The Computational Phenotype Discovery Problem
Wednesday, October 21, 2015
3:30 pm - 4:30 pm
Gross Hall 330
Tom Lasko, Vanderbilt University School of Medicine
12 noon lunch/learner discussion with grad students and postdocs 3:30 pm seminar/reception Abstract: One of the key advances that we're going to need in order to achieve precision, personalized medicine is to stop using our broad, clinically-driven descriptions (or phenotypes) of each disease, and start allowing large clinical datasets to speak for themselves, to tell us in high resolution what all of the phenotypes really are, including how they progress over time. In this talk I will present the phenotype discovery problem, discuss some of the computational challenges it involves, describe my machine-learning approach to it, and present some early results. Bio: Tom Lasko is an Assistant Professor of Biomedical Informatics at Vanderbilt University School of Medicine. He has a PhD in Computer Science from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) and an MD from UC San Diego. His current research at Vanderbilt is in the computational aspects of precision, personalized medicine.