Tools for the Precision Medicine Era: How to Develop Highly Personalized Treatment Recommendations from Cohort and Registry Data Using Q-Learning

Elizabeth F. Krakow, Michael Hemmer, Tao Wang, Brent Logan, Mukta Arora, Stephen Spellman, Daniel Couriel, Amin Alousi, Joseph Pidala, Michael Last, Silvy Lachance, Erica E.M. Moodie

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

Q-Learning is a method of reinforcement learning that employs backwards stagewise estimation to identify sequences of actions that maximize some long-term reward. The method can be applied to sequential multipleassignment randomized trials to develop personalized adaptive treatment strategies (ATSs)-longitudinal practice guidelines highly tailored to time-varying attributes of individual patients. Sometimes, the basis for choosing which ATSs to include in a sequential multiple-assignment randomized trial (or randomized controlled trial) may be inadequate. Nonrandomized data sources may inform the initial design of ATSs, which could later be prospectively validated. In this paper, we illustrate challenges involved in using nonrandomized data for this purpose with a case study from the Center for International Blood and Marrow Transplant Research registry (1995-2007) aimed at 1) determining whether the sequence of therapeutic classes used in graft-versus-host disease prophylaxis and in refractory graft-versus-host disease is associated with improved survival and 2) identifying donor and patient factors with which to guide individualized immunosuppressant selections over time. We discuss how to communicate the potential benefit derived from following an ATS at the population and subgroup levels and how to evaluate its robustness to modeling assumptions. This worked example may serve as a model for developing ATSs from registries and cohorts in oncology and other fields requiring sequential treatment decisions.

Original languageEnglish (US)
Pages (from-to)160-172
Number of pages13
JournalAmerican journal of epidemiology
Volume186
Issue number2
DOIs
StatePublished - Jul 15 2017

Bibliographical note

Funding Information:
E.F.K. was supported by the Cole Foundation. E.E.M.M. was supported by the Fonds de recherche du Québec–Santé. We thank the Audiovisual Service of Hôpital Maisonneuve-Rosemont and Helen Crawford of the Fred Hutchinson Cancer Research Center for assistance with figure preparation. Conflict of interest: none declared.

Publisher Copyright:
© 2017 The Author(s).

Keywords

  • Adaptive treatment strategies
  • Dynamic treatment regimes
  • Graft-versus-host disease
  • Machine learning
  • Personalized medicine
  • Prediction
  • Q-learning
  • Registry data

Fingerprint

Dive into the research topics of 'Tools for the Precision Medicine Era: How to Develop Highly Personalized Treatment Recommendations from Cohort and Registry Data Using Q-Learning'. Together they form a unique fingerprint.

Cite this