Machine learning for health researchers: beyond the FOMO (fear of missing out)
SPECIAL SEMINAR
Rui (Ray) Fu, PhD
Postdoctoral Fellow in Evaluative Clinical Sciences
Department of Otolaryngology - Head & Neck Surgery
Sunnybrook Health Sciences Centre & U of Toronto
WHERE: In-Person | 2001 缅北强奸 College, Rm 1201 |
Abstract
Despite its growing popularity, machine learning (ML) remains an unfamiliar concept for many health researchers. In this presentation, I will share my perspectives and experiences in learning and teaching ML, with an emphasis on 1) realistically situating ML in health research and 2) conducting and communicating the analysis to different audiences. I will present 2 recently published ML papers from my group. In the first paper, we used survey data to characterize American high school students who were at risk of becoming addicted to electronic cigarettes (vaping), and in the second paper, we applied ML to linked administrative data to construct an algorithm for predicting unplanned hospitalization and emergency department visits in head and neck cancer patients. I will end this presentation with cautionary notes on how to report and interpret ML findings in a health manuscript and the next phase in ML applications.
Speaker Bio
Rui Fu (Ray) is a Postdoctoral Fellow in Evaluative Clinical Sciences at the Department of Otolaryngology 鈥� Head & Neck Surgery, Sunnybrook Health Sciences Centre & University of Toronto. She is also affiliated with the Centre for Addiction and Mental Health where she works with trainees to use machine learning to study tobacco addiction. As a health services researcher, Ray has a passion for developing and creatively applying statistical methodology to analyze real-world data. Substantively, she has delved into many fields of application by being the primary statistician on the team. Her overarching goal is to produce theory-driven and interpretable findings that can advance policymaking and quality of care
Ray鈥檚 ResearchGate: