Just-in-Time Adaptive Interventions
Susan A. Murphy & Danny Almirall
All day workshop- Monday, May 21, 2018 9:00 am-5:00 pm
Mobile devices along with wearable sensors facilitate our ability to deliver supportive treatments anytime and anywhere. Indeed mobile interventions are being developed and employed across a variety of health fields, including to support HIV medication adherence, encourage physical activity and healthier eating as well as to support recovery in addictions. Just-in-time adaptive interventions are mobile health interventions that include notifications or other types of pushes to the user. This workshop will discuss the components of just-in-time adaptive interventions with an eye towards how we might use data to inform the development of these components. We will discuss the design of micro-randomized trial for providing useful data. Lastly a critical question in the optimization of mobile health interventions is: “When and in which contexts, is it most useful to deliver treatments to the user?” This question concerns time-varying dynamic moderation by the context (location, stress, time of day, mood, ambient noise, etc.) of the effectiveness of the treatments on user behavior. We will review and discuss methods for using micro-randomized trial data to assess moderation. Throughout we will illustrate the concepts using trials in a variety of domains including trials aimed at improving engagement in mobile health interventions, in smoking cessation and in physical activity. Register for the preconference and/or the 2018 Modern Modeling Methods Conference here.
This workshop will be held in Laurel Hall, Room 102 on Monday, 5/21/18 from 9:00am-5:00pm.
Bio for Susan A. Murphy
Dr. Murphy’s primary interest concerns the development of experimental designs and statistical machine learning methods for informing sequential decision making in mobile health. These methods are used to construct real time treatment policies also known as Just-in-Time Adaptive Interventions (JITAIs). JITAIs are composed of a sequence of decision rules that specify in which user context it is most useful to provide an treatment as well as how to deliver the treatment to the user. The context is observed via sensor and self-report data and involves, for example, current and past user location, weather, social setting, user stress and mood, user behaviors and user engagement.
Bio for Daniel Almirall
Dr. Almirall develops methods used to form adaptive interventions, also known as dynamic treatment regimens. Adaptive interventions can be used to inform individualized treatment guidelines for the on-going management of chronic illnesses or disorders such as anxiety, depression, autism, diabetes, obesity, or HIV/AIDS. Dr. Almirall works primarily on methods related to the design, execution, and analysis of sequential multiple assignment randomized trials (SMARTs). SMARTs give rise to high-quality data that can be used to build and optimize ATSs. He is also interested in the development of methods for causal inference using longitudinal intervention data in which treatments, covariates, and outcomes are all time-varying. A specific interest in this area has been the development of methods for examining time-varying effect moderation.