Invited Talk

The Global Open Source Severity of Illness Scale (GOSSIS): Opportunities and Challenges

Speaker: Jesse D. Raffa, MIT Critical Data, Cambridge, MA

Abstract: This talk will provide an overview of MIT Critical Data’s effort to develop a global open severity of illness scale for critical care patients in collaboration with international partners. There is an increasing need for an openly available severity of illness scale which is well documented and easy to deploy. Many current offerings exist, but they are often: proprietary, expensive or developed at a single center or geographic region. Thus far, we have collaborators who have contributed data from North and South America, Asia and Oceania. We will discuss the current technical approach for handling this heterogeneous set of data, where differences in data collection practices and patient case mix can severely affect the ability to predict patient outcomes. The ability of models trained in one setting and applied in other settings will also be explored, with the ultimate aim to foster international collaboration in critical care research.

Bio: Dr. Jesse Raffa, PhD, is a Research Scientist at the Laboratory of Computational Physiology at MIT. His background is in data science, biostatistics and epidemiology, having completed a PhD in biostatistics from the University of Waterloo, Canada, and more recently, a postdoc at the University of Washington, USA. His methodological interests include modeling complex longitudinal data and reproducible research. He has collaborated with colleagues in a diverse set of fields including: virology, addiction, psychiatry, the social sciences, genetics and critical care. He was the recipient of the New Investigator of the Year for Clinical Science by the Canadian Association of HIV/AIDS Research in 2004, and winner of a Distinguished Student Paper award by the Eastern North American section of the International Biometrics Society in 2013. Dr. Raffa has organized several critical care datathons since joining the Laboratory of Computational Physiology, has chaired a session at the Joint Statistical Meetings, was a core-instructor for the MITx massive open online course, Global Health Informatics to Improve Quality of Care, and created the residential MIT course: HST.953, Collaborative Data Science in Medicine.