SPEAKER:  Turgay Ayer, Faculty Candidate

ABSTRACT:

Breast cancer is the most common cancer and the principal cause of cancer deaths in women worldwide. Although mammography is the most effective modality for breast cancer screening, it has several potential risks, including high false-positive rates. Benefits and harms of mammography depend on personal characteristics of women and balancing these benefits and harms is critical in designing a mammography screening schedule. In contrast to prior research and existing breast cancer screening guidelines which consider population-based screening recommendations, we propose a personalized mammography screening policy based on the personal risk characteristics of women and their prior screening history.

We develop a novel finite-horizon partially observable Markov decision process (POMDP) model for this problem. Our POMDP model incorporates two methods of detection (self or screen), age-specific disease progression, mortality rates, and mammography test characteristics, as well as prior screening history. We use a validated micro-simulation model based on real data in estimating the parameters and solve this POMDP model optimally for individual patients. Our results show that our proposed personalized screening schedules outperform the existing guidelines with respect to the total expected quality-adjusted life years, while significantly decreasing the number of mammograms and false-positives. We further find that the mammography screening threshold risk increases with age. We derive several structural properties of the model, including the sufficiency conditions that ensure the existence of a control-limit policy.