Researchers at New York City-based NYU School of Medicine and NYU Langone Health used machine learning techniques to train the program to identify speech patterns in recorded interviews with individuals diagnosed with military service-related PTSD. Once trained, the AI was reportedly able to distinguish between the voices of those with and without PTSD with 89 percent accuracy.
Though the study did not seek to identify the underlying biological mechanisms of PTSD, the biomarkers observed in the study, including less clear speech and a lifeless tone of voice, are regularly used to help diagnose PTSD in clinical settings.
The next steps for the researchers will be to continue training and validating the AI tool using even more data, then apply for government approval for its widespread use, perhaps in the form of a PTSD-identifying smartphone app, according to Adam Brown, PhD, lead author of the study and adjunct assistant professor in the Department of Psychiatry at NYU School of Medicine.
More articles about AI:
IBM stops development, sales of Watson for Drug Discovery
Study: Crowdsourced AI faster than humans in segmenting cancerous lung tumors
Gilead, machine learning startup test AI’s drug development potential
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.