The technology could help people with other conditions as well.
The app, which monitors the subtle qualities of the user’s voice during daily phone conversations, shows promise for detecting early signs of mood changes. It requires more testing before it becomes publicly available, but early results show strong potential to monitor patients’ moods while also protecting privacy.
Currently, study participants are using the app on study-provided smartphones. As more patients volunteer, the team will continue to test and improve the technology.
Researchers call the app PRIORI, because they hope it will offer a biological marker that will prioritize bipolar care to those who need it most urgently, particularly in areas with few mental health services.
“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,” said Zahi Karam, Ph.D, a postdoctoral fellow and specialist in machine learning and speech analysis.
“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.”
The app automatically monitors the patients’ voice patterns during all calls, including those between the patient and a health care provider. The computer program analyzes many characteristics of the sounds, and silences, during each call.
Only the patient’s side of everyday phone calls is recorded, and they are encrypted and kept off-limits to the researchers. They only see the results of the analysis, which are stored in secure servers that adhere to patient privacy laws.
“This is tremendously exciting not only as a technical achievement, but also as an illustration of what the marriage of mental health research, engineering and innovative research funding can make possible,” said psychiatrist and bipolar specialist Melvin McInnis, M.D.
“The ability to predict mood changes with sufficient advance time to intervene would be an enormously valuable biomarker for bipolar disorder.”
Since other mental health disorders could cause changes in a person’s voice as well, the technology could prove useful in everything from schizophrenia and posttraumatic stress disorder to Parkinson’s disease, added the researchers.
Source: University of Michigan