Prof. Dr. Oguzhan Alagoz
University of Wisconsin-Madison, USA
Oguzhan Alagoz is Procter & Gamble Bascom Professor of Industrial and Systems Engineering and Population Health Sciences at the University of Wisconsin-Madison. His research interests include stochastic optimization, medical decision making, completely and partially observable Markov decision processes, simulation, risk-prediction modeling, and health technology assessment. He served as a member of ISPOR-SMDM Modeling Good Research Practices Task Force which developed recommendations for good modeling practices in state-transition modeling for the evaluation of health care decisions in 2012. He is also co-leading the University of Wisconsin Breast Cancer Simulation Model, a member of the National Cancer Institute’s Cancer Intervention and Surveillance Modeling Network (CISNET), that was used to inform national breast cancer screening guidelines in the US in 2016 and 2024. He is currently serving as an associate editor for Operations Research. He previously served as the editor-in-chief of IISE Transactions on Healthcare Systems Engineering, the flagship journal of IISE in the area of healthcare systems engineering and on the editorial board of Medical Decision Making and IISE Transactions. He is an elected fellow of IISE. He published over 110 refereed journal articles throughout his career. His research has been recognized with numerous awards, including the IISE David F. Baker Distinguished Research Award, the premier research award from IISE, a CAREER Award from the National Science Foundation, the IISE Outstanding Young Industrial Engineer in Education Award, and several Best Paper Awards from INFORMS.
Keynote
- Date
- Time
- RoomKhalifa University Auditorium
Harnessing the Potential of Operations Research to Optimize Health Policy and Medical Decisions: Lessons from Cancer Screening
Healthcare should be one of the most fertile domains for operations research. We now have vast amounts of data, creating the possibility of moving beyond broad, population-level recommendations toward more personalized and evidence-based medical decisions. Yet despite extraordinary methodological advances, that potential remains underused. Operations research does not lack sophisticated methods; it lacks sufficient emphasis on translation and impact. Too often, methodological novelty is rewarded more than the difficult work of building credible models from imperfect real-world data, validating them rigorously, and carrying their results across the final mile into clinical practice and health policy.
In this keynote, I will argue that making operations research consequential in healthcare requires a somewhat different mindset. Technical rigor remains essential, but it must be accompanied by patience, high-quality numerical work, transparency about uncertainty, and sustained collaboration with clinicians, scientists, and policymakers who are genuinely invested in the decisions being studied. Impact rarely comes from a single elegant model. It emerges from years of model development, calibration, validation, refinement, and engagement with decision makers—and from a willingness to address the messy realities that often lie outside the traditional definition of methodological contribution.
I will illustrate these lessons through cancer screening and the National Cancer Institute’s Cancer Intervention and Surveillance Modeling Network (CISNET), focusing on breast cancer modeling at the University of Wisconsin. Over two decades, CISNET models have informed major U.S. breast cancer screening recommendations, with modeling evidence incorporated into guidelines that now shape screening decisions in clinical practice. This progression—from mathematical modeling, to evidence generation, to policy, and ultimately to clinical care—demonstrates the potential of rigorous operations research to influence decisions at both the population and individual-patient levels. The lessons extend well beyond cancer screening. If operations research is to fulfill its potential in healthcare, our goal cannot simply be to develop better models—it must be to develop models that are trusted, used, and capable of changing decisions.