Dilemmas in Personalizing Medicine:
Estimation of Heterogeneous Treatment Effects
Sanjay Basu, MD, PhD
Assistant Professor of Medicine, Stanford
Abstract: How can we estimate personalized risk/benefit calculations for individual patients from population and trial data? A number of traditional statistical and machine learning methods have been proposed, which we are formally comparing to see if they can address the dilemma of conflicting trial results, uncertainty in treatment recommendations, and the generation and evaluation of guidelines applied to diverse individuals.
Sanjay Basu, MD, PhD, is an Assistant Professor of Medicine at Stanford. He is a primary care physician and epidemiologist. He received his undergraduate education from the Massachusetts Institute of Technology (MIT), was a Rhodes Scholar at Oxford University, and received his MD and PhD at Yale University before completing his residency training in internal medicine at the University of California in San Francisco. Dr. Basu conducts research on health and social policies to reduce morbidity and mortality from cardiovascular disease and type II diabetes in both the United States and internationally, typically using methods from the fields of computer science, econometrics, and large-scale data analysis. Dr. Basu is currently Director of the Analytics and Modeling Core of Stanford’s SPHERE Center (Stanford Precision Health for Ethnic and Racial Equity) as well as serving as Co-Director for the Health Disparities section of Stanford’s Center for Population Health Sciences. He also serves in an advisory capacity for the United Nations, the World Health Organization, the Columbia University GRAPH Center, and Harvard Medical School’s Center for Primary Care. In 2013, he was named one of the “Top 100 Global Thinkers” by Foreign Policy Magazine, and in 2015 he was awarded the NIH Director’s New Innovator Award.
Snacks and beverages will be provided to those who RSVP.