Optimizing DTRs via threshold utility analysis on quality adjusted survival

Authors

  • Geoffrey S Johnson Center for Observational and Real-world Evidence, Merck & Co. Inc., West Point, PA 19426, U.S.A.
  • Andrew S Topp AbbVie Inc., Chicago, Illinois 60064, U.S.A.
  • Abdus S Wahed Department of Biostatistics, University of Pittsburgh, Pittsburgh, PA 15261, U.S.A.

Keywords:

Counterfactuals; Dynamic treatment regime; Inverse probability weighting; m-out-of-n bootstrap; Potential outcomes; Quality adjusted lifetime; Qlearning; Survival analysis; Threshold utility analysis.

Abstract

The analysis of quality adjusted lifetime adds an interesting wrinkle to the field of dynamic treatment regimes (DTRs), in that the optimal regime will not only depend on patient information (including treatments taken, intermediate outcomes, and other patient covariates), but it will also depend on information on the treatments themselves, e.g. monetary cost or toxicity. The focus of this paper is to investigate a form of Q-learning using estimating equations for the quality adjusted survival outcome. We use m-out-of-n bootstrap for inference and threshold utility analysis to show how the patient-specific optimal regime varies according to the treatment characteristics (e.g. cost, side effects). Methodologies developed are investigated through a simulation study and are demonstrated to construct optimal treatment regimes for the treatment of children’s neuroblastoma.

Journal of Statistical Research 2021, Vol. 55, No. 1, pp. 127-145

Abstract
24
PDF
13

Downloads

Published

2021-12-09

How to Cite

Johnson, G. S., Topp, A. S. ., & Wahed, A. S. (2021). Optimizing DTRs via threshold utility analysis on quality adjusted survival. Journal of Statistical Research, 55(1), 127–145. Retrieved from https://banglajol.info/index.php/JStR/article/view/56580

Issue

Section

Articles