Recently the MONARCA system, an electronic monitoring system for smartphones for patients with bipolar disorder, was extended to collect and extract voice features from phone calls made during everyday life.
The research shows, that affective (manic vs. depressive) states can be identified (‘classified’) by sampling and analyzing voice features collected from smartphones. Data were collected from 28 outpatients during a period of 12 weeks.
The accuracy of classification of affective states based on voice features was in the range of 61–74%. Combining voice features with automatically generated objective smartphone data on behavioral activities and electronic self-monitored data on illness activity increased the accuracy slightly.
This is the first example where everyday speech in smartphones has been used for this analysis.These results show that real-time collection and analysis of voice features from everyday phone calls may be used to automatically detect depressive and manic state in bipolar disorder and seem promising as a tool for continuous monitoring of illness activity and effect of treatment in patients with bipolar disorder.
These results were subsequently discussed in the Technology Magazine WIRED.
Citation: Translational Psychiatry (2016) 6, e856; doi:10.1038/tp.2016.123 Published online 19 July 2016