Jones Seminar: Advances in Personalized Medicine and Public Health via Data-driven Optimization and Machine Learning

Optional ZOOM LINK
Meeting ID: 935 8655 7757
Passcode: 008066

The sheer volume at which data have been generated in the past decade has created the opportunity to revolutionize nearly every aspect of healthcare. In patient-level disease monitoring and treatment planning, these data can be used to generate individualized forecasts for a person’s future disease trajectory, and, accordingly, identify the optimal course of treatments in real-time. At the population-level, these data can facilitate the identification of emerging trends, forecast public health crises months in advance, and inform which interventions should be deployed. However, to harness the potential in these data, emerging prediction and decision technologies must address fundamental challenges in data-driven modeling, including: understanding how these data were generated, what information the data do (and do not) contain, how unintended consequences (e.g., biases and uncertainty) can propagate in data-driven systems, and how to synthesize multiple disjoint data sources.

In an effort to address these fundamental challenges, my research group focuses on the design, analysis, and optimization of novel data-driven frameworks at the intersection of mathematical optimization and machine learning. This work is largely motivated by high-impact problems from various disease areas, including concussion, chronic disease management, and opioid-related overdose. In this talk, I will discuss our recent and ongoing work in personalized medicine and public health, highlighting both the methodological advances and potential practical impact of this work.

Hosted by Professor Wesley Marrero.

About the Speaker(s)

Gian-Gabriel Garcia
Assistant Professor of Industrial & Systems Engineering, U Washington

Gian-Gabriel Garcia is an assistant professor of industrial and systems engineering at the University of Washington. He earned his PhD and MS in industrial and operations engineering at the University of Michigan and a BS in industrial engineering from the University of Pittsburgh. His research interests are in the design, analysis, and optimization of data-driven frameworks at the intersection of optimization, machine learning, and artificial intelligence as motivated by high-impact problems in medical decision-making, health policy, and healthcare operations. Garcia has received several scholarly recognitions for his scholarship, including the IISE Transactions Best Paper Award in Operations Engineering and Analytics, INFORMS Minority Issues Forum Best Paper Award, INFORMS Bonder Scholarship, and the Society for Medical Decision Making's Lee B. Lusted Prize in Quantitative Methods and Theoretical Developments.

Contact

For more information, contact Amos Johnson at amos.l.johnson@dartmouth.edu.