AUTHOR=van Duuren Luuk A. , Ozik Jonathan , Spliet Remy , Collier Nicholson T. , Lansdorp-Vogelaar Iris , Meester Reinier G. S. 

TITLE=An Evolutionary Algorithm to Personalize Stool-Based Colorectal Cancer Screening

JOURNAL=Frontiers in Physiology

VOLUME=Volume 12 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2021.718276

DOI=10.3389/fphys.2021.718276

ISSN=1664-042X

ABSTRACT=Background: Fecal immunochemical testing (FIT) is an established method for colorectal cancer (CRC) screening. Measured FIT-concentrations are associated with both present and future risk of CRC, and may be used for personalized screening. However, evaluation of personalized screening is computationally challenging. In this study, an algorithm is presented to efficiently optimize personalized screening policies that prescribe screening intervals and FIT-cutoffs, based on age and FIT-history. It has the flexibility to combine with any simulation model that evaluates the generated policies in terms of costs and benefits.

Methods: We present a mathematical framework for personalized screening policies and a bi-objective Evolutionary Algorithm that identifies policies with minimal costs and maximal health benefits. The algorithm is combined with an established microsimulation model (MISCAN-Colon), to accurately estimate the costs and benefits of generated policies, without restrictive Markov assumptions. The performance of the algorithm is demonstrated in three experiments.

Results: In Experiment 1, a relatively small benchmark problem, the optimal policies are known. The algorithm approaches the maximum feasible benefits with a relative difference of 0.07%. Experiment 2 optimized both intervals and cutoffs, Experiment 3 optimized cutoffs only. Optimal policies in both experiments are unknown. Compared to policies recently evaluated for the USPSTF, personalized screening increased health benefits up to 14% and 4.3%, for Experiments 2 and 3 respectively, without adding costs. Generated policies have several features concordant with current screening recommendations.

Discussion: The method presented in this paper is flexible and capable of optimizing personalized screening policies evaluated with computationally-intensive but established simulation models. It could also be used to design screening policies for diseases other than CRC. In the case of CRC, more debate is needed on what features a policy needs to exhibit to make it suitable for implementation in practice.