May 16, 2017

U-M team part of effort behind award-winning app to help track and detect manic and depressive episodes in bipolar disorder

Today, the winner was announced in a national “Mood Challenge” competition to develop mobile apps to study mood disorders using Apple’s ResearchKit. The grand prize went to a team that includes University of Michigan researchers, and is led by colleagues at the University of Illinois at Chicago, along with collaborators at Sage Bionetworks.

The Mood Challenge for ResearchKit -- a New Venture Fund program funded by the Robert Wood Johnson Foundation -- called on researchers to use the open-source platform for creating iOS apps to come up with new ways to study mood disorders.

The winning app, called BiAffect, unobtrusively monitors mobile device usage – including keyboard dynamics such as typing speed -- to help predict manic and depressive episodes in people with bipolar disorder. The $200,000 grand prize will allow the team to continue to refine and launch their app in the Apple App Store.

“Having a tool that’s on a device that everyone is using anyway, that can capture changes in behavior and problems with functioning before the patient is even aware, could be a great way to help people with bipolar disorder manage their condition,” says Kelly Ryan, Ph.D., a U-M neuropsychologist and clinical assistant professor of psychiatry who worked on the project. “We’re glad to have partnered with UIC on this effort.”

The team was led by UIC’s Alex Leow, associate professor of psychiatry, bioengineering, and computer science in the UIC College of Medicine and College of Engineering, and Peter Nelson, professor of computer science and dean of the UIC College of Engineering.

"The vision for BiAffect is for it to serve as a kind of 'fitness tracker' for the brain," said Leow. "The Mood Challenge helped us to realize this vision and the finished app will be a first-of-its kind tool for researchers to study mood disorders and even cognitive disorders such as Parkinson's and Alzheimer's disease."

Bipolar disorder, which causes extreme mood swings between the emotional highs of manic episodes and low periods of depression, affects approximately 5.7 million adult Americans, or about 2.6 percent of those over 18, according to the National Institute of Mental Health. Diagnosis relies on careful history-taking and examination.

In previous research, Ryan, Leow and Nelson completed a pilot study of 30 participants recruited from the Heinz C. Prechter Bipolar Research Program that showed altered keystroke dynamics metadata on smartphones correlated with depressive and manic episodes in people with bipolar disorder.

 “During a manic episode, people with bipolar disorder exhibit some common behaviors, such as talking really, really fast with diminished self-control and ‘flight of ideas’” Leow said. “It is thus natural that they also exhibit similar abnormalities in non-verbal communications that are typed on their phones.”

As a concrete example, spell-checking requires the writer to pause and determine whether or not to edit or accept suggestions according to Autocorrect, or rather to simply keep typing. "People in the midst of a manic episode commonly have reduced impulse control, so it is not surprising that our pilot data supported that they tend to blow through the spellcheck alerts,” Leow said.

During depressive episodes, typing a long message may become laborious, and messages tend to be shorter, she explained.

BiAffect could also lead to a novel mobile health technology that helps researchers determine the efficacy of various treatments for bipolar and other mood disorders.

The Mood Challenge attracted more than 70 applications after it was announced in April 2016. BiAffect and four other teams were recommended by a panel of judges to receive $20,000 and expert mentorship at a 2-day app design boot camp. BiAffect was selected as one of the finalists last October, and received an additional $100,000 to develop their ResearchKit design into a prototype and pilot project using Apple’s TestFlight.

Other senior personnel of BiAffect includes Dr. Olusola Ajilore, Dr. Scott Langenecker, Dr. Neil Smalheiser, Dr. Philip Yu and Dr. Jennifer Duffecy of UIC, and Dr. Melvin McInnis and Dr. Kelly Ryan of the University of Michigan. BiAffect’s lead iOS developers are Andrea Piscitello and Faraz Hussain. In addition, Dr. John Zulueta, Bokai Cao, and the Motus Design Group are also members of the BiAffect team.

Langenecker, who moved to UIC from U-M several years ago, connected the UIC team to the Prechter team. Ryan was able to incorporate an Android version of BiAffect’s keyboard extension to an app she has been developing that involves interactive tracking of mood, cognition, and daily function.

Ryan and McInnis also see potential for the BiAffect approach to be combined with a voice-based approach that McInnis has been developing with U-M College of Engineering colleagues, called PRIORI. The PRIORI app is currently being evaluated and analyzes voice patterns in outgoing calls to look for patterns over time and how they relate to mood and function.
Adapted from a UIC press release