Bipolar disorder is a mental illness that causes extreme emotional highs and lows. It affects millions of people worldwide and can have serious consequences, including suicide.
The app showed promise in early tests with a small group of patients, according to a University of Michigan research team, and if further testing confirms its usefulness, the app could be used to detect subtle voice changes that give an early warning about mood changes to people with bipolar disorder and their health care providers.
The app automatically analyses users' voices during smartphone calls and does so without infringing on anyone's privacy, according to the team.
Anticipating mood swings
"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," study co-leader Zahi Karam, a postdoctoral fellow and specialist in machine learning and speech analysis, said in a university news release.
"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," Karam added.
"The ability to predict mood changes with sufficient advance time to intervene would be an enormously valuable biomarker for bipolar disorder," study co-leader Dr Melvin McInnis, a bipolar specialist, said in the news release.
The study, funded by the National Institute of Mental Health and facilitated by the Prechter Bipolar Research Fund at the U-M Depression Centre, was scheduled to be presented at last week's International Conference on Acoustics, Speech and Signal Processing in Florence, Italy.
Other health conditions also affect patients' voices, so it may be possible to develop similar smartphone apps for disorders that range from schizophrenia and post-traumatic stress disorder to Parkinson's disease, the researchers noted.