University of Wisconsin-Madison’s Center for Healthy Minds to Explore Machine Learning for Predicting Well-being

The University of Wisconsin-Madison’s Center for Healthy Minds is set to launch a two-year project that aims to leverage artificial intelligence to deliver personalized well-being content through a person’s mobile device when they need it most. The project, supported by more than $3 million in funding from the Defense Advanced Research Projects Agency (DARPA), will focus on developing a machine learning algorithm that can predict a person’s emotional state, particularly when the individual is feeling anxious, lonely, or unfulfilled. This algorithm will provide short well-being practices, or micro-supports, such as mindful breathing to help in the moment. The multi-phase project will begin with a research study to gather data on participants’ well-being levels at specific times in the day, using experience sampling and passive mobile data collection. The findings from these studies will inform the development of an algorithm and micro-support framework and content that will ultimately deliver in-the-moment, personalized well-being practices to users. The end goal of the project is to develop a platform that can deliver micro-supports based on an algorithmic trigger, potentially changing the way mental health services are accessed and delivered.