Researchers have created an artificial intelligence (AI) algorithm that may be able to identify complex mood disorders—such as major depressive disorder (MDD) —while also pinpointing a medication response from the patient.

 “This study takes a major step towards finding a biomarker of medication response in emerging adults with complex mood disorders,” Elizabeth Osuch, MD, a clinician-scientist at Lawson, medical director at FEMAP and co-lead investigator on the study, said in a statement. “It also suggests that we may one day have an objective measure of psychiatric illness through brain imaging that would make diagnosis faster, more effective and more consistent across health care providers.”

Researchers from Lawson Health Research Institute, The Mind Research Network and the Brainnetome Center examined 78 adult patients emerging from mental health programs at the London Health Sciences Centre (LHSC), primarily from the First Episode Mood and Anxiety Program (FEMAP).

The first phase of the study featured 66 patients who had completed treatment for either MDD or bipolar type I, a form of bipolar disorder that often includes full manic episodes. An additional 33 research participants with no history of mental illness represented the control group.

Each individual underwent a brain scan to examine different brain networks using Lawson’s functional magnetic resonance imaging (fMRI) capabilities at St. Joseph’s Health Care London.

The researchers analyzed and compared the scans of the three groups and found that they were different in particular brain networks, including the default mode network—a set of regions known to control self-reflection—and the thalamus—a gateway that connects multiple cortical regions and helps control arousal alertness.

The team used the data to update a new algorithm that uses machine learning. It was able to examine fMRI scans to identify whether a patient has MDD or bipolar I with a 92.4 percent accuracy.

Next, the researchers performed imaging with 12 additional volunteers that have an unclear diagnosis of a complex mood disorder. The algorithm was able to predict the diagnosis and more importantly how the participant would respond to medication.

“Antidepressants are the gold standard pharmaceutical therapy for MDD while mood stabilizers are the gold standard for bipolar I,” Osuch said. “But it becomes difficult to predict which medication will work in patients with complex mood disorders when a diagnosis is not clear. Will they respond better to an antidepressant or to a mood stabilizer?”

Diagnoses are currently based on a patient’s history and behavior and medication decisions are ultimately based on that diagnosis.

“This can be difficult with complex mood disorders and in the early course of an illness when symptoms may be less well-defined,” Osuch said. “Patients may also have more than one diagnosis, such as a combination of a mood disorder and a substance abuse disorder, further complicating diagnosis. Having a biological test or procedure to identify what class of medication a patient will respond to would significantly advance the field of psychiatry.”

The study was published in  Acta Psychiatrica Scandinavica.