How Do Tumor Cytogenetics Inform Cancer Treatments? Dynamic Risk Stratification and Precision Medicine Using Multi-armed Bandits

51 Pages Posted: 12 Jul 2019 Last revised: 6 Jul 2021

See all articles by Zhijin Zhou

Zhijin Zhou

University of Washington - Michael G. Foster School of Business

Yingfei Wang

University of Washington - Michael G. Foster School of Business

Hamed Mamani

University of Washington - Michael G. Foster School of Business

David G. Coffey

Fred Hutchinson Cancer Research Center

Date Written: June 17, 2019

Abstract

Multiple myeloma is an incurable cancer of bone marrow plasma cells with a median overall survival of 5 years. With newly approved drugs to treat this disease over the last decade, physicians are afforded more opportunities to tailor treatment to individual patients and thereby improve survival outcomes and quality of life. However, since the optimal sequence of therapy is unknown, selecting a treatment that will result in the most effective outcome for each individual patient is challenging. This paper addresses this challenge, considering the problem of designing personalized treatment recommendations for patients with multiple myeloma using a data-driven analytics method. We formulate the treatment recommendation problem as a Bayesian contextual bandit, which sequentially selects treatments based on contextual information about patients and therapies, with the goal of maximizing overall survival outcomes. We developed a multilevel Bayesian linear Thompson sampling to learn patients’ heterogeneous response on treatment decisions, which allows us to flexibly account for patient and line-of-therapy level heterogeneity even in the absence of a large number of observations.

Facing the difficulty of evaluating the performance of the policy with only observational data, we propose a causal offline evaluation approach to measure the effect of the treatment in the presence of unmeasured confounders. We evaluate the performance of our policy on clinical data collected from 803 patients treated at Seattle Cancer Care Alliance. Our policy achieved an 19.75\% predicted improvement compared to the current clinical practice, and outperforms other benchmark strategies. Moreover, our policy achieves higher improvement for aging or high-risk patients with more complications by keeping the disease controlled at a relatively stable condition.

Keywords: Multiple Myeloma, Precision Medicine, Multi-Armed Bandit, Thompson Sampling, Hidden Markov Model (HMM)

Suggested Citation

Zhou, Zhijin and Wang, Yingfei and Mamani, Hamed and Coffey, David G., How Do Tumor Cytogenetics Inform Cancer Treatments? Dynamic Risk Stratification and Precision Medicine Using Multi-armed Bandits (June 17, 2019). Available at SSRN: https://ssrn.com/abstract=3405082 or http://dx.doi.org/10.2139/ssrn.3405082

Zhijin Zhou (Contact Author)

University of Washington - Michael G. Foster School of Business ( email )

Box 353200
Seattle, WA 98195-3200
United States

Yingfei Wang

University of Washington - Michael G. Foster School of Business ( email )

Box 353200
Seattle, WA 98195-3200
United States

Hamed Mamani

University of Washington - Michael G. Foster School of Business ( email )

Box 353200
Seattle, WA 98195-3200
United States

David G. Coffey

Fred Hutchinson Cancer Research Center ( email )

Seattle, WA
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
200
Abstract Views
918
rank
215,352
PlumX Metrics