Friday, January 12, 2018
11 AM - 12 PM
With over 90% of care providers in the United States now using an electronic medical record system, health data is being collected at a scale (petabytes), resolution (up to 500Hz), and level of heterogeneity that is historically unprecedented. Beyond allowing for the study of rare disease conditions, the sheer magnitude of such data has facilitated the application of advanced algorithmic techniques (e.g. Deep Learning) to diagnose skin cancers, diabetic eye conditions, sepsis and other ailments. Health data collected in hospital settings provide an opportunity for prognostication and the reactionary optimization of care for the critically ill. When coupled with knowledge of patient physiology and behavior outside the hospital environment, health data may also clarify the causal factors of disease. The increasingly comprehensive digital footprint of human life (social media, email, phone records, GPS coordinates, etc.), and the use of wearable devices (e.g. Apple watch) can provide the missing data, and bring us closer to the goal of precision medicine. This talk will provide an overview of my work at the interface of machine learning, health, and behavioral science. The first project demonstrates a novel methodology for the prognostication of coma outcomes, after cardiac arrest. The second project provides a novel approach for passive monitoring of mood (happy or sad) using audio and physiological data sources. The third project presents a platform for addressing social isolation among college students, and its potential value for proactive optimization of behavior to address the underlying causes of health and behavioral tragedies.
Mohammad Ghassemi is completing his doctoral studies in Electrical Engineering and Computer Science at the Massachusetts Institute of Technology. As an undergraduate, he studied Electrical Engineering and graduated with highest honors as a Goldwater scholar. Mohammad later perused an MPhil in Information Engineering at the University of Cambridge where he was a recipient of the Gates-Cambridge Scholarship. Since arriving at MIT, he has perused research at the interface of machine learning and critical care medicine. Mohammad's doctoral focus is machine learning techniques in the context of multi-modal, multi-scale datasets. He has currently put together the largest collection of post-anoxic coma EEGs in the world, which he is investigating for his doctoral thesis. He has published over 20 journal and conference papers in top artificial intelligence and medical venues including: Intensive Care Medicine, Science Translational Medicine, Nature Scientific Data and the Proceedings of the Association for the Advancement of Artificial Intelligence. Mohammad's work has been covered by venues including: The Wall Street Journal, Wired and Newsweek. In addition to his research efforts, Mohammad is also involved in a range of entrepreneurial activities including a platform to facilitate connections between students, and an algorithm for social coaching.
Dr. Abdol-Hossein Esfahanian