A clever new smartphone app could help sufferers of bipolar disorder to know when they might expect a swing in their mood. Developed at the University of Michigan, the PRIORI app carefully analyzes the user's voice, and uses historical data built up through calibration and ongoing use to identify the changes that could potentially flag a forthcoming change in mood.
The app, which is still in its experimental stage, runs in the background of the user's handset and gets its data by recording only the user's side of phone conversations, which are then uploaded to a secure server that only the app's creators have access to, for processing.
When this processing determines specific changes in the speech patterns of the user, it will flag the possibility for a mood change, letting the person know that they should prepare themselves.
So far the app has been tested with a total of six bipolar disorder suffers, and the results have been promising. Speaking about the app and its early findings, co-leader of the project Zahi Karam says:
These pilot study results give us preliminary proof of the concept that we can detect mood states in regular phone calls by analysing broad features and properties of speech, without violating the privacy of those conversations.As we collect more data the model will become better, and our ultimate goal is to be able to anticipate swings, so that it may be possible to intervene early.
Ultimately, it is hoped that the technology used by the app could be utilized to help sufferers of other conditions, like depression, post traumatic stress and schizophrenia. If you're interested in learning more, or participating in the study, you can find everything you need on the university's clinical studies website.