Collecting data to better identify bipolar disorder
Prof. Emily Mower Provost is collaborating to develop new technologies that provide individuals with insight into how the disease changes over time.
Bipolar disorder is a chronic psychiatric illness characterized by pathological swings of mood and energy between euthymic (healthy) and pathological states of mania and depression. It results in profound disruptions in personal, social, and vocational functioning. Suicidal behavior is common and lifetime, up to 20% of bipolar patients die by suicide.
Prof. Emily Mower Provost is collaborating with researchers at the University of Michigan Depression Center to develop new technologies that provide individuals and their caregivers with insight into how the disease changes over time. The long-term goal of this program is to automatically learn personalized early warning signs associated with mobile phone usage.
The team, with support from the Prechter Bipolar Research Fund at U-M and the National Institute of Mental Health, has collected speech data from 51 patients with bipolar disorder and nine healthy controls. This includes 42,731 and 5,215 calls from the two groups, respectively, totaling over 3,600 hours of speech.
Research on this unique dataset is ongoing. Results have shown that mood can be recognized automatically from conversational speech data and have highlighted both the benefit and importance of personalization.
The focus of Prof. Mower Provost’s research is to provide a computational description of human behavior from audio-visual speech data. This includes work in emotion recognition, modeling the temporal dynamics of emotion expressions, and emotion perception, investigating methods to understand how people integrate audio-visual information when evaluating emotions. Her work also focuses on assistive technology, studying how speech technologies can be used to track mood for people with mental health concerns and to provide speech feedback for individuals with aphasia.
Prof. Emily Mower Provost received her Ph.D. in Electrical Engineering from the University of Southern California (USC), Los Angeles, CA in 2010. She has been awarded a National Science Foundation Graduate Research Fellowship, the Herbert Kunzel Engineering Fellowship from USC, an Intel Research Fellowship, the Achievement Rewards For College Scientists (ARCS) Award, and the UM Oscar Stern Award for Depression Research. She is a member of Tau-Beta-Pi, Eta-Kappa-Nu, and a member of IEEE and ISCA.