App For Bipolar Disorder Could Predict Mood Swings By Listening In On Phone Calls

A new smartphone app could detect mood swings in individuals with bipolar disorders by listening to their voice.

Bipolar disorder is a mental disorder that causes mood swings, it can lead to serious consequences such as suicide, HealthDay reported.

In a test of a small group of patients the app proved to have the ability to detect changes in the voices of those suffering from the condition; those changes could predict future mood changes.

The app would automatically monitor the user's voice while they were having a phone conversation without recording the call.

These pilot study results give us preliminary proof of the concept that we can detect mood states in regular phone calls by analyzing broad features and properties of speech, without violating the privacy of those conversations," co-leader Zahi Karam, a postdoctoral fellow and specialist in machine learning and speech analysis, said in a university news release, HealthDay reported.

"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 said.

The researchers hope the app could help patients monitor their illness, and prevent suicide.

"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, HealthDay reported.

There are other illnesses that also affect the individual's voice; the researchers hope this app can be tweaked to monitor conditions such as post-traumatic stress disorder (PTSD), Parkinson's, and schizophrenia.

Other signs and symptoms of bipolar disorder can include agitation, risky behavior, being easily distracted, fatigue, guilt, sleep problems, high or low appetite, concentration problems, excessive drug and alcohol use, and chronic pain without a medical cause, MayoClinic reported.

Real Time Analytics