Individual-Level Modeling of Depressive Symptom Severity Using Smartphone and Wearable Data: A Time-Aware 1-Year Study with Feature-Group Contributions (Preprint)

BACKGROUND Smartphones and wearables can continuously capture behavioral and physiological data in everyday life. Such mobile-sensing data may help track depressive symptoms more closely than occasional retrospective questionnaires, but prior findings have been mixed. Inconsistent findings do not preclude the presence of predictive relationships in specific individuals or time periods. In addition, it remains unclear which broader sensor domains, rather than single features, contribute most to prediction at the individual level. OBJECTIVE The objective of the current study is to evaluate whether smartphone and wearable data improve prospective prediction of daily depressive symptom severity beyond a person-specific baseline and, where improvement is observed, to identify contributing sensor feature groups. METHODS Among 11 participants with sufficient data, 8 (73%) showed improved performance over baseline with linear models and 9 (82%) with nonlinear models. Among models showing improvement, fold-averaged mean absolute error ranged from 0.91 to 2.31 points on the adapted PHQ-2 scale for linear models and from 0.54 to 2.54 points for nonlinear models. Improvements over the person-specific baseline ranged from ΔMAE = 0.04 to 1.19 points for linear models and from ΔMAE = 0.11 to 1.09 points for nonlinear models. Predictive performance varied substantially between individuals, and no consistent overall advantage of nonlinear over linear models was observed. Feature-group importance profiles were heterogeneous, and no single sensor domain dominated across all participants. RESULTS Among 11 participants with sufficient data, 8 (73%) showed improved performance over baseline with linear models and 9 (82%) with nonlinear models. Predictive performance varied substantially between individuals, and no consistent overall advantage of nonlinear over linear models was observed. Feature-group importance profiles were heterogeneous, and no single sensor domain dominated across participants. CONCLUSIONS Multimodal smartphone and wearable data can provide individual-specific predictive signals for daily depressive symptom severity in a subset of patients when evaluated under prospective, time-aware conditions. Both predictive performance and contributing sensor domains vary markedly across individuals, and no single modeling approach is uniformly superior. These findings suggest that previously reported associations in mobile sensing research, often arising from heterogeneous study designs and feature representations, may not consistently translate into prospective prediction, and highlight the importance of evaluation frameworks that assess predictive signal at the temporal individual-participant level. CLINICALTRIAL German Clinical Trials Register (DRKS), DRKS00032618. Registered 12 September 2023.