An app created by researchers at University of Illinois at Chicago could be used to tack and predict manic and depressive episodes in patients with bipolar disorder just by monitoring their typing on a smartphone keyboard.
The app is called BiAffect. Created by a team of UIC researchers, led by Dr. Alex Leow, associate professor of psychiatry in the UIC College of Medicine and professor of bioengineering and computer science, as well as Peter Nelson, professor of computer science and dean of the UIC College of Engineering, the app unobtrusively analyzes keystroke dynamics such as typing speed, frequency of texting, and social media use.
Based on a pilot study completed with the University of Michigan, more erratic typing (such as ignoring spell check) correlates with a manic episode, while shorter messages correlate with a depressive episode.
“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, according to UIC. “It is thus natural that they also exhibit similar abnormalities in non-verbal communications that are typed on their phones.”
At the moment, BiAffect can be used to study bipolar disorder, as well as bring the app user more self-awareness through dashboard metrics, Nelson said to Chicago Inno. In the future, it could be used to suggest interventions or early warnings, as well as study other mood and cognitive disorders such as Parkinson's and Alzheimer's disease. While they've received interest from commercial health entities, they're currently focused on research with BiAffect.
BiAffect was just awarded a $200,000 grand prize in the Mood Challenge for ResearchKit, funded by the Robert Wood Johnson Foundation, which seeks to support better understanding of mood disorders through smartphone tech. They'll use the funding to further refine the app, release it on the App Store, and support a large scale study of the app including data analysis, said Nelson.
Bipolar disorder affects approximately 5.7 million adult Americans, and is characterized by emotional highs (manic episodes) and lows (depression), according to the National Institute of Mental Health.
For Nelson, researching bipolar disorder and developing BiAffect hits close to home: His son was diagnosed bipolar disorder when he was a freshman in college.
“I began working on this idea many years ago as a way to help my son, and to see it come to fruition with this kind of recognition, and to know that the app will be out there to help people get a better understanding of this disorder is thrilling,” Nelson said.
