Clin Trials. 2014 Aug;11(4):400-407. doi: 10.1177/1740774514532570. Epub 2014 May 28.
Estimation of optimal dynamic treatment regimes.
Clinical trials (London, England)
Ying-Qi Zhao, Eric B Laber
Affiliations
Affiliations
- Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI, USA [email protected].
- Department of Statistics, North Carolina State University, Raleigh, NC, USA.
PMID: 24872361
PMCID: PMC4247353 DOI: 10.1177/1740774514532570
Abstract
BACKGROUND: Recent advances in medical research suggest that the optimal treatment rules should be adaptive to patients over time. This has led to an increasing interest in studying dynamic treatment regime, a sequence of individualized treatment rules, one per stage of clinical intervention, which maps present patient information to a recommended treatment. There has been a recent surge of statistical work for estimating optimal dynamic treatment regimes from randomized and observational studies. The purpose of this article is to review recent methodological progress and applied issues associated with estimating optimal dynamic treatment regimes.
METHODS: We discuss sequential multiple assignment randomized trials, a clinical trial design used to study treatment sequences. We use a common estimator of an optimal dynamic treatment regime that applies to sequential multiple assignment randomized trials data as a platform to discuss several practical and methodological issues.
RESULTS: We provide a limited survey of practical issues associated with modeling sequential multiple assignment randomized trials data. We review some existing estimators of optimal dynamic treatment regimes and discuss practical issues associated with these methods including model building, missing data, statistical inference, and choosing an outcome when only non-responders are re-randomized. We mainly focus on the estimation and inference of dynamic treatment regimes using sequential multiple assignment randomized trials data. Dynamic treatment regimes can also be constructed from observational data, which may be easier to obtain in practice; however, care must be taken to account for potential confounding.
© The Author(s), 2014.
References
- J Mach Learn Res. 2005 Jul;6:1073-1097 - PubMed
- Lancet Oncol. 2010 Oct;11(10):934-41 - PubMed
- Stat Med. 2012 Jul 30;31(17):1887-902 - PubMed
- Scand Stat Theory Appl. 2009 Sep 22;37(1):126-146 - PubMed
- Biometrika. 2013;100(3): - PubMed
- Biometrika. 2011 Sep;98(3):503-518 - PubMed
- N Engl J Med. 1995 Jun 22;332(25):1671-7 - PubMed
- Biometrics. 2013 Sep;69(3):714-23 - PubMed
- Biometrics. 2011 Dec;67(4):1422-33 - PubMed
- Ann Oncol. 1994 Dec;5(10):921-8 - PubMed
- J Clin Child Adolesc Psychol. 2006 Sep;35(3):369-85 - PubMed
- Clin Trials. 2004 Feb;1(1):9-20 - PubMed
- Stat Med. 2004 Nov 15;23(21):3249-62 - PubMed
- J Mach Learn Res. 2012 Nov;13(Nov):3253-3295 - PubMed
- Ann Stat. 2012 Feb 1;40(1):529-560 - PubMed
- Neuropsychopharmacology. 2007 Feb;32(2):257-62 - PubMed
- Cancer. 1997 Dec 15;80(12):2222-9 - PubMed
- Schizophr Bull. 2003;29(1):15-31 - PubMed
- Biometrics. 2007 Jun;63(2):447-55 - PubMed
- Biometrics. 2012 Dec;68(4):1010-8 - PubMed
- J Clin Oncol. 2006 Jul 1;24(19):3121-7 - PubMed
- Int J Biostat. 2010;6(2):Article 8 - PubMed
- Math Comput Model Dyn Syst. 2011 Jan 12;17(2):183-203 - PubMed
- Stat Sci. 2014 Nov;29(4):640-661 - PubMed
- Mach Learn. 2011 Jul 1;84(1-2):109-136 - PubMed
- Psychol Methods. 2012 Dec;17(4):478-94 - PubMed
- Drug Alcohol Depend. 2007 May;88 Suppl 2:S31-40 - PubMed
- Psychol Methods. 2012 Dec;17(4):457-477 - PubMed
- Biometrics. 2010 Dec;66(4):1192-201 - PubMed
- Stat. 2012 Jan 1;1(1):103-114 - PubMed
- Stat Med. 2009 Nov 20;28(26):3294-315 - PubMed
- J Consult Clin Psychol. 2002 Apr;70(2):320-35 - PubMed
- N Engl J Med. 1999 Oct 14;341(16):1165-73 - PubMed
- Int J Biostat. 2010;6(2):Article 18 - PubMed
- Clin Trials. 2009 Oct;6(5):480-90 - PubMed
- J Am Stat Assoc. 2012 Sep 1;107(449):1106-1118 - PubMed
- Stat Methods Med Res. 2010 Jun;19(3):317-43 - PubMed
- Stat Med. 2005 May 30;24(10):1455-81 - PubMed
- Biometrics. 2014 Mar;70(1):53-61 - PubMed
Publication Types
Grant support