Exploring social activity in bipolar disorder using automated smartphone tracking

Social Activity (SA) is a potential early warning sign of relapse in Bipolar Disorder (BD). Smartphones enable continuous, automatic monitoring of objective, real-time data. The intention of the current study was to explore the relationship between objective measures of SA and mood in people with BD. Levels of SA among 12 individuals with BD I (n=5) and II (n=7) were monitored using smartphone sensors (calls/SMS, location, audio) over 6-months. Participants were assessed by a clinician at baseline, 1-week, 3- and 6-months, and completed an online weekly mood survey. Results were analysed using linear mixed models with random intercept and likelihood ratio tests. Self-reported depressed mood was positively correlated with the number of sent and received SMS, while elevated mood was positively correlated with the number of people contacted and with mobility. The current study was limited by a small sample size and missing data due to technical challenges. Individual variation in both SA patterns and smartphone use, potentially influenced results. Personalised approaches, combining sensor modalities, and measuring multiple features for each sensor, may assist with effective tracking of objective SA. In clinical practice, SA measures and other early warning signs should be tailored to the individual to maximise the effectiveness of self-monitoring.