ORIE Special Seminar: Holly Wiberg '16 (MIT) - Data-Driven Healthcare via Constraint Learning and Analytics
Frank H. T. Rhodes Hall 253
The proliferation of digitally-available medical data has enabled a new paradigm of decision-making in medicine. Machine learning allows us to glean large-scale insights directly from data, systematizing the heuristic risk assessment process that physicians use on a local scale. Optimization similarly adds rigor to decision-making, providing a quantitative framework for optimizing decisions under certain constraints. The rise in data, coupled with methodological and computational advancements in these fields, presents both opportunities and novel challenges. In this talk, we harness the power of machine learning and optimization to learn from data and drive better decisions. In the first part of the talk, we introduce a constraint learning framework that embeds trained machine learning models directly into mixed-integer optimization formulations and highlights an application in chemotherapy regimen design. The second part of the talk demonstrates the use of analytics to address the COVID-19 pandemic, specifically for clinical risk assessment and resource allocation. We develop methods and applied models to bridge the gap between research and clinical practice, with interpretability and practicality as guiding principles.
Holly Wiberg ‘16 is a fifth-year Ph.D. student at MIT's Operations Research Center advised by Dimitris Bertsimas. Her research leverages optimization and machine learning to improve healthcare in both clinical and operational settings. She has developed novel approaches to enable data-driven decision-making, including prescriptive frameworks and interpretable methods. In parallel, she has collaborated extensively with medical organizations from both the U.S. and Europe on projects spanning oncology, pediatric trauma, and COVID-19. Her work with the MIT COVID Analytics team was awarded the Pierskalla Award for best healthcare paper (INFORMS 2020). Prior to MIT, Holly was a data scientist at athenahealth. She received her B.S. in operations research and engineering from Cornell University in 2016. Her work is supported by an NSF Graduate Research Fellowship.