Mood disorders require consistent management of symptoms to prevent recurrences of mood episodes. Circadian rhythm (CR) disruption is a key symptom of mood disorders to be proactively managed to prevent mood episode recurrences. This study aims to predict impending mood episodes recurrences using digital phenotypes related to CR obtained from wearable devices and smartphones.

The study is a multicenter, nationwide, prospective, observational study with major depressive disorder, bipolar disorder I, and bipolar II disorder. A total of 495 patients were recruited from eight hospitals in South Korea. Patients were followed up for an average of 279.7 days (a total sample of 75 506 days) with wearable devices and smartphones and with clinical interviews conducted every 3 months. Algorithms predicting impending mood episodes were developed with machine learning. Algorithm-predicted mood episodes were then compared to those identified through face-to-face clinical interviews incorporating ecological momentary assessments of daily mood and energy.

Two hundred seventy mood episodes recurred in 135 subjects during the follow-up period. The prediction accuracies for impending major depressive episodes, manic episodes, and hypomanic episodes for the next 3 days were 90.1, 92.6, and 93.0%, with the area under the curve values of 0.937, 0.957, and 0.963, respectively.

We predicted the onset of mood episode recurrences exclusively using digital phenotypes. Specifically, phenotypes indicating CR misalignment contributed the most to the prediction of episodes recurrences. Our findings suggest that monitoring of CR using digital devices can be useful in preventing and treating mood disorders.

Given its diverse disease courses and symptom presentations, multiple phenotype dimensions with different biological underpinnings are expected with bipolar disorders (BPs). In this study, we aimed to identify lifetime BP psychopathology dimensions. We also explored the differing associations with bipolar I (BP-I) and bipolar II (BP-II) disorders.

We included a total of 307 subjects with BPs in the analysis. For the factor analysis, we chose six variables related to clinical courses, 29 indicators covering lifetime symptoms of mood episodes, and 6 specific comorbid conditions. To determine the relationships among the identified phenotypic dimensions and their effects on differentiating BP subtypes, we applied structural equation modeling.

We selected a six-factor solution through scree plot, Velicer's minimum average partial test, and face validity evaluations; the six factors were cyclicity, depression, atypical vegetative symptoms, elation, psychotic/irritable mania, and comorbidity. In the path analysis, five factors excluding atypical vegetative symptoms were associated with one another. Cyclicity, depression, and comorbidity had positive associations, and they correlated negatively with psychotic/irritable mania; elation showed positive correlations with cyclicity and psychotic/irritable mania. Depression, cyclicity, and comorbidity were stronger in BP-II than in BP-I, and they contributed significantly to the distinction between the two disorders.

We identified six phenotype dimensions; in addition to symptom features of manic and depressive episodes, various comorbidities and high cyclicity constructed separate dimensions. Except for atypical vegetative symptoms, all factors showed a complex interdependency and played roles in discriminating BP-II from BP-I.