Events and Seminars : 2014 Seminars

LEVERAGING ELECTRONIC HEALTH RECORDS TO UNDERSTAND AND PREDICT CARDIAC EVENTS IN HEMODIALYSIS: MAKIN

BENJAMIN A. GOLDSTEIN, PH.D.
Assistant Professor
Department of Biostatistics & Bioinformatics
Duke University

WEDNESDAY, MARCH 18, 2015
2:00 p.m.–3:00 p.m., CRB 692

Electronic health records (EHRs) capture detailed and changing information about patients’ health status, creating a unique opportunity for medical researchers to understand and predict the risk of acute clinical events. For statisticians, they present the opportunity to apply a range of methodological approaches to address these questions. One of the challenges in working with large data sets is defining the optimal way to analyze the data. In this talk, I will illustrate how different questions require different cuts of the data and different methodologies to best answer the question. Specifically, I will examine (1) a propensity-matched data set to assess the “causal” impact of a common dialysis drug, (2) a functional spline regression methodto identify biomarkers for cardiac events, (3) an approach to classifying blood pressure curves and (4) a machine learning approach to derive a predictor and assess how far out an event can be forecast. By leveraging the large data size (> 100 million sessions across almost 1 million people), we create tailored data sets to best address each question. The talk highlights both the potential and challenges for analyzing acute events with a dense set of data.