Mood disorders like major depressive disorder (MDD) and bipolar disorder are often complex and hard to diagnose, especially among youth when the illness is just evolving. This can make decisions about medication difficult. In a collaborative study by Lawson Health Research Institute, The Mind Research Network and Brainnetome Center, researchers have developed an artificial intelligence (AI) algorithm that analyzes brain scans to better classify illness in patients with a complex mood disorder and help predict their response to medication.
The study included 78 adult patients from mental health programs at London Health Sciences Centre (LHSC), primarily from the First Episode Mood and Anxiety Program (FEMAP). The first part of the study involved 66 patients who had already completed treatment for a clear diagnosis of either MDD or bipolar type I. Bipolar I is a form of disorder that features full manic episodes. This part of the study also involved 33 research participants with no history of mental illness. Each individual participated in scanning to examine different brain networks using functional magnetic resonance imaging (fMRI).
The researcher analyzed and compared the scans of those with MDD, bipolar I and no history of mental illness. They found the three groups differed in particular brain networks. These included regions in the default mode network, a set of regions thought to be important for self-reflection. It also included the thalamus, a ‘gateway’ that connects multiple cortical regions and helps control arousal and alertness.
Machine learning predicts medication response
Researchers used the data to develop an AI algorithm that uses machine learning to examine fMRI scans to classify whether a patient has MDD or bipolar I. The algorithm correctly classified the illness of participants with a known diagnosis with 92.4 per cent accuracy.
Then they performed imaging with 12 participants with complex mood disorders for whom a diagnosis was not clear. They used the algorithm to study a participant’s brain function to predict the diagnosis. More importantly, they examined the participant’s response to medication. “Antidepressants are the gold standard pharmaceutical therapy for MDD while mood stabilizers are the gold standard for bipolar I,” says Dr. Elizabeth Osuch, medical director at FEMAP. “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?”
The researchers hypothesized that participants classified by the algorithm as having MDD would respond to antidepressants while those classified as having bipolar I would respond to mood stabilizers. When tested with the complex patients, 11 out of 12 responded to the medication predicted by the algorithm. “Machine learning is an approach that learns in a data-centric way. It provides information that can be used to predict future data sets. In this case, that’s the prediction of MDD from bipolar I,” says Dr. Vince Calhoun, President of The Mind Research Network. “There are multiple layers of algorithms in this project. The first layer includes an approach that automatically extracts brain networks from the data provided. The second layer includes automatically identifying which combinations of networks are most sensitive or predictive of MDD and bipolar I.”
“This study takes a major step towards finding a biomarker of medication response in emerging adults with complex mood disorders,” says Dr. Osuch. “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.”
Source: Lawson Health Research Institute