Strata Rx 2012: Learning Models for Metabolic Syndrome from Medical Claims Data

StrataRx: Learning Models for Metabolic Syndrome from Medical Claims Data
Bruce Church (GNS Healthcare) and Greg Steinberg (Aetna)

Presented at the StrataRx Conference
San Francisco, CA
Wednesday, October 17, 2012

Metabolic Syndrome, MetS, is a huge and growing health burden, whether we’re talking about burdens that are clinical or economic, societal or individual. MetS, a cluster of the most dangerous heart attack risk factors affects 25% of the world’s adults, with a twofold greater risk of a heart attack or stroke and a fivefold greater risk of type-2 diabetes. This clustering of risks is now considered to be the driving force for a cardiovascular disease epidemic. Falling outside of a defined range of at least 3 of the following five factors characterizes an individual as having MetS: waist circumference; blood pressure; triglycerides; HDL (good) cholesterol; blood sugar. Understanding who is at risk for which specific factors of MetS is important for implementing effective interventions to prevent and reduce the impact of the condition.

GNS and Aetna have partnered to develop Big Data analytics solutions to identify and characterize both those with MetS and at risk for MetS to learn what conditions a person is most likely to add or drop and ultimately which combinations of offerings – and for which types of people – are proving effective at driving better health outcomes. These models were built and applied to data from a national employer with over 100K employees. The data including diagnoses, procedures and medicines from claims, information from health risk appraisals, data from biometric screenings and lab results, and behavior measures for things like medication adherence and preventive health screenings. We will share results and discuss insights and challenges in working with real-world data.

Bruce Church
GNS Healthcare

Bruce Church leads the design and implementation of the company’s proprietary REFS™ inference and forward simulation engine.

An expert in computational biophysics and supercomputing, Bruce spent the previous decade developing global optimization methods for computational protein folding, the results of which have been published in several peer-reviewed journals. Bruce has been awarded and served as the principal investigator on several major grants, including a $2.5 million award from the Department of Energy. Bruce received a B.S. in Applied and Engineering Physics and a Ph.D. in Applied Physics from Cornell University in Ithaca, New York.

Greg Steinberg
Aetna

Gregory Steinberg serves as the head of Clinical Innovation at Aetna. He was previously the CEO and President of ActiveHealth Management between 2010 and 2011, and their Chief Medical Officer between 2000 and 2010.

Prior to ActiveHealth, Greg was the Associate Director of Medicine at St. Luke’s-Roosevelt Hospital Center in New York City from 1992-2000, and an Associate Clinical Professor of Medicine at the Columbia University College of Physicians and Surgeons. He currently is an Emeritus Attending Physician at St. Luke’s-Roosevelt Hospital Center.

Greg received his medical degree from the Welsh National School of Medicine in 1978, trained in Internal Medicine and Cardiovascular Disease at St. Luke’s Roosevelt in New York City, and is board-certified in Internal Medicine (1985) and Cardiovascular Diseases (1987).