Science 2 min read

AI in Mental Health: Using Speech Analysis to Diagnose PTSD 

PTSD is one of the most common mental disorders, yet it continues to be difficult to diagnose. Now, a new form of speech analysis could make diagnosis easier than ever.

Shutterstock

Shutterstock

Researchers have developed a speech analysis software that could change the way we diagnose mental disorders.

Of all the mental disorders, Post Traumatic Stress Disorder (PTSD) may be the most challenging to diagnose. Aside from the clinician’s subjectivity, patients often withhold information, making it difficult for the clinician to spot the symptoms.

Now, researchers at New York University are using artificial intelligence to take the guesswork out of diagnosing the mental disorder. And it only requires listening to the sound of the patient’s voice.

Speech Analysis Algorithm For Diagnosing PTSD

Researchers at NYU teamed up with SRI International – the research institute that brought Siri to iPhones – to develop a voice analysis program. Alongside understanding human speech, the program is designed to detect PTSD signifiers and emotions.

In other words, it could listen for auditory markers and other minor variables that the human ear would easily miss, analyze the data, and reach a diagnosis.

While the algorithm’s verdict is not perfect, it’s pretty close. According to the researchers, the speech analysis program can diagnose PTSD with 89 percent accuracy.

How the Speech Analysis Program Works

The researchers collected 40,000 speech samples from 129 war-zone exposed veterans. Using the audio recordings, they taught the AI to identify vocal changes that are linked with PTSD.

These include a shorter tonal range with less enunciation as well as a slow and more monotonous cadence.

Also, the AI can detect other potential indicators of a PTSD diagnosis such as changes in voice caused by the tension of the throat muscle and whether the patient’s tongue touches the lips.

Speaking to New York Times, Psychiatry Professor at NYU and one of the paper’s author, Charles Marmar said;

”We thought the telling features would reflect agitated speech. In point of fact, when we saw the data, the features are flatter, more atonal speech. We were capturing the numbness that is so typical of PTSD patients.”

There is no denying that the program is a breakthrough for mental health professionals. However, it is still far from perfect.

Since the researchers only used data from male combat veterans, the program is limited to military use. But there’s room for growth.

In the near future, the researchers can refine the technology to enable clinicians to diagnose the mental disorder effectively.

Read More: 4 Stephen Hawking Predictions to Ruin Your Faith in Humanity

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.