A0754
Title: SMART-EXAM: Incorporating participants welfare into sequential multiple assignment randomized trials
Authors: Xinru Wang - Duke-NUS Medical School (Singapore) [presenting]
Nina Deliu - Sapienza University of Rome; University of Cambridge (Italy)
Yusuke Narita - Yale University (United States)
Bibhas Chakraborty - Duke-NUS Medical School, National University of Singapore (Singapore)
Abstract: Dynamic treatment regimes (DTRs) are sequences of decision rules that recommend treatments based on patients time-varying clinical conditions. The sequential multiple assignment randomized trial (SMART) is an experimental design that can provide high-quality evidence for constructing optimal DTRs. Despite its relative simplicity of implementation and desirable performance in comparing embedded DTRs, the SMART with balanced randomization is faced with inevitable ethical issues, including assigning many participants to the observed inferior treatment or the treatment they dislike, which might slow down the recruitment procedure and lead to higher attrition rates. In this context, a SMART is proposed under the Experiment-as-Market framework (SMART-EXAM), a novel SMART design that can potentially improve patient welfare by incorporating participant preferences and predicted treatment effects into the randomization procedure. The procedure of conducting a SMART-EXAM is described, and its theoretical and empirical statistical properties compared with other competing SMART designs are evaluated. The results indicate that the SMART-EXAM design can improve the welfare of participants enrolled in the trial while achieving a comparable ability to construct an optimal DTR. Finally, the practical potential of the SMART-EXAM design is illustrated using data from a SMART for children with attention deficit/hyperactivity disorder (ADHD).
