-Cost Elderly Renal Transplant Recipients

Abstract

Caring for elderly patients with end-stage renal disease is a pressing issue worldwide. In Canada, transplanting elderly patients has high upfront costs to the health care system. In this study we used machine learning to identify high-cost users of health care among deceased-donor renal transplant recipients aged over 70 in Ontario, Canada. Three classification methods were explored, including K-nearest neighbors, logistic lasso regression, and random forest. Insights offered by this study have implications that can aid renal programs to cost-effectively optimize outcomes of elderly patients.