Early detection of depressive symptom changes is vital for timely interventions. Mobile andwearable technologies enable continuous, unobtrusive monitoring of behavioral, psychological,and physiological data, offering new possibilities for digital phenotyping and just-in-time (JIT)prediction of depression. This scoping review synthesized findings from 52 studies to identifycommonly used features, evaluate their predictive value, and assess methodologicalapproaches. Frequently assessed features included location data, sleep metrics, physicalactivity, communication patterns, heart rate variability, and mood self-reports. Features such astime spent at home, sleep variability, and reduced mobility were strongly associated withdepressive symptoms. Combining physiological, behavioral, and self-report data enhancedpredictive performance. Personalized models and anomaly detection approaches outperformedgeneralized ones in predicting individual symptom changes. Overall, mobile and wearable datashow strong potential for JIT depression prediction. Future research should emphasize novelfeatures, diverse populations, and personalized models to improve accuracy and real-worldapplicability.
Zwalmen et al. (Tue,) studied this question.