APS
2026 APS Annual Convention
From Moments to Mechanisms: Predicting Mental Health Problems In Daily Life Using Computational and Machine Learning Models
This symposium showcases cutting-edge applications of machine learning and computational modeling to ecological momentary assessment (EMA) data across internalizing and externalizing psychopathology. Four talks demonstrate how drift diffusion modeling, machine learning, and multilevel growth curve models can predict clinical outcomes, identify intervention targets, and reveal mechanisms in naturalistic contexts.
Chairs & Discussants
- Jonas DoraChair
University of Washington
Presentations
- Predicting Daily Lapse Risk Using Personal Sensing and Machine Learning In a National Sample of Individuals with Opioid Use DisorderKendra Wyant
- Situation-Specific Effects of Stress on Alcohol Decision-MakingJonas Dora
- Modeling High-Resolution Stress Reactivity and Recovery Dynamics In Adolescents to Predict One-Year Changes In Internalizing and Externalizing SymptomsPaula Philippi
- Integrating EMA and Wearable Data to Predict Depression Severity In n~1200 Young Adults from the Warn-D StudyEiko Fried
