• Corpus ID: 218595891

The Micro-Randomized Trial for Developing Digital Interventions: Experimental Design Considerations

  title={The Micro-Randomized Trial for Developing Digital Interventions: Experimental Design Considerations},
  author={Ashley Walton and Linda M. Collins and Predrag V. Klasnja and Inbal Nahum-Shani and Mashfiqui Rabbi and Maureen A. Walton and Susan A. Murphy},
Just-in-time adaptive interventions (JITAIs) are time-varying adaptive interventions that use frequent opportunities for the intervention to be adapted such as weekly, daily, or even many times a day. This high intensity of adaptation is facilitated by the ability of digital technology to continuously collect information about an individual's current context and deliver treatments adapted to this information. The micro-randomized trial (MRT) has emerged for use in informing the construction of… 
Notifications to Improve Engagement With an Alcohol Reduction App: Protocol for a Micro-Randomized Trial
A micro-randomized trial to assess whether sending a notification at 8 pm increases behavioral engagement (opening the app) in the subsequent hour, and to more generally understand the role notifications have on the overall duration, depth, and frequency of engagement with Drink Less over the first 30 days after download.
StudyU: a platform for designing and conducting innovative digital N-of-1 trials
The StudyU platform allows clinicians and researchers worldwide to easily design and conduct digital Nof-1 trials in a safe manner and can change the landscape of personalized treatments both for patients and healthy individuals.


Experimental design and primary data analysis methods for comparing adaptive interventions.
The sequential multiple assignment randomized trial (SMART), an experimental design useful for addressing research questions that inform the construction of high-quality adaptive interventions, is proposed.
Microrandomized trials: An experimental design for developing just-in-time adaptive interventions.
  • P. Klasnja, E. Hekler, +4 authors S. Murphy
  • Medicine
    Health psychology : official journal of the Division of Health Psychology, American Psychological Association
  • 2015
Microrandomized trials can help researchers understand whether their interventions are having intended effects, when and for whom they are effective, and what factors moderate the interventions' effects, enabling creation of more effective JITAIs.
Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support
It is critical that researchers develop sophisticated and nuanced health behavior theories capable of guiding the construction of JITAIs and particular attention has to be given to better understanding the implications of providing timely and ecologically sound support for intervention adherence and retention.
Efficacy of Contextually Tailored Suggestions for Physical Activity: A Micro-randomized Optimization Trial of HeartSteps.
Contextually tailored walking suggestions are a promising way of initiating bouts of walking throughout the day in adults in an mHealth intervention.
To Prompt or Not to Prompt? A Microrandomized Trial of Time-Varying Push Notifications to Increase Proximal Engagement With a Mobile Health App
Sending a push notification containing a tailored health message was associated with greater engagement in an mHealth app, and users are more likely to engage with the app within 24 hours when push notifications are sent at mid-day on weekends.
Does monitoring goal progress promote goal attainment? A meta-analysis of the experimental evidence.
The findings suggest that monitoring goal progress is an effective self-regulation strategy, and that interventions that increase the frequency of progress monitoring are likely to promote behavior change.
Intensively Adaptive Interventions Using Control Systems Engineering: Two Illustrative Examples
This chapter describes how control systems engineering principles, particularly system identification and model predictive control, can be applied to serve as dynamic modeling methods and optimal decision frameworks, respectively, for two intensively adaptive interventions: Just Walk and Healthy Mom Zone.
Analysis of longitudinal data: the integration of theoretical model, temporal design, and statistical model.
  • L. Collins
  • Psychology, Medicine
    Annual review of psychology
  • 2006
This article argues that ideal longitudinal research is characterized by the seamless integration of three elements: (a) a well-articulated theoretical model of change observed using (b) a temporal
Personalizing Mobile Fitness Apps using Reinforcement Learning
A novel fitness app called CalFit is described, which implements important behavior-change features like dynamic goal setting and self-monitoring and uses a reinforcement learning algorithm to generate personalized daily step goals that are challenging but attainable.
Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity
A Reinforcement Learning (RL) algorithm that continuously learns and improves the treatment policy embedded in the JITAI as the data is being collected from the user is developed.