Illustration: Maja Moden
An interactive voice application using artificial intelligence (AI) can effectively monitor the well-being of people being treated for serious mental illness, a UCLA study has concluded.
Forty-seven patients under physician care for serious mental illnesses — including bipolar disorder, schizophrenia and major depressive disorder — were followed for up to 14 months using an application called MyCoachConnect. Participants called a toll-free number one or two times a week and answered three open-ended questions when prompted by a computer-generated voice: How have you been over the past few days?; What’s been troubling or challenging over the past few days?; and What’s been particularly good or positive?
MyCoachConnect was designed to collect personalized patient responses, says Armen Arevian, MD (RES ’14), PhD, director of the Innovation Lab at the Jane and Terry Semel Institute for Neuroscience and Human Behavior at UCLA. Specifically, the AI was trained to use an individual’s own words to offer a personalized analysis. The application focuses primarily on the choice of words the patients use in their responses and how their responses change over time, while also taking into account audio features such as tone of voice.
The study, conducted in collaboration with researchers from USC’s Signal Analysis and Interpretation Laboratory, found that the application’s analysis was closely aligned with the physicians’ tracking of their patients’ well-being during the study period. “Technology doesn’t have to be complicated,” Dr. Arevian says. “In this study, patients didn’t need a smartphone. It could be simple and low-tech on the patient end, and high-tech on the back end.”
The researchers hope artificial intelligence that can analyze data collected from apps such as MyCoachConnect will enable more proactive and personalized care. The application, for example, could help to improve treatment by intervening early when a patient is experiencing more symptoms. Participants who were interviewed after the study ended said they found the system easy and enjoyable to use. “They said speaking to a computer-generated voice allowed them to speak more freely,” Dr. Arevian notes. “They also said it helped them feel less lonely because they knew that someone would be listening to it, and to them that meant that someone cared.”
— Marrecca Fiore
“Clinical State Tracking in Serious Mental Illness Through Computational Analysis of Speech,” PLoS ONE, January 15, 2020