Sample size considerations for comparing dynamic treatment regimens in a sequential multiple-assignment randomized trial with a continuous longitudinal outcome

Abstract

Clinicians and researchers alike are increasingly interested in how best to personalize interventions. A dynamic treatment regimen is a sequence of prespecified decision rules which can be used to guide the delivery of a sequence of treatments or interventions that is tailored to the changing needs of the individual. The sequential multiple-assignment randomized trial is a research tool which allows for the construction of effective dynamic treatment regimens. We derive easy-to-use formulae for computing the total sample size for three common two-stage sequential multiple-assignment randomized trial designs in which the primary aim is to compare mean end-of-study outcomes for two embedded dynamic treatment regimens which recommend different first-stage treatments. The formulae are derived in the context of a regression model which leverages information from a longitudinal outcome collected over the entire study. We show that the sample size formula for a sequential multiple-assignment randomized trial can be written as the product of the sample size formula for a standard two-arm randomized trial, a deflation factor that accounts for the increased statistical efficiency resulting from a longitudinal analysis, and an inflation factor that accounts for the design of a sequential multiple-assignment randomized trial. The sequential multiple-assignment randomized trial design inflation factor is typically a function of the anticipated probability of response to first-stage treatment. We review modeling and estimation for dynamic treatment regimen effect analyses using a longitudinal outcome from a sequential multiple-assignment randomized trial, as well as the estimation of standard errors. We also present estimators for the covariance matrix for a variety of common working correlation structures. Methods are motivated using the ENGAGE study, a sequential multiple-assignment randomized trial aimed at developing a dynamic treatment regimen for increasing motivation to attend treatments among alcohol- and cocaine-dependent patients.

Keywords

Sample size sequential multiple-assignment randomized trials dynamic treatment regimens longitudinal data

Get full access to this article

View all access options for this article.

References

Kosorok

Moodie

EEM

. Adaptive treatment strategies in practice, Philadelphia: Society for Industrial and Applied Mathematics, 2016.

Chakraborty

Moodie

EEM

. Statistical methods for dynamic treatment regimes, New York: Springer, 2013. ISBN 1461474280.

McKay

Drapkin

Van Horn

DHA

, et al. Effect of patient choice in an adaptive sequential randomization trial of treatment for alcohol and cocaine dependence. J Consult Clin Psychol 2015; 83: 1021–1032.

Wallace

Moodie

EEM

. Personalizing medicine: a review of adaptive treatment strategies. Pharmacoepidem Dr S 2014; 23: 580–585.

Ogbagaber

Karp

Wahed

. Design of sequentially randomized trials for testing adaptive treatment strategies. Stat Med 2016; 35: 840–858.

Almirall

Nahum-Shani

Sherwood

, et al. Introduction to SMART designs for the development of adaptive interventions: with application to weight loss research. Transl Behav Med 2014; 4: 260–274.

Nahum-Shani

Qian

Almirall

, et al. Experimental design and primary data analysis methods for comparing adaptive interventions. Psychol Methods 2012; 17: 457–477.

Lavori

Dawson

. A design for testing clinical strategies: biased individually tailored within-subject randomization. J R Stat Soc A Stat 2000; 163: 29–38.

Lavori

Dawson

. Dynamic treatment regimes: practical design considerations. Clin Trials 2004; 1: 9–20.

10.

Murphy

. An experimental design for the development of adaptive treatment strategies. Stat Med 2005; 24: 1455–1481.

11.

Auyeung

Long

Royster

, et al. Sequential multiple-assignment randomized trial design of neurobehavioral treatment for patients with metastatic malignant melanoma undergoing high-dose interferon-alpha therapy. Clin Trials 2009; 6: 480–490.

12.

Kidwell

. SMART designs in cancer research: past, present, and future. Clin Trials 2014; 11: 445–456.

13.

Thall PF. SMART design, conduct, and analysis in oncology. In Kosorok MR and Moodie EEM (eds) Adaptive Treatment Strategies in Practice, 1 ed., chapter 4. Philadelphia: Society for Industrial and Applied Mathematics, 2016, pp. 41–54.

14.

Diegidio P, Hermiz S, Hibbard J et al. Hypertrophic burn scar research: from quantitative assessment to designing clinical sequential multiple assignment randomized trials. Clin Plast Surg 2017; 44: 917–924. DOI:10.1016/j.cps.2017.05.024.

15.

Hibbard JC, Friedstat JS, Thomas SM, et al. LIBERTI: a SMART study in plastic surgery. Clin Trials 2018; 15: 286–293. DOI:10.1177/1740774518762435.

16.

Murphy

Lynch

Oslin

, et al. Developing adaptive treatment strategies in substance abuse research. Drug Alcohol Depen 2007; 88: S24–S30.

17.

Kasari

Kaiser

Goods

, et al. Communication interventions for minimally verbal children with autism: a sequential multiple assignment randomized trial. J Am Acad Child Psy 2014; 53: 635–646.

18.

Murphy

. Sample size formulae for two-stage randomized trials with survival outcomes. Biometrika 2011; 98: 503–518.

19.

Kidwell KM, Seewald NJ, Tran Q, et al. Design and analysis considerations for comparing dynamic treatment regimens with binary outcomes from sequential multiple assignment randomized trials. J Appl Stat 2017; 45: 1628–1651. DOI:10.1080/02664763.2017.1386773.

20.

Necamp T, Kilbourne A and Almirall D. Comparing cluster-level dynamic treatment regimens using sequential, multiple assignment, randomized trials: regression estimation and sample size considerations. Stat Methods Med Res 2017: 26: 1572–1589. DOI:10.1177/0962280217708654.

21.

Nahum-Shani

Kasari

, et al. Comparing dynamic treatment regimes using repeated-measures outcomes: modeling considerations in SMART studies. Stat Med 2016; 35: 1595–1615.

22.

. Comparison of adaptive treatment strategies based on longitudinal outcomes in sequential multiple assignment randomized trials. Stat Med 2017; 36: 403–415. DOI:10.1002/sim.7136.

23.

Oslin DW. Managing alcoholism in people who do not respond to naltrexone (EXTEND), 2005, https://clinicaltrials.gov/ct2/show/NCT00115037.

24.

Fitzsimons

Tuten

O’Grady

, et al. A smart design: response to reinforcement-based treatment intensity among pregnant, drug-dependent women. Drug Alcohol Depen 2015; 156: e69–e69. DOI:10.1016/j.drugalcdep.2015.07.1106.

25.

Rothman

Vock

, et al. Program for lung cancer screening and tobacco cessation: study protocol of a sequential, multiple assignment, randomized trial. Contemp Clin Trials 2017; 60: 86–95.

26.

Eckshtain D. Using SMART experimental design to personalize treatment for child depression, 2013, https://clinicaltrials.gov/ct2/show/NCT01880814.

27.

Pelham

Fabiano

Waxmonsky

, et al. Treatment sequencing for childhood ADHD: a multiple-randomization study of adaptive medication and behavioral interventions. J Clin Child Adolesc 2016; 45: 396–415. DOI:10.1080/15374416.2015.1105138.

28.

Budney AJ. Behavioral treatment of adolescent substance use (SMART), 2014, https://clinicaltrials.gov/ct2/show/NCT02063984.

29.

Almirall

DiStefano

Chang

, et al. Longitudinal effects of adaptive interventions with a speech-generating device in minimally verbal children with ASD. J Clin Child Adolesc 2016; 4416: 1–15. DOI:10.1080/15374416.2016.1138407.

30.

Kilbourne

Abraham

Goodrich

, et al. Cluster randomized adaptive implementation trial comparing a standard versus enhanced implementation intervention to improve uptake of an effective re-engagement program for patients with serious mental illness. Implement Sci 2013; 8: 136–136. http://www.implementationscience.com/content/8/1/136 .

31.

Lei

Nahum-shani

Lynch

, et al. A “SMART” design for building individualized treatment sequences. Annu Rev Clin Psycho 2012; 8: 21–48.

32.

Vaart

AWvd

. Asymptotic statistics, Cambridge Series in Statistical and Probabilistic Mathematics, Cambridge University Press, 1998. DOI:10.1017/CBO9780511802256.

33.

Liang

Zeger

. Longitudinal data analysis using generalized linear models. Biometrika 1986; 73: 13–22. DOI:10.1093/biomet/73.1.13.

34.

Ahn C, Heo M and Zhang S. Sample size calculations for clustered and longitudinal outcomes in clinical research. Chapman & Hall/CRC Biostatistics Series, Boca Raton: CRC Press, 2015. ISBN 978-1-4667-5626-3.

35.

Fitzmaurice

Laird

Ware

. Applied longitudinal analysis, 2nd ed. Hoboken: Wiley, 2011.

36.

Bowden CL. Sequential multiple assignment treatment for bipolar disorder, https://clinicaltrials.gov/ct2/show/NCT01588457, 2017.

37.

Cohen

. Statistical power analysis for the behavioral sciences, volume 2nd ed. New York: Routledge, 1988. ISBN 0805802835.

38.

Oetting AI, Levy JA, Weiss RD, et al. Statistical methodology for a SMART design in the development of adaptive treatment strategies. In Shrout P, Keyes K and Ornstein K (eds) Causality psychopathology: finding determinants of disorders and their cures. Arlington, VA: American Psychiatric Publishing, Inc., 2011. pp. 179–205.

39.

Kahan

Jairath

Doré

, et al. The risks and rewards of covariate adjustment in randomized trials: an assessment of 12 outcomes from 8 studies. Trials 2014; 15: 1–7.

40.

Friedman LM, Furberg CD and Demets DL. Fundamentals of clinical trials. 4th ed. New York: Springer, 2010. ISBN 9781441915856. DOI:10.1007/978-1-4419-1586-3. arXiv:1011.1669v3.

41.

Watkins Christopher JCH. Learning from delayed rewards. PhD Thesis, King’s College, 1989, http://www.cs.rhul.ac.uk/∼chrisw/new–thesis.pdf.

42.

Nahum-Shani

Qian

Almirall

, et al. Q-learning: a data analysis method for constructing adaptive interventions. Psychol Methods 2012; 17: 478–494.

43.

Zhang

Laber

Tsiatis

, et al. Using decision lists to construct interpretable and parsimonious treatment regimes. Biometrics 2015; 71: 895–904.

44.

Zhang

Cao

Ahn

. A GEE approach to determine sample size for pre- and post-intervention experiments with dropout. Comput Stat Data An 2014; 69: 114–121.

45.

Kidwell

Wahed

. Weighted log-rank statistic to compare shared-path adaptive treatment strategies. Biostatistics 2013; 14: 299–312.

46.

Robins JM. Causal inference from complex longitudinal data. In Berkane M (ed) Latent variable modeling and applications to causality, Lecture notes in statistics, volume 120. New York: Springer, pp. 69–117. ISBN 978-1-4612-1842-5, 1997. DOI:10.1007/978-1-4612-1842-5_ 4, https://link-springer-com.web.bisu.edu.cn/10.1007/978-1-4612-1842-5_4.

47.

Lavori

Dawson

. Introduction to dynamic treatment strategies and sequential multiple assignment randomization. Clin Trials 2014; 11: 393–399. DOI:10.1177/1740774514527651.

48.

Lachin

. Introduction to sample size determination and power analysis for clinical trials. Control Clin Trials 1981; 2: 93–113.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.49 MB