Although applications of Machine Learning (ML) are now pervasive in the clinical literature, ML has yet to be embraced by the clinical community. So, what constitutes a good machine learning model for clinical applications? Certainly, a necessary condition for the success of any machine learning model is that it achieves an accuracy that is superior to pre-existing methods. In the healthcare sphere, however, accuracy alone does not, nor should it, ensure that a model will gain clinical acceptance. In view of the fact that no model, in practice, has 100% accuracy, attempts to understand when a given model is likely to fail should form an important part of the evaluation of any machine learning model that will be used clinically. Moreover, the most useful clinical models are explainable in the sense that it is possible to clearly articulate why the model arrives at a particular result for a given set of inputs. In this talk I will expand upon these challenges that make the creation of clinically useful ML models particularly difficult, and discuss ways in which they can be overcome.
Collin M. Stultz is Professor of Electrical Engineering and Computer Science and Professor in the Institute for Medical Engineering & Science at MIT, and Cardiologist, Division of Cardiology, at Massachusetts General Hospital. Dr. Stultz is a physician-scientist and academic at the Massachusetts Institute of Technology and Massachusetts General Hospital. He received his AB magna cum laude in Mathematics and Philosophy from Harvard College in 1988, as well as a MD magna cum laude from Harvard Medical School and a PhD in Biophysics from Harvard University, both in 1997. His PhD thesis work was done in the laboratory of Nobelist Martin Karplus. He is a past recipient of a Burroughs Wellcome Award in the Biomedical Sciences, and a NSF Career Award. He is also a member of the American Institute for Medical and Biological Engineering College of Fellows.
This event is sponsored by
Carleton Phi Beta Kappa, the Computer Science department, the Humanities Center, and The Andrew W. Mellon Foundation.
Logistics: Our speaker will be presenting remotely, by Zoom. Members of the on-campus community who wish to participate together can join a group of audience members in Olin 141 (no registration required). Others who wish to listen in from elsewhere are welcome to
register for a Zoom link here (your registration will be approved promptly so you do not have to register more than a few minutes in advance).