Brain scan, AI may help determine efficacy of OCD treatment

UCLA researchers said a series of brain scans and an artificial intelligence system correctly predicted which obsessive compulsive disorder patients would respond to therapy more than two-thirds of the time.

By Ed Adamczyk

Feb. 14 (UPI) -- Researchers at the University of California Los Angeles have developed an artificial intelligence system to predict whether patients with obsessive compulsive disorder can benefit from cognitive behavior therapy.

Neuroscience researchers at UCLA announced on Tuesday that a technique using brain scans and machine learning can forecast whether those with OCD should be treated with cognitive behavior therapy.


OCD is a lifelong illness marked by repetitive thoughts and actions that can seriously impair work performance, relationships and quality of life. It is commonly treated with medication and cognitive behavioral therapy, or CBT, a form of psychotherapy. Treatment can be expensive and time-consuming, and is not always successful.

"If the results of this study are replicated in future studies, the methods we used could potentially give clinicians a new predictive tool," Nicco Reggente, the study's lead author, said in a press release. "If a patient is predicted to be a non-responder to cognitive behavioral therapy, clinicians could pursue different options."

For the study, published this week in the Proceedings of the National Academy of Sciences, researchers analyzed MRI brain scans of 42 people before and after four weeks of cognitive behavioral therapy, noting how different areas of the brain synchronized and were activated, a process called functional connectivity, during downtime. The researchers also studied the severity of OCD before and after therapy using a scaled system.


Using machine learning, a form of artificial intelligence, they determined which patients would best respond to treatment. The system determined rates or success or failure with 70 percent accuracy, and its algorithm correctly predicted final test scores with only a small margin of error.

"This method opens a window into OCD patients' brains to help us see how responsive they will be to treatment," said Dr. Jamie Feusner, the study's senior author. "The algorithm performed far better than our own predictions, based on their symptoms and other clinical information."

Feusner added that OCD treatment could begin with a low-cost brain scan, to eliminate patients unlikely to improve with behavioral therapy -- which can cost up to $5,000 per week.

Latest Headlines