A Markov Decision Process Model to Guide Treatment of Abdominal Aortic Aneurysms

TL;DR

This paper develops a Markov decision process model to optimize treatment strategies for abdominal aortic aneurysms, considering patient age and aneurysm size to improve quality-adjusted life-years over current policies.

Contribution

It introduces a novel MDP-based treatment policy that accounts for factors ignored by current guidelines, proposing more personalized and potentially more effective treatment decisions.

Findings

Optimal policy suggests surgery for young patients with small aneurysms.

Simulation shows increased expected QALYs with the new policy.

Policy differs structurally from current clinical guidelines.

Abstract

An abdominal aortic aneurysm (AAA) is an enlargement of the abdominal aorta which, if left untreated, can progressively widen and may rupture with fatal consequences. In this paper, we determine an optimal treatment policy using Markov decision process modeling. The policy is optimal with respect to the number of quality adjusted life-years (QALYs) that are expected to be accumulated during the remaining life of a patient. The new policy takes into account factors that are ignored by the current clinical policy (e.g. the life-expectancy and the age-dependent surgical mortality). The resulting optimal policy is structurally different from the current policy. In particular, the policy suggests that young patients with small aneurysms should undergo surgery. The robustness of the policy structure is demonstrated using simulations. A gain in the number of expected QALYs is shown, which indicates a possibility of improved care for patients with AAAs.