Background: Depression is the top contributor to global disability. Early detection of depression and depressive symptoms enables timely intervention and reduces their physical and social consequences. Prevalence estimates of depression approach 30% among college students. Passive, device-based sensing further enables detection of depressive symptoms at a low burden to the individual.

Objective: We leveraged an ensemble machine learning method (light gradient boosting machine) to detect depressive symptoms entirely through passive sensing.

Methods: A diverse sample of undergraduate students (N=28; mean age 19.96, SD 1.23 y; 15/28, 54% women; 13/28, 46% Latine; 10/28, 36%Asian; 4/28, 14% non-Latine White; 11/28, 4% other) participated in an intensive longitudinal study. Participants wore 2 devices (an Oura ring for sleep and physiology data, and a Samsung smartwatch for physiology and movement data) and installed the AWARE software on their mobile devices, which collects passive sensing data such as screen time. Participants were derived from a randomized controlled trial of a positive psychology mobile health intervention. They completed a self-report measure of depressive symptoms administered weekly over a 19-to 22-week period.

Results: The light gradient boosting machine model achieved an F1-score of 0.744 and a Cohen kappa coefficient of 0.474, indicating moderate agreement between the predicted labels and the ground truth. The most predictive features of depressive symptoms were sleep quality and missed mobile interactions.

Conclusions:Findings suggest that data collected from passive sensing devices may provide real-time, low-cost insight into the detection of depressive symptoms in college students and may present an opportunity for future prevention and perhaps intervention.