Stratified Breast Cancer Follow-Up Using a Continuous-state POMDP.

Frequency and duration of follow-up for patients with breast cancer is still under discussion. Current follow-up consists of annual mammography for the first five years after treatment and does not depend on the personal risk of developing a locoregional recurrence (LRR) or second primary tumor. Aim of this study is to formulate a continuous-state POMDP, in which at every epoch a decision is made whether or not to test, based on the personal risk factors of the patient. We show that the optimal value function of the POMDP is piece-wise linear and convex (PWLC). This result provides an alternative expression of the optimal value function, which leads to a solution algorithm for the POMDP. Under some conditions the optimal value function can be obtained by a simple solution algorithm. We present results for this case to illustrate how the model can be applied in practice.