Comparing cluster-level dynamic treatment regimens using sequential, multiple assignment, randomized trials: Regression estimation and sample size considerations

Cluster-level dynamic treatment regimens can be used to guide sequential treatment decision-making at the cluster level in order to improve outcomes at the individual or patient-level. In a cluster-level dynamic treatment regimen, the treatment is potentially adapted and re-adapted over time based on changes in the cluster that could be impacted by prior intervention, including aggregate measures of the individuals or patients that compose it. Cluster-randomized sequential multiple assignment randomized trials can be used to answer multiple open questions preventing scientists from developing high-quality cluster-level dynamic treatment regimens. In a cluster-randomized sequential multiple assignment randomized trial, sequential randomizations occur at the cluster level and outcomes are observed at the individual level. This manuscript makes two contributions to the design and analysis of cluster-randomized sequential multiple assignment randomized trials. First, a weighted least squares regression approach is proposed for comparing the mean of a patient-level outcome between the cluster-level dynamic treatment regimens embedded in a sequential multiple assignment randomized trial. The regression approach facilitates the use of baseline covariates which is often critical in the analysis of cluster-level trials. Second, sample size calculators are derived for two common cluster-randomized sequential multiple assignment randomized trial designs for use when the primary aim is a between-dynamic treatment regimen comparison of the mean of a continuous patient-level outcome. The methods are motivated by the Adaptive Implementation of Effective Programs Trial which is, to our knowledge, the first-ever cluster-randomized sequential multiple assignment randomized trial in psychiatry.

[1]  A note on using the estimated versus the known propensity score to estimate the average treatment effect , 2009 .

[2]  Ying Kuen Cheung,et al.  Chapter 5: Sample size calculations for clustered SMART designs , 2015 .

[3]  Andrew Forbes,et al.  Variance reduction in randomised trials by inverse probability weighting using the propensity score , 2013, Statistics in medicine.

[4]  D. Almirall,et al.  Longitudinal Effects of Adaptive Interventions With a Speech-Generating Device in Minimally Verbal Children With ASD , 2016, Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53.

[5]  J. Robins,et al.  Marginal Structural Models and Causal Inference in Epidemiology , 2000, Epidemiology.

[6]  J. Robins,et al.  The International Journal of Biostatistics CAUSAL INFERENCE Dynamic Regime Marginal Structural Mean Models for Estimation of Optimal Dynamic Treatment Regimes , Part I : Main Content , 2011 .

[7]  Donald B. Rubin,et al.  Bayesian Inference for Causal Effects: The Role of Randomization , 1978 .

[8]  James M. Robins,et al.  Causal Inference from Complex Longitudinal Data , 1997 .

[9]  Kristin A. Linn,et al.  Interactive Q-learning for Probabilities and Quantiles , 2014, 1407.3414.

[10]  Donglin Zeng,et al.  New Statistical Learning Methods for Estimating Optimal Dynamic Treatment Regimes , 2015, Journal of the American Statistical Association.

[11]  Jacob Cohen.  Statistical Power Analysis for the Behavioral Sciences , 1969, The SAGE Encyclopedia of Research Design.

[12]  D. Oslin,et al.  Effect of patient choice in an adaptive sequential randomization trial of treatment for alcohol and cocaine dependence. , 2015, Journal of consulting and clinical psychology.

[13]  Inbal Nahum-Shani,et al.  Treatment Sequencing for Childhood ADHD: A Multiple-Randomization Study of Adaptive Medication and Behavioral Interventions , 2016, Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53.

[14]  Alena I. Oetting,et al.  Statistical Methodology for a SMART Design in the Development of Adaptive Treatment Strategies , 2011 .

[15]  P. Lachenbruch.  Statistical Power Analysis for the Behavioral Sciences (2nd ed.) , 1989 .

[16]  Larry V. Hedges,et al.  Statistical Power Analysis in Education Research , 2010 .

[17]  S M Kerry,et al.  Unequal cluster sizes for trials in English and Welsh general practice: implications for sample size calculations. , 2001, Statistics in medicine.

[18]  Inbal Nahum-Shani,et al.  Comparing dynamic treatment regimes using repeated‐measures outcomes: modeling considerations in SMART studies , 2016, Statistics in medicine.

[19]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[20]  B. Chakraborty,et al.  Statistical Methods for Dynamic Treatment Regimes: Reinforcement Learning, Causal Inference, and Personalized Medicine , 2013 .

[21]  Xi Lu,et al.  Comparing treatment policies with assistance from the structural nested mean model , 2016, Biometrics.

[22]  Donald Hedeker,et al.  Longitudinal Data Analysis , 2006 .

[23]  T. Templin,et al.  Sequential Multiple Assignment Randomized Trial (SMART) to Construct Weight Loss Interventions for African American Adolescents , 2016, Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53.

[24]  Allan Donner,et al.  Design and Analysis of Cluster Randomization Trials in Health Research , 2001 .

[25]  Susan A Murphy,et al.  Sample size formulae for two-stage randomized trials with survival outcomes. , 2011, Biometrika.

[26]  Daniel Almirall,et al.  Protocol: Adaptive Implementation of Effective Programs Trial (ADEPT): cluster randomized SMART trial comparing a standard versus enhanced implementation strategy to improve outcomes of a mood disorders program , 2014, Implementation Science.

[27]  Eric B. Laber,et al.  Interactive Q-Learning for Quantiles , 2017, Journal of the American Statistical Association.

[28]  M. J. van der Laan,et al.  Statistical methods for analyzing sequentially randomized trials. , 2007, Journal of the National Cancer Institute.

[29]  J M Robins,et al.  Marginal Mean Models for Dynamic Regimes , 2001, Journal of the American Statistical Association.

[30]  G. Imbens,et al.  Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score , 2000 .

[31]  Anthony S. Bryk,et al.  Hierarchical Linear Models: Applications and Data Analysis Methods , 1992 .

[32]  J. Robins,et al.  Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. , 2000, Epidemiology.

[33]  S. Murphy,et al.  PERFORMANCE GUARANTEES FOR INDIVIDUALIZED TREATMENT RULES. , 2011, Annals of statistics.

[34]  Philip W. Lavori,et al.  A design for testing clinical strategies: biased adaptive within‐subject randomization , 2000 .

[35]  D. Almirall,et al.  The BestFIT trial: A SMART approach to developing individualized weight loss treatments. , 2016, Contemporary clinical trials.

[36]  J. Neyman,et al.  Statistical Problems in Agricultural Experimentation , 1935 .

[37]  D. Zucker.  Design and Analysis of Cluster Randomization Trials , 2003 .

[38]  D. Almirall,et al.  Communication interventions for minimally verbal children with autism: a sequential multiple assignment randomized trial. , 2014, Journal of the American Academy of Child and Adolescent Psychiatry.

[39]  S. Murphy,et al.  An experimental design for the development of adaptive treatment strategies , 2005, Statistics in medicine.

[40]  Ree Dawson,et al.  Introduction to dynamic treatment strategies and sequential multiple assignment randomization , 2014, Clinical trials.

[41]  Susan A. Murphy,et al.  Introduction to SMART designs for the development of adaptive interventions: with application to weight loss research , 2014, Translational behavioral medicine.

[42]  G. August,et al.  Being “SMART” About Adolescent Conduct Problems Prevention: Executing a SMART Pilot Study in a Juvenile Diversion Agency , 2016, Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53.

[43]  S L Zeger,et al.  Regression analysis for correlated data. , 1993, Annual review of public health.

[44]  David E. 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 , 2013, Implementation Science.

[45]  David M. Murray,et al.  Design and Analysis of Group- Randomized Trials , 1998 .

[46]  J. Robins,et al.  Analysis of semiparametric regression models for repeated outcomes in the presence of missing data , 1995 .

[47]  James M. Robins,et al.  Association, Causation, And Marginal Structural Models , 1999, Synthese.

[48]  J. Robins,et al.  Estimating the causal effect of zidovudine on CD4 count with a marginal structural model for repeated measures , 2002, Statistics in medicine.

[49]  John B. Carlin,et al.  The Intra‐Cluster Correlation Coefficient in Cluster Randomized Trials: A Review of Definitions , 2009 .

[50]  S. Murphy,et al.  A "SMART" design for building individualized treatment sequences. , 2012, Annual review of clinical psychology.

[51]  Daniel Almirall,et al.  A Pilot SMART for Developing an Adaptive Treatment Strategy for Adolescent Depression , 2016, Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53.

[52]  G. Imbens,et al.  Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score , 2002 .

[53]  Eric B. Laber,et al.  Tree-based methods for individualized treatment regimes. , 2015, Biometrika.

[54]  Michael R Kosorok,et al.  Residual Weighted Learning for Estimating Individualized Treatment Rules , 2015, Journal of the American Statistical Association.

[55]  Nema Dean,et al.  Q-Learning: Flexible Learning About Useful Utilities , 2013, Statistics in Biosciences.

[56]  D. Almirall,et al.  Personalized Treatment of Mothers With ADHD and Their Young At-Risk Children: A SMART Pilot , 2016, Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53.

[57]  S. Murphy,et al.  Experimental design and primary data analysis methods for comparing adaptive interventions. , 2012, Psychological methods.

[58]  P. Diggle,et al.  Latent Variable Modeling and Applications to Causality , 2017 .

[59]  Marie Davidian,et al.  Using decision lists to construct interpretable and parsimonious treatment regimes , 2015, Biometrics.

[60]  M. Kosorok,et al.  Adaptive Treatment Strategies in Practice: Planning Trials and Analyzing Data for Personalized Medicine , 2015 .

[61]  David E. Goodrich,et al.  Life Goals Collaborative Care for patients with bipolar disorder and cardiovascular disease risk. , 2012, Psychiatric services.