Machine learning tool analyzes brain scan data to predict mood disorder medication responses
Georgia State University scientists are developing a new technology that uses complex brain imaging data to predict how patients may respond to mood disorder medications.
The group says their machine learning algorithm analyzes an individual’s functional MRI (fMRI) scan and compares it to thousands of others. Based on these results, and additional clinical information, psychiatrists can gain more insight into which medications they should prescribe.
“This tool could give clinicians an objective window into a patient’s brain, helping them make more tailored treatment recommendations,” said the head of Advanced Biomedical Informatics Group, Jeremy Bockholt, whose startup company received a grant for the project. “Regardless of the diagnosis, is the patient’s brain more similar to someone who responded better to mood stabilizers or to someone who responded better to antidepressants?”
Buckholt is working with his longtime collaborator, Vince Calhoun, a professor of psychology at Georgia State, to train and update the algorithm on scans from a wide range of patients and different types of fMRI machines. They will also interview psychiatrists to understand how the tool can be implemented in real-world settings.
On prior datasets, the group noted, the algorithm was 90% accurate at predicting medical outcomes. But the team believes they can do better, noting that differentiating between mood disorders, such as bipolar disorder and depression is difficult, taking up to a decade for some patients.
The researchers plan to submit their tool to the U.S. Food & Drug Administration soon for medical device approval.
“We’re focused on a patient population that is difficult to diagnose and treat using current methods,” Calhoun said in a statement. “It can be hard to know what type of medication would be helpful for them, if medication is warranted. This could help inform those decisions and get patients on the right medication sooner.”
The work is backed by a two-year, $875,110 grant from the National Institute of Mental Health.
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.