2019/11/11 by Niklas Rindtorff, Mingyu Lu, Rindtorff, Niklas T. +7
Biochemistry, Genetics and Molecular Biology · Decision Sciences · Medicine · #Advanced Bandit Algorithms Research #Artificial Intelligence in Healthcare and Education #Cell Image Analysis Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.1911.04389
openalex publication_date 2019/11/11 · openalex created_date 2019/11/22 · openalex updated_date 2026/07/28
Precision oncology, the genetic sequencing of tumors to identify druggable targets, has emerged as the standard of care in the treatment of many cancers. Nonetheless, due to the pace of therapy development and variability in patient information, designing effective protocols for individual treatment assignment in a sample-efficient way remains a major challenge. One promising approach to this problem is to frame precision oncology treatment as a contextual bandit problem and to apply sequential decision-making algorithms designed to minimize regret in this setting. However, a clear prerequisite for considering this methodology in high-stakes clinical decisions is careful benchmarking to understand realistic costs and benefits. Here, we propose a benchmark dataset to evaluate contextual bandit algorithms based on real in vitro drug response of approximately 900 cancer cell lines. Specifically, we curated a dataset of complete treatment responses for a subset of 7 treatments from prior in vitro studies. This allows us to compute the regret of proposed decision policies using biologically plausible counterfactuals. We ran a suite of Bayesian bandit algorithms on our benchmark, and found that the methods accumulate less regret over a sequence of treatment assignment tasks than a rule-based baseline derived from current clinical practice. This effect was more pronounced when genomic information was included as context. We expect this work to be a starting point for evaluation of both the unique structural requirements and ethical implications for real-world testing of bandit based clinical decision support.