Experimental designs with repeated randomizations for optimizing adaptive interventions: guidelines and practical considerations.

BACKGROUND

In adaptive interventions, dynamic information about individuals is used to determine whether and how to intervene. Depending on the nature of the intervention (eg, human-delivered vs digitally delivered), adaptations may need to occur slowly or rapidly (eg, after a month vs daily). The optimization of adaptive interventions has been powered by 2 experimental designs, both employing sequential randomizations but on different timescales: the sequential multiple assignment randomized trial (SMART) on a slow timescale for standard adaptive interventions and the microrandomized trial (MRT) on a fast timescale for just-in-time adaptive interventions.

PURPOSE: This paper intends to help investigators who have research questions about the delivery and adaptation of intervention options at more than 1 time point, select and plan a trial design with the right form of sequential randomizations, on the appropriate timescale.

METHODS

This is a conceptual paper discussing considerations related to designing trials with sequential randomizations.

RESULTS

We clarify the differences and similarities between the SMART and the MRT, outline the types of questions that can be answered by the 2 experimental designs, and provide guidelines for selecting and planning the appropriate form of trial design based on the questions that need answers.

CONCLUSIONS

When designing a trial with sequential randomizations, it is essential to consider the need for sequential randomizations, the appropriate timescale for randomizations, whether to impose restrictions on randomizations, whether to randomize upfront or sequentially, the timing for measuring the primary outcome, and sample size planning.