This talk presents two complementary approaches to optimizing population-based cancer screening programs: (i) use of partially observable Markov decision processes (POMDPs) to personalize screening decisions and (ii) use of the University of Breast Cancer Simulation Model.

Overview

Population-based cancer screening programs have been widely implemented to enable early cancer diagnosis and reduce mortality. However, screening also carries potential harms, including overdiagnosis, and false positives, which are not uncommon. As these tradeoffs vary based on individual risk profiles, it is essential to design screening strategies that balance benefits and harms at a personalized level. While most existing research and guidelines focus on population-level recommendations, our work proposes a personalized cancer screening policy tailored to an individual’s personal risk characteristics and screening history.

This talk presents two complementary approaches to optimizing cancer screening. The first part will describe the use of partially observable Markov decision processes (POMDPs) to personalize screening decisions. POMDP models can be used to address several controversial open research questions in cancer screening, such as when to start and stop screening and how often to screen. We demonstrate the development and application of a POMDP-based personalized cancer screening policy using breast cancer as an example. In addition, we briefly describe how nonadherence to the screening recommendations, limited screening resources, and existence of chronic conditions could be addressed using the POMDP modeling framework.

The second part of this talk will describe the use of the University of Breast Cancer Simulation Model (UWBCS), developed as part of the National Cancer Institute-funded Cancer Intervention and Surveillance Modeling Network (CISNET), to inform high-impact screening policy decisions. We will summarize how UWBCS contributed to the U.S. Preventive Services Task Force (USPSTF) screening guidelines for average-risk women in 2016 and 2024, influenced National Comprehensive Cancer Network (NCCN) recommendations for women with certain genetic mutations in 2024, and supported the development of the first-ever breast cancer screening recommendations for women with Down syndrome.

Presenters

Oguzhan Alagoz, Proctor & Gamble Bascom Professor, Industrial and Systems Engineering and Population Health Sciences, University of Wisconsin-Madison (UW–Madison)

Brief Biography

Oguzhan Alagoz is Proctor & 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, 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 120 refereed journal articles throughout his career. Furthermore, he has received various awards including the Baker Research award from IISE, a CAREER award from National Science Foundation (NSF), outstanding young industrial engineer in education award from IISE, Dantzig Dissertation Honorable Mention Award from INFORMS, 2nd place award from INFORMS Junior Faculty Interest Group best paper competition, best paper award from INFORMS Service Science Section, best podium presentation award from ISPOR, and best poster award from UW Carbone Comprehensive Cancer Center. He has been the principal investigator and co-investigator on grants totaling over $8 million, with an average annual research funding of approximately $500K, primarily funded by NIH and NSF.