Researchers win Best Paper Award at IEEE Healthcare Informatics and Systems Biology Conference

Dr. Gyemin Lee with conference chair Lucila Ohno-Machado, MD, PhD Enlarge
Dr. Gyemin Lee with conference chair Lucila Ohno-Machado, MD, PhD

CSE post-doctoral researcher Gyemin Lee, Dr. Hitinder Gurm in U-M Department of Internal Medicine, and Professor Zeeshan Syed have won the Best Paper Award at the IEEE Healthcare Informatics and Systems Biology conference (HISB), which took place September 27 – 28 in La Jolla, CA.

Their paper is entitled “Predicting Complications of Percutaneous Coronary Intervention using a Novel Support Vector Method.” (Extended abstract – PDF)

Dr. Lee describes the research as follows:

Clinical tools to identify patients at risk of complications during percutaneous coronary intervention (PCI) can play an important role in assessing quality and outcomes, as well as in streamlining delivery of care in the presence of hospitals with and without on-site surgical backup. PCI is a non-surgical procedure used to treat narrowed coronary arteries of the heart found in coronary heart disease.

In this paper, we propose a novel support vector machine (SVM) classification approach to stratify patients undergoing PCI. Our approach focuses on leveraging properties of both one-class and two-class SVM classification to address the diminished prevalence of many important PCI complications. When studied on data from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) multi-center cardiology registry data, we find that our SVM method provides moderate to high levels of discrimination for different PCI endpoints, and improves model performance in many cases relative to both the standard one-class and two-class SVM algorithms.

We believe this allows for PCI models that have increased clinical utility at the bedside, and for objective assessments of quality and outcomes.