New research led by M. Faurholt-Jepsen at Copenhagen suggests that smartphone based vocal analysis can measure changes in speech which often indicate depression and mania in bipolar disorder.
The researchers collected data from 28 bipolar disorder outpatients of the Copenhagen Clinic for Affective Disorders. They were observed in naturalistic settings on a daily basis during a period of 12 weeks. All patients were instructed to use smartphones with MONARCA app installed as the self-monitoring tool. They used it for their primary phone and for their usual communicative purposes.
The app made an alarm sound once a day to prompt the patients to provide self-monitored data, which included mood, sleep length, medication taken, medication taken with changes, activity level, alcohol consumption, mixed mood, irritability, cognitive problems, stress, and indication of the presence of individualized early warning signs. Voice data was captured by recording participants’ daily conversations.
Combining voice features and electronic self-monitored data revealed that the accuracy of bipolar disorder identification increased slightly. These results show that real-time collection and analysis of voice features from everyday phone calls may represent state markers in bipolar disorder and seem promising as a tool for continuous monitoring of illness activity and effect of treatment in patients with bipolar disorder.
More articles on My Health Career: