The pJITAI Toolbox: A No-Code Platform for Creating Personalized Adaptive mHealth Interventions using Reinforcement Learning

The pJITAI Toolbox: A No-Code Platform for Creating Personalized Adaptive mHealth Interventions using Reinforcement Learning

We propose to build and release the personalizing JITAI (pJITAI) Toolbox, a no-code web-based system to allow mHealth researchers to create, configure, and deploy RL algorithms for mHealth interventions. The pJITAI Toolbox features a web-based graphical user interface that guides users (health scientists) through a series of steps to design and configure the personalizing component of their mHealth intervention. In each step, the user makes a small number of decisions regarding a subset of factors that are required to specify for configuring the RL for their application. Once the configuration is complete, the Toolbox will generate a hosted, customized web service to run the specified RL algorithm, and documentation for how to integrate the RL into a standard (non-personalized) JITAI.

Fast Fact

Principal Investigator

Mark Newman, PhD
Professor of Information, School of Information
Professor of Electrical Engineering and Computer Science, College of Engineering
University of Michigan

Key Collaborators

Funding Source

Focus Area