Listening to bipolar disorder: Smartphone app detects mood swings via voice analysis

Subtle changes could act as early warning of need for care, U-M research suggests

2014-05-08

(Press-News.org) ANN ARBOR, Mich. — A smartphone app that monitors subtle qualities of a person's voice during everyday phone conversations shows promise for detecting early signs of mood changes in people with bipolar disorder, a University of Michigan team reports.

While the app still needs much testing before widespread use, early results from a small group of patients show its potential to monitor moods while protecting privacy.

The researchers hope the app will eventually give people with bipolar disorder and their health care teams an early warning of the changing moods that give the condition its name. The technology could also help people with other conditions.

More patients, all taking part in the study funded by the National Institute of Mental Health and facilitated by the Prechter Bipolar Research Fund at the U-M Depression Center, have already started to use the app on study-provided smartphones. As more patients volunteer, the team will continue to test and improve the technology.

The U-M team, led by computer scientists Zahi Karam, Ph.D. and Emily Mower Provost, Ph.D., and psychiatrist Melvin McInnis, M.D., presented its first findings today at the International Conference on Acoustics, Speech and Signal Processing in Italy, and published details simultaneously in the conference proceedings.

They call the project PRIORI, because they hope it will yield a biological marker to prioritize bipolar disorder care to those who need it most urgently to stabilize their moods – especially in regions of the world with scarce mental health services. Bipolar disorder affects tens of millions of people worldwide, and can have devastating effects including suicide.

But first, based on these encouraging findings, the technology and algorithms will be developed via research involving 60 American patients who receive treatment from U-M teams at the nation's first center devoted to depression and related disorders.

"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," says Karam, 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."

Adds McInnis, a bipolar specialist, "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."

He adds, "The ability to predict mood changes with sufficient advance time to intervene would be an enormously valuable biomarker for bipolar disorder."

He notes that the initial seed funding for the voice technology research came from the Michigan Institute for Clinical and Health Research. The ready source of patient-volunteers came from a Prechter Fund-supported registry, and the new early results were made possible by NIMH funding.

The research team hails from the Department of Psychiatry at the U-M Medical School and the Division of Computer Science and Engineering in the Department of Electrical and Computer Engineering at the U-M College of Engineering. It includes Satinder Singh, Ph.D. an artificial intelligence and machine learning expert.

How it works

The app runs in the background on an ordinary smartphone, and automatically monitors the patients' voice patterns during any calls made as well as during weekly conversations with a member of the patient's care team. The computer program analyzes many characteristics of the sounds – and silences – of each conversation.

Only the patient's side of everyday phone calls is recorded – and the recordings themselves are encrypted and kept off-limits to the research team. They can see only the results of computer analysis of the recordings, which are stored in secure servers that comply with patient privacy laws.

Standardized weekly mood assessments with a trained clinician provide a benchmark for the patient's mood, and are used to correlate the acoustic features of speech with their mood state.

Because other mental health conditions also cause changes in a person's voice, the same technology framework developed for bipolar disorder could prove useful in everything from schizophrenia and post-traumatic stress disorder to Parkinson's disease, the researchers say.

Results so far

The first six patients all have a rapid-cycling form of Type 1 bipolar disorder and a history of being prone to frequent depressive and manic episodes. The researchers showed that their analysis of voice characteristics from everyday conversations could detect elevated and depressed moods.

The detection of mood states will improve over time as the software gets trained based on more conversations and data from more patients.

The researchers study patients as they experience all aspects of bipolar disorder mood changes, from mild depressions and hypomania (mild mania) to full-blown depressed and manic states. Over time, they hope to develop software that will learn to detect the changes that precede the transitions to each of these states. They also need to develop and explore strategies for notifying the app user and care providers about mood changes, so that appropriate intervention can take place.

The app currently runs on Android operating system phones, and complies with laws about recording conversations because only one side of the conversation actually gets recorded. The University of Michigan has applied for patent protection for the intellectual property involved.

INFORMATION: Prechter project manager Gloria Harrington, MSW, social worked Jennifer Montgomery, MSW, and research technician Christopher Archer, B.S. also worked on the project.

To be eligible for the smartphone app study, patients must first enroll in the Prechter Fund-sponsored long-term study of bipolar disorder, which accepts adults with and without bipolar disorder. More information and contact information to sign up: http://umhealth.me/prechterbp (study number HUM00000606). For more about the Prechter Fund, visit http://prechterfund.org/

Funding: National Institute of Mental Health, MH100404 END

ELSE PRESS RELEASES FROM THIS DATE:

Why a bacterium got its curve -- and why biologists should know

2014-05-08

Drawing from his engineering background, Princeton University researcher Alexandre Persat had a notion as to why the bacteria Caulobacter crescentus are curved — a hunch that now could lead to a new way of studying the evolution of bacteria, according to research published in the journal Nature Communications. Commonly used in labs to study cell division, C. crescentus naturally take on a banana-like curve, but they also can undergo a mutation in which they grow to be perfectly straight. The problem was that in a laboratory there was no apparent functional difference ...

Population screening for SCD in young people: Feasible with basic screening program

2014-05-08

Amsterdam, 8 May 2014. Despite fears over cost, the wide-scale screening of young people to detect risk of sudden cardiac death (SCD) is feasible and cost effective, according to a study presented at EuroPRevent 2014.(1) More than 12,000 people aged between 14 and 35 were screened at a cost of £35 (40 euro) each; rates of subsequent referral for further investigation were low and considered of "a relative low additional cost" to health services. The study was reported at the EuroPRevent congress 2014 in Amsterdam by Dr Rajay Narain, Clinical Research Fellow from the Department ...

Adults with autism virtually learn how to get the job

2014-05-08

CHICAGO --- Adults with an autism spectrum disorder, who may have trouble talking about themselves and interacting socially, don't always make good impressions in job interviews and have low employment rates. A new human simulation training program -- based on software originally used to train FBI agents -- helps adults with autism improve their job interview skills and confidence, reports a new Northwestern Medicine® study. The new interactive program was designed specifically for adults with psychiatric disorders and was also evaluated for use by adults with autism ...

Hybrid SPECT-CT greatly improves localization of gastrointestinal bleeding

2014-05-08

Leesburg, VA, May 8, 2014—Prompt and accurate localization of the site of bleeding is critical for the management of patients with acute GI bleeding. Planar 99mTc-labeled RBC scintigraphy is sensitive for detection of acute gastrointestinal (GI) bleeding but its accuracy for localization of a bleeding source is arguable, particularly in patients with complex GI anatomy from prior surgeries. Researchers at the Cleveland Clinic reviewed cases of GI bleeding in patients who had a concurrent hybrid SPECT–CT for evaluating equivocal 99mTc-labeled RBC activity on planar scintigraphy. ...

Gluten-free diet reduces risk of type 1 diabetes in mice

2014-05-08

New experiments on mice show, that mouse mothers can protect their pups from developing type 1 diabetes by eating a gluten-free diet. According to preliminary studies by reseachers at the University of Copenhagen, the findings may apply to humans. More than 1% of the Danish population has type 1 diabetes, one of the highest incidence rates in the world. New experiments on mice now show a correlation between the health of the pups and their mothers eating a gluten-free diet. Our hope is that the disease may be prevented through simple dietary changes, the researchers say. "Preliminary ...

Partisan media driving a wedge between citizens, study finds

2014-05-08

COLUMBUS, Ohio – Viewing partisan news reports from both the conservative and liberal viewpoints doesn't make people more accepting of citizens on the other side of the political fence, new research finds. A study of people in the United States and Israel examined citizens' media consumption: specifically, how often they viewed liberal and conservative news outlets and how often they viewed mainstream, relatively neutral news sites. Results showed that people who consumed a greater amount of partisan media content were more polarized – even if they viewed partisan content ...

Homemade stink bug traps squash store-bought models, Virginia Tech researchers find

2014-05-08

A Virginia Tech team of researchers has proven that homemade, inexpensive stink bug traps crafted from simple household items outshine pricier models designed to kill the invasive, annoying bugs. This discovery comes just as warm weather is coaxing the critters out of crevices of homes they were hiding in during the cold winter and homeowners will be looking for a way to get rid of the pest. Researchers in the College of Agriculture and Life Sciences found that the best way to get rid of the little buggers is to fill a foil roasting pan with water and dish soap and ...

Athletes' fear of failure likely to lead to 'choke,' study shows

2014-05-08

A new study by sports scientists at Coventry University and Staffordshire University shows that anxiety about a competitive situation makes even the most physically active of us more likely to slip-up. The research, which is set to be presented at the British Psychological Society's flagship annual conference this week, tested the anticipation and coordination abilities of 18 active and healthy young adults during two sets of identical physical tests – one ostensibly a practice, the other a competition. In the 'competitive' trials, researchers found that the participants' ...

Musical training increases blood flow in the brain

2014-05-08

Research by the University of Liverpool has found that brief musical training can increase the blood flow in the left hemisphere of our brain. This suggests that the areas responsible for music and language share common brain pathways. Researchers from the University's Institute of Psychology, Health and Society carried out two separate studies which looked at brain activity patterns in musicians and non-musicians. The first study looking for patterns of brain activity of 14 musicians and 9 non-musicians whilst they participated in music and word generation tasks. The ...

The Lancet: Antipsychotic medication associated with reduced rate of violent crime

2014-05-08

People who use antipsychotic medication (such as clozapine or risperidone) to treat psychiatric illness are nearly half as likely to commit a violent crime compared to when they are not using such medication, according to new results published in The Lancet. The use of mood stabilising drugs (such as lithium or carbamazepine) is also associated with a reduced rate of violent crime, although the reduction is less pronounced, and only in patients with bipolar disorder. Antipsychotic and mood stabilising medication are used to treat a variety of disorders, but are most commonly ...

Krebs von den Lungen-6 as a biomarker for distinguishing between interstitial lung disease and interstitial lung abnormalities based on computed tomography findings

Listening to bipolar disorder: Smartphone app detects mood swings via voice analysis

ELSE PRESS RELEASES FROM THIS DATE:

LAST 30 PRESS RELEASES: