Speaker: Kelley M. Kidwell, PhD (University of Michigan)
Description: A sequential, multiple assignment, randomized trial (SMART) is a type of multi-stage randomized trial design such that participants are randomized at least twice in sequence. Subsequent randomization and/or treatment assignment is often based on response or engagement to previous treatment. SMARTs have been applied in a variety of health research areas including mental health, weight loss, and chronic pain, education, and implementation science and funded across many agencies. SMART designs provide robust evidence for adaptive interventions that guide tailored treatment at critical decision points along the course of care. This seminar will provide an introduction to how SMART designs can be used to develop high-quality adaptive interventions. We will define SMART design and illustrate SMARTs through various case studies in the mental health setting. SMART design principles will be discussed along with typical primary, secondary and exploratory aims. A high-level overview of analytic methods of a SMART design, along with power and sample size calculations, will be presented.
Dr. Kidwell is interested in the design and analysis of clinical trials. Her methodological work centers on better matching the way in which we practice medicine and public health (critical decisions over time tailored to individuals) to the way in which we experimentally study it. Dr. Kidwell's methods work has primarily focused on the design and analysis of sequential, multiple assignment, randomized trials (SMARTs), in standard or large size trials for treating common diseases and disorders, and in small samples or for treating rare diseases. Collaboratively, Dr. Kidwell aims to improve public health science by bridging the gap between researchers, the biostatistical methods needed and applied to studies, and the communication of results. Dr. Kidwell is involved in the design and analysis of many trials with investigators across the university in settings such as mental health, chronic pain, substance use, and oncology. Her methods and collaborative work influences clinical trial statistical theory and practice and hopefully is improving people's lives through new designs and efficient treatment estimates.