Scientists say they are close to identifying speech patterns to differentiate between post-traumatic stress disorder (PTSD) and traumatic brain injury.
MIT Technology Review reports how Charles Marmar, chairman of the department of psychiatry at New York University’s Langone Medical Center, together with researchers at Stanford University’s non-profit R&D development organisation, SRI International, are collecting voice samples to analyse vocal cues such as tone, pitch, rhythm, rate and volume.
Marmar has worked in psychiatry for 40 years and told the publication that when a combat veteran steps into his office for an evaluation, “he still can’t diagnose post-traumatic stress disorder with 100 per cent accuracy,” based on patient responses to questions as some patients may be too ashamed to answer honestly.
Over the past five years, Marmar has identified a set of 30 vocal characteristics that he believes to be associated with PTSD and traumatic brain injury, from 40,000 features extracted from the voices of war veterans and control subjects.
Early results presented back in 2015 showed that a voice test developed by Marmar and his team was 77 per cent accurate at distinguishing between PTSD patients and healthy volunteers in a study of 39 men.