Computational Medicine: Data Science as a Tool for Discovery
Much has been made about how algorithms will automate parts of medicine, such as the reading of an X-ray. Such a vision is too short-sighted, failing to recognize a far more transformative role data science can have in medicine. When it comes to the human body, we have far more data than understanding. Rather than simply automating our existing limited knowledge, algorithms can serve to radically expand that knowledge. In this talk I will describe how medicine can be a high dimensional empirical science: empirical science because the basic goal is improved understanding; and high dimensional because we rely on data, such as imaging, which is by its nature an immensely rich input source. I will illustrate the discoveries to be had when taking such an approach, illustrating the currently overlooked signal in X-rays and ECGs. I will also describe the technical and conceptual challenges that arise in trying to use machine learning algorithms as a tool for scientific discovery.
Sendhil Mullainathan is the Roman Family University Professor of Computation and Behavioral Science at Chicago Booth. His latest research is on computational medicine—applying machine learning and other data science tools to produce biomedical insights. In past work he has combined insights from behavioral science with empirical methods—experiments, causal inference tools, and machine learning—to study social problems such as discrimination and poverty. He currently teaches a course on Artificial Intelligence. Outside of research, he co-founded a non-profit to apply behavioral science (ideas42), a center to promote the use of randomized control trials in development (the Abdul Latif Jameel Poverty Action Lab), has worked in government in various roles, and currently serves on the board of the MacArthur Foundation board. He is also a regular contributor to the New York Times.