Skip to main content

Using Voice Analysis to Assess the Well-Being of Patients

January 24, 2020

An interactive voice application’s assessment of patient well-being through analysis of their speech was highly comparable with physicians’ tracking of patient well-being, according to a study published online in PLOS One.

Armen Arevian
Armen Arevian, MD, PhD

The pilot study included 47 patients with diagnoses of bipolar disorder, major depressive disorder, schizophrenia, or schizoaffective disorder. For up to 14 months, patients provided speech samples by calling a toll-free number at least weekly and answering 3 open-ended questions: How have you been over the past few days? What’s been troubling or challenging over the past few days? What’s been particularly good or positive?

The application, MyCoachConnect, employed artificial intelligence trained to use a patient’s words to analyze well-being. The app focused mostly on word choice and how responses changed over time and had a smaller emphasis on tone of voice and other audio features.

Using Data to Better Understand Patients and Their Mental Health

“The way people answer questions and the way they change their answers over time is unique to each patient,” said lead author Armen Arevian, MD, PhD, director of the Innovation Lab at the Jane and Terry Semel Institute for Neuroscience and Human Behavior, University of California Los Angeles. “We were looking at a person as a person and not as a diagnosis.”

After comparing the technology’s analysis of patient well-being with patient global assessment ratings provided by clinicians, researchers deemed the app both effective and feasible to use.

“Technology doesn’t have to be complicated,” Dr. Arevian said. “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 backend.”

Some patients remarked that speaking to a computer-generated voice was freeing.

“They also said it helped them feel less lonely because they knew that someone would be listening to it,” Dr. Arevian said, “and to them that meant that someone cared.”

—Jolynn Tumolo

References

Arevian AC, Bone D, Malandrakis N, et al. Clinical state tracking in serious mental illness through computational analysis of speech. PLOS One. 2020;15(1):e0225695.

App uses voice analysis, AI to track wellness of people with mental illness [press release]. Los Angeles, California: University of California - Los Angeles Health Sciences; January 17, 2020.

Back to Top