Prediction using patient comparison vs. modeling: A case study for mortality prediction

Abstract

Information in Electronic Medical Records (EMRs) can be used to generate accurate predictions for the occurrence of a variety of health states, which can contribute to more pro-active interventions. The very nature of EMRs does make the application of off-the-shelf machine learning techniques difficult. In this paper, we study two approaches to making predictions that have hardly been compared in the past: (1) extracting high-level (temporal) features from EMRs and building a predictive model, and (2) defining a patient similarity metric and predicting based on the outcome observed for similar patients. We analyze and compare both approaches on the MIMIC-II ICU dataset to predict patient mortality and find that the patient similarity approach does not scale well and results in a less accurate model (AUC of 0.68) compared to the modeling approach (0.84). We also show that mortality can be predicted within a median of 72 hours.