Please register for January’s AI4C Lecture Series on Eventbrite, and feel free to forward to anyone who may be interested!
Abstract: In virtually any practical field or application, discovering and implementing near-optimal decision strategies is essential for achieving desired outcomes, and for avoiding costly mistakes. Finding these strategies, however, usually requires substantial time, risk, and expensive trial and error. Recently, machine learning has been used to attack this problem, but unfortunately, most proposed solutions are “black box” algorithms, with underlying logic unclear to humans, significantly limiting their practical use and scientific value. In this work, we propose an alternative approach: repurposing machine learning to discover optimal, comprehensible strategies which can be understood, transferred, and used by humans directly. Through three common decision-making problems found in scheduling, we demonstrate the implementation and feasibility of this approach, as well as its great potential to attain optimal results.
AI4C Virtual Lecture Series are now CME approved! MDs, DOs, NPs, and PAs can receive CME Category 1 Credit. Other health care professionals can get participation certificates including Information Technology professionals. Use this link to register: Mass General Brigham Office of Continuing Professional Development
Oleg S. Pianykh, PhD, is the Director of Medical Analytics Group at Massachusetts General Hospital, and Assistant Professor at Harvard Medical School. Dr. Pianykh has been actively working on developing and implementing data-driven healthcare applications for the past 20 years, with projects ranging from digital image analysis and clinical workflow optimization to teaching graduate courses. Dr. Pianykh current interests include operations management, machine learning, and data analysis in healthcare.