Brain structure predicts treatment response to antidepressants and placebos, study finds

New research from the Institute of Psychiatry, Psychology and Neuroscience (IoPPN) at King’s College London, the University of East London (UEL) and the University of Pennsylvania has used artificial intelligence to analyze images brain of people living with major depressive disorder (MDD).

The article “Neuroanatomical dimensions in medication-free individuals with major depressive disorder and response to treatment with SSRI antidepressants or placebo,” published in Natural mental healthfound that the amount of gray and white brain matter in MDD could predict treatment response to traditional antidepressants (SSRIs) and placebo drugs.

Gray matter in the brain has several responsibilities, including processing sensations, perception, voluntary movements, learning, speech, and cognition. The white matter is responsible for ensuring communication between the different gray matter areas of the brain and the rest of the body.

Although MDD affects more than 320 million people worldwide, researchers have yet to establish biomarkers that can help predict treatment response. The researchers in this study wanted to explore whether there are distinct brain mechanisms underlying disease presentation.

They studied brain scans of 685 participants with a confirmed diagnosis of MDD, who were experiencing a depressive episode of at least moderate severity and who were not taking any medication at the time of the scan. This was compared to brain scans of 699 healthy controls.

The research team established two distinct “dimensions”. Dimension 1 (D1) was characterized by preserved gray and white matter, similar to levels found in healthy controls. Conversely, those in dimension 2 (D2) showed widespread declines.

“Depression can have a huge impact on a person’s daily life. It is not only the leading cause of disability, but also the leading precursor to suicide. Despite this, we have no biomarkers to help us prevent identify depression. and we cannot predict treatment response at the individual level. In this study, we used machine learning to analyze MRI scans for depression. Our results provide an essential first step in defining biomarkers that make up depression,” says Professor Cynthia Fu, the joint first author of King’s IoPPN and UEL study.

The researchers also wanted to study how these dimensions related to clinical response to antidepressant use. They found that participants in the D1 study had a significantly greater response to SSRI medications than to placebo. In contrast, those in the D2 group showed no significant difference in the effectiveness of SSRIs or placebos. The research team suggests that this could act as a biomarker to identify the likelihood of treatment resistance much earlier.

Dr Mathilde Antoniades, co-author of the study, said: “Researchers around the world are generously sharing data on MDD participants who were all taking no medication. » Professor Christos Davatzikos, from the University of Pennsylvania, said: “We are using cutting-edge AI methods in this unique dataset. »

Researchers now hope to define the pathological dimensions specific to depression and those common to other mental health disorders.