A recent study conducted by the USC Signal Analysis and Interpretation Lab (SAIL) in collaboration with the University of California, Los Angeles suggests that AI can accurately decipher the mental health of people from speech.
The researchers analyzed voice data from people with serious mental illnesses including bipolar disorder, schizophrenia, and major depressive disorders. The individuals and clinicians used the MyCoachConnect interactive voice and mobile tool created by UCLA researchers to provide voice notes regarding their mental health states.
With this data, the researchers used AI to detect changes in the clinical states and the AI produced ratings similar to how the clinicians would rate their patients. Impressive, right?
“Machine learning allowed us to illuminate the various clinically-meaningful dimensions of language use and vocal patterns of the patients over time and personalized at each individual level,” said Dr. Shri Narayanan, senior author and Director of USC SAIL.
This could potentially help detect if the treatment is improving or worsening the mental health of patients. Also, different strategies could be employed to study and analyze the mental health of patients to find what works best for the betterment of a particular patient.
“Listening to people has always been at the core of psychiatry. Our approach builds on that fundamental technique to hear what people are saying using modern AI. We hope this will help us better understand how our patients are doing and transform mental health care to be more personalized and proactive to what an individual needs,” said lead author of the study Dr. Armen Arevian, Director of the Jane and Terry Semel Institute Innovation Lab.
In addition to patient diagnosis, the AI could be used to detect the empathy of trainee addiction counselors so that they could improve their counseling skills for providing better consultation.
