July 18, 2019
2 min read

Using speech-based technologies to detect mental illness

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

The potential of artificial intelligence and machine learning approaches to identify mental illness continues to be an exciting area of research.

According to a paper presented at the Canadian Conference on Artificial Intelligence, Mashrura Tasnim, PhD student, and Eleni Stroulia, PhD, professor in the department of computing science at University of Alberta, Canada, developed a methodology that combines several machine-learning algorithms to detect depression using acoustic cues.

"A realistic scenario is to have people use an app that will collect voice samples as they speak naturally,” Stroulia said in a press release. “The app, running on the user's phone, will recognize and track indicators of mood, such as depression, over time. Much like you have a step counter on your phone, you could have a depression indicator based on your voice as you use the phone. This work, developing more accurate detection in standard benchmark data sets, is the first step.”

To give mental health professionals some examples of what similar technologies can do in clinical settings, Healio Psychiatry has compiled some recent articles.

Machine learning approach predicts emergence of psychosis

Using a machine learning approach to analyze language, researchers found that speech with low levels of semantic density and an increased tendency to talk about voices and sounds predicted the emergence of psychosis. Read more.

Speech-based technologies could detect PTSD in veterans

Using a speech-based algorithm, researchers could objectively differentiate male warzone-exposed veterans with and without PTSD, according to a study published in Depression & Anxiety. Read more.

VIDEO: Analyzing speech patterns to measure emotion in bipolar disorder

Melvin G. McInnis, MD, Thomas B. and Nancy Upjohn Woodworth Professor of Bipolar disorder and Depression and director of the Heinz C. Prechter Bipolar Research Program at University of Michigan, discussed analyzing speech segments from people with bipolar disorder to measure emotion at the American Psychiatric Association annual meeting. Read more.

Machine learning analysis of speech detects anxiety, depression in children

Using a machine learning algorithm to analyze audio data, researchers could detect signs of anxiety and depression in the speech patterns of young children, according to research published in Journal of Biomedical and Health Informatics. Read more.

AI could play role in treatment of mental health, neurological disorders

Artificial intelligence and machine learning are becoming more prevalent in health care. The science of training computers is providing clinicians with additional insights into the mental health of patients, which they may be able to soon use to determine appropriate treatment plans. Read more.

Digital phenotyping has potential in psychiatry

Digital phenotyping — a method of collecting and synthesizing data from people’s experiences via smartphones or wearable technology — has the potential to help clinicians monitor and treat patients with psychiatric disorders, according to a CME article published in Psychiatric Annals. Read more.


Tasnim M, Stroulia E. Detecting depression from voice. Presented at: Canadian Conference on Artificial Intelligence; May 28-31, 2019; Kingston, Ontario, Canada.