Abstract
Burnout among medical students can emerge early and is strongly linked to emotional exhaustion, impaired academic performance, dropout risk, and mental health concerns such as anxiety and suicidal ideation. Traditional wellness interventions, while effective, often fail to engage busy students due to time demands. This pilot study evaluates Jivika, a mobile wellness platform that combines artificial and emotional intelligence to deliver personalized burnout prevention. Jivika uses biometric data (heart rate variability) and psychometric inputs (self-reported stress and mood) to identify early signs of chronic stress and predict burnout before it manifests. Based on these trends, the app recommends targeted, daily micro-habit interventions rooted in mindfulness and neuroscience. Twelve medical students from Mercer University School of Medicine in Macon, Georgia participated in an 8-week, single-group pre-post study. The intervention included daily 30-second mindfulness-based micro-habits delivered via app and weekly peer-circle sessions. Measures included the Maslach Burnout Inventory (MBI), Depression Anxiety Stress Scale (DASS-21), and a weekly self-reported stress scale. Among the six students who completed the MBI post-intervention, emotional exhaustion decreased with a large effect size (d = 0.99; p = .06). The five who completed the DASS-21 showed a moderate drop in anxiety (d = 0.57), though not statistically significant. Despite the small sample, the findings suggest that even ultra-brief, AI-personalized interventions can meaningfully reduce burnout symptoms. This supports further exploration of predictive, micro-habit-based digital tools that integrate biometric and psychometric intelligence to prevent burnout in high-risk populations.
Details
Presentation Type
Theme
Health Promotion and Education
KEYWORDS
Burnout, Medical students, Wellness, Chronic stress prediction, Stress, Anxiety
