From EHRs to Body-Worn Sensors: Finding Causes of Health and Disease
Assistant Professor, Computer Science, Stevens Institute of Technology
Massive amounts of medical data from electronic health records are now being mined by researchers, and can be used to improve care such as by finding factors affecting the recovery of patients in intensive care, or early risk factors for heart failure. However, patients are highly heterogeneous, the data are noisy, and we lack ground truth for evaluating algorithms. Further, many important events occur outside of medical settings. This is particularly true for chronic diseases such as diabetes and obesity. In this talk I discuss why outpatient data are needed to understand chronic disease, the computational challenges of inferring causality in these data and why we need automated monitoring of nutrition. In the second part of this talk I discuss our recent work using multiple sensing modalities to automatically identifying eating and how this can ultimately be used to support individuals with chronic disease.
Samantha Kleinberg is an Assistant Professor of Computer Science at Stevens Institute of Technology. She received her PhD in Computer Science from New York University in 2010 and was a Computing Innovation Fellow at Columbia University in the Department of Biomedical informatics from 2010-2012. She is the recipient of NSF CAREER and JSMF Complex Systems Scholar Awards and her work is also supported by the NIH through an R01. Her research focuses on two main areas: developing methods for finding causes from large-scale, complex, time-series data; and better understanding human health through analysis of medical and health data. She is the author of Causality, Probability, and Time (Cambridge University Press, 2012) and the forthcoming book Why: A Guide to Finding and Using Causes (O’Reilly Media, in press).