Press "Enter" to skip to content

Using AI to diagnose Post Traumatic Stress Disorder by Voices

Post traumatic stress disorder is a mental health condition triggered by a terrifying event either experiencing it or witnessing it. Most people who go through traumatic events may have temporary difficulty adjusting and coping, but with time and good self-care, they usually get better.

The symptoms PTSD may include flashbacks, nightmares and severe anxiety, as well as uncontrollable thoughts about the event. If the symptoms get worse, last for months or even years, and interfere with a patient’s day-to-day functioning such person may be suffering from post traumatic stress disorder.

A recent publication on the Depression and Anxiety journal studies found that an artificial intelligence tool can distinguish with 89 per cent accuracy between the voices of those with or without post traumatic stress disorder.

Speech-based characteristics can be used to diagnose post traumatic stress disorder

It has been confirmed that more than 70 per cent of adults globally are experiencing a traumatic event at some point in their lives, with up to 12 per cent of people in some struggling countries suffering from PTSD. Those with the condition experience strong, persistent distress when reminded of a triggering event.

According to a study, post traumatic stress disorder diagnosis is most often determined by clinical interview or a self-report assessment, both inherently prone to biases. Read: Vital Post Stress Support for you Health

This has led to efforts to develop objective, measurable, physical markers of post-traumatic stress disorder progression, much like laboratory values for medical conditions, but progress has been slow.

Read also:   Role of Neuropathologist to Brain and Nervous System Patients

Another research through a statistical/machine learning technique, called random forests, claimed that the ability to “learn” how to classify individuals based on examples.

Such Artificial Intelligence programs build “decision” rules and mathematical models that enable decision-making with increasing accuracy as the amount of training data grows.

Post Traumatic Stress

The researchers recorded standard first, hours-long diagnostic interviews, called Clinician-Administered PTSD Scale, or CAPS, of 53 Iraq and Afghanistan veterans with military-service-related PTSD, as well as those of 78 veterans without the disease.

The recordings were then fed into voice software from SRI International the institute that also invented Siri to yield a total of 40,526 speech-based features captured in short spurts of talk, which the team’s AI program sifted through for patterns.

The random forest program linked patterns of specific voice features with post traumatic stress disorder, including less clear speech and a lifeless, metallic tone, both of which had long been reported anecdotally as helpful in diagnosis.

While the current study did not explore the disease mechanisms behind post traumatic stress disorder, the theory is that traumatic events change brain circuits that process emotion and muscle tone, which affects a person’s voice.

Application of Artificial Intelligence voice tool with more data

The research team plans to train the Artificial Intelligence voice tool with more data to further validate it on an independent sample, and apply for government approval to use the tool clinically globally.

A lead author Adam Brown, PhD, adjunct assistant professor in the Department of Psychiatry at NYU School of Medicine. said;

“Speech is an attractive candidate for use in an automated diagnostic system, perhaps as part of a future post traumatic stress disorder smartphone app, because it can be measured cheaply, remotely, and non-intrusively,”

Dimitra Vergyri, director of SRI International’s Speech Technology and Research (STAR) Laboratory, said;

“The speech analysis technology used in the current study on PTSD detection falls into the range of capabilities included in our speech analytics platform called SenSay Analytics.

“The software analyzes words — in combination with frequency, rhythm, tone, and articulatory characteristics of speech to infer the state of the speaker, including emotion, sentiment, cognition, health, mental health and communication quality. The technology has been involved in a series of industry applications visible in startups like Oto, Ambit and Decoded Health.”

Culled from Science Daily | Artificial intelligence can diagnose PTSD by analyzing voices (Study tests potential telemedicine approach)

 29 total views,  3 views today

One Comment

Leave a Reply

Your email address will not be published. Required fields are marked *