Computationally Generated Biomarkers: Cardiology and Beyond

Abstract

The disease burden of many important clinical conditions remains unacceptably high because of a failure to promptly match patients to treatments that are appropriate to their current condition or their individual risk. For the most part, this matching is done today using biomarkers derived from instantaneous measurements of biochemical substances or imaging data. Particularly striking is the lack of clinically useful biomarkers that exploit computational advances in acquiring large volumes of physiological time series continuously from patients over periods of days.

This talk describes how we have used techniques drawn from different areas of computer science, including advanced algorithms, machine learning, data mining, signal processing, and computational biology, for the structured analysis of large multi-patient time series datasets. I will present three computationally generated biomarkers that use information in long-term cardiovascular datasets to risk stratify patients following heart attacks, and present the results of evaluating these biomarkers in two separate clinical studies with over 5,500 patients. Among other results, I will discuss how computationally generated biomarkers can identify which patients are at a significantly increased risk of death following heart attacks, even after adjusting for other clinical predictors, and how these biomarkers significantly improve the precision and recall of existing methods used for making clinical decisions. I will also discuss some recent work we have done on how computation can have a translational impact in clinical applications related to neurology, psychiatry, obstetrics, surgery, and critical care.

Bio:
Zeeshan Syed is an Assistant Professor in the Department of Electrical Engineering and Computer Science at the University of Michigan. His research interests lie at the intersection of EECS and medicine, and focus on the development of novel computational methods to address the needs of modern medicine and developing world healthcare. Zeeshan received a Ph.D. in Computer Science and Biomedical Engineering from MIT EECS and Harvard Medical School through the Harvard-MIT Health Sciences and Technology program, and M.Eng. and S.B. degrees from MIT EECS. He is a recipient of a National Science Foundation CAREER award.