Brain imaging used to diagnose, classify PTSD

Andrew Nicholson, PhD, lead author on the study and a post-doctoral fellow at Schulich Medicine & Dentistry and Dr. Ruth Lanius, Professor at Schulich Medicine & Dentistry and Lawson Scientist. Photo courtesy of

London-based researchers believe they’ve come up with a more accurate way to diagnose and classify post-traumatic stress disorder (PTSD) using brain imaging and artificial intelligence.

A study from the Lawson Health Research Institute and Western University found MRI scans combined with machine learning, a method of data analysis that automates analytical model building, could identify whether an individual has PTSD and what subtype it was with 92 per cent accuracy.

Researchers studied 181 participants — some with the common type of PTSD, some with the dissociative subtype of the disorder, and others with no history of PTSD. Using high-powered imaging to analyze patterns of resting-state brain activity, they found unique patterns of brain activity differed significantly between the three groups.

The patterns of brain activity were then uploaded into a machine learning computer algorithm, which analyzed brain scans to predict whether an individual had PTSD.

“Our research group has been leading a number of studies that have shown differences in brain activity and neural connections between healthy individuals and those with different subtypes of PTSD,” said Dr. Ruth Lanius, Lawson researcher and professor at Western’s Schulich School of Medicine & Dentistry. “This study further validates that unique patterns of brain activity are associated with different forms of PTSD.”

PTSD is a mental health condition that can present differently in different patients. In the more common form of the disorder, individuals can become hyperactive with outbursts of emotion, while those with the dissociative subtype become detached and can feel like they are shutting down or having out-of-body experiences.

“Our study suggests brain activity can be used to assist diagnosis of psychiatric disorders and help predict symptoms,” said study lead author Andrew Nicholson, a post-doctoral fellow at Western’s Schulich Medicine & Dentistry. “Patterns of brain activity are objective biomarkers that could be used to diagnose PTSD and, with more research, even predict response to treatment.”

Identifying objective biomarkers could transform psychiatric medicine, Nicholson added.

“The field of psychiatry does not currently have objective biomarkers like those used to diagnose and understand other illnesses or diseases like cancer,” said Nicholson. “By discovering and validating patterns of brain activity as biomarkers, we can bring objective measures to psychiatry and transform patient care.”

The study was recently published in the journal of Psychological Medicine.