Variability in self-reported depression symptomology and associated behavioral markers in digital phenotyping.

Digital phenotyping studies using smartphone-sensed data have identified several behavioral markers associated with depression. However, the generalizability of these markers is constrained by multiple factors, including variability in depressive symptoms and associated behaviors, both between and within individuals over time. This study explores variability in depression symptoms and associated behaviors using smartphone-sensed data collected from participants diagnosed with depression. It examines behavioral features derived from smartphone sensing as potential markers of depression. We analyzed smartphone-sensed behavioral data from 62 patients with major depressive episodes across three subgroups: major depressive disorder (MDD, n = 41), borderline personality disorder (BPD, n = 12), and bipolar disorder (BD, n = 9). Depression symptoms were assessed with the 9-item Patient Health Questionnaire (PHQ-9). Symptoms differed between subgroups and across severity levels. Association analysis suggested variability in correlations between depression severity and behavioral features, both between participants and over time. Multilevel modeling identified two demographic predictors, employment status (β = − 4.79, 95% CI [− 7.65, − 1.80], p = 0.004) and age (β = − 0.12, 95% CI [− 0.25, 0.00], p = 0.050), along with one behavioral predictor, lower nighttime movement (β = − 0.79, 95% CI [− 1.29, − 0.29], p = 0.024), that were associated with depression severity.