AI Overview
Young adults face unprecedented mental health challenges, yet barriers like stigma and accessibility prevent many from seeking help. Bite-sized interventions could prevent distress before it escalates, but lack personalized, interactive, and scalable delivery methods.
- Question: Does a generative AI mobile app improve mental health and well-being among undergraduate students?
- Setting and data: Three U.S. institutions, fall 2024, 486 undergraduate students followed over 6 weeks.
- Method: Randomized controlled trial
- AI tools: Flourish
- Students instructed to use the app reported significantly greater resilience and social well-being, including higher belonging, closer community ties, and lower loneliness.
- Using the app buffered students against typical declines in positive affect, mindfulness, and flourishing.
- No significant differences over time were observed between the app and control groups for depression, anxiety, or stress.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
Background
Young adults today face unprecedented mental health challenges, yet many hesitate to seek support owing to barriers such as accessibility, stigma, and time constraints. Bite-sized well-being interventions offer a promising solution to preventing mental distress before it escalates to clinical levels, but have not yet been delivered through personalized, interactive, and scalable technology.
Methods
We conducted the first multi-institutional, longitudinal, preregistered randomized controlled trial of a generative artificial intelligence (AI)–powered mobile app (Flourish) designed to address this gap. Over 6 weeks in the fall of 2024, 486 undergraduate students from three U.S. institutions were randomly assigned to receive app access or to a care-as-usual control condition.
Results
Participants instructed to use the Flourish app twice per week reported significantly greater resilience and social well-being (i.e., increased belonging, closeness to community, and reduced loneliness), and they were buffered against declines in positive affect, mindfulness, and flourishing. No significant condition-by-time effects were observed for depression, anxiety, or stress in this study with a general population.
Conclusions
These findings suggest that, with purposeful and ethical design, generative AI can deliver proactive population-level well-being interventions that produce measurable benefits.
