In the not too distant future, a screening assessment for the depression it might include a quick brain scan to identify the best treatment.
Brain imaging combined with machine learning can reveal subtypes of depression and anxiety, according to a new study by researchers at Stanford Medicine. The study, published in the journal Nature Medicineclassifies depression into six biological subtypes, or “biotypes,” and identifies treatments that are more or less likely to work for three of these subtypes.
The different facets of depression
Better methods of matching patients to treatments are desperately needed, said the study’s senior author, Leanne Williams, Ph.D., the Vincent V. C. Woo professor, professor of psychiatry and behavioral sciences and director of the Center for Precision Mental Health at Stanford Medicine. and Wellbeing. Williams, who lost his partner to depression in 2015, has focused his work on innovation in the field of precision psychiatry.
About 30% of people with depression suffer from so-called treatment-resistant depression, meaning that different types of medications or therapies have failed to improve their symptoms. And for about two-thirds of people with depression, treatment fails to completely reverse symptoms back to healthy levels.
This is partly because there is no good way to know which antidepressant or type of therapy might help a particular patient. Drugs are prescribed through a method of trial and error, so it can take months or years to arrive at a drug that works, if that happens at all. And spending so much time trying treatment after treatment, only to feel no relief, can make depression symptoms worse.
“The goal of our work is to figure out how we can do it right the first time,” Williams said. “It’s very frustrating to work in the field of depression and not have a better alternative to this one-size-fits-all approach.”
To better understand the biology underlying depression and anxiety, Williams and his colleagues evaluated 801 study participants who had previously been diagnosed with depression or anxiety using imaging technology known as functional MRI, or fMRI, to measure the brain activity.
They scanned the volunteers’ brains at rest and when they were engaged in several tasks designed to test their cognitive and emotional functioning. The scientists focused on brain regions and the connections between them, which were already known to play a role in depression.
Using a machine learning approach known as cluster analysis to cluster patients’ brain images, they identified six distinct patterns of activity in the brain regions they studied.
The scientists also randomly assigned 250 study participants to receive one of three commonly used antidepressants or behavioral talk therapy. Patients with one subtype, characterized by hyperactivity in cognitive regions of the brain, experienced the best response to the antidepressant venlafaxine (commonly known as Effexor) compared to those with other biotypes.
Those with another subtype, whose resting brains had higher levels of activity across the three regions associated with depression and problem solving, had better symptom relief with behavioral talk therapy. And those with a third subtype, who had lower levels of resting activity in the brain circuit that controls attention, were less likely to see an improvement in their symptoms with talk therapy than those with other biotypes.
The biotypes and their response to behavioral therapy make sense based on what they know about these brain regions, said Jun Ma, M.D., Ph.D., the Beth and George Vitoux Professor of Medicine at the University of Illinois at Chicago is one of the authors of the study.
The type of therapy used in their study teaches patients skills to better deal with everyday problems, so the high levels of activity in these brain regions may allow patients with that biotype to more easily adopt new skills.
As for those with less activity in the region associated with attention and engagement, Ma said it’s possible that pharmaceutical treatment aimed at addressing that less activity first could help these patients get more from talk therapy.
“As far as we know, this is the first time we have been able to show that depression can be explained by different disruptions in the functioning of the brain,” Williams said. “In essence, it is a demonstration of a personalized medicine approach to mental health based on objective measures of brain function.”
In another study, Williams and his team showed that using fMRI brain imaging improved their ability to identify individuals who might respond to antidepressant treatment. In that study, scientists focused on a subtype they call the cognitive biotype of depression, which affects more than a quarter of depressed people and is less likely to respond to standard antidepressants.
By identifying those with the cognitive biotype using fMRI, the researchers accurately predicted the probability of remission in 63% of patients, compared to 36% accuracy without using brain imaging. This increased accuracy means providers may be more likely to get the treatment right the first time. Scientists are now studying new treatments for this biotype with the hope of finding more options for those who do not respond to standard antidepressants.
The different biotypes also correlated with differences in symptoms and work performance among study participants. Those with overactive cognitive regions of the brain, for example, had higher levels of anhedonia (inability to experience pleasure) than those with other biotypes; they also performed worse on executive function tasks. Those with the subtype that responded best to talk therapy also made errors on executive function tasks, but performed well on cognitive tasks.
One of the six biotypes discovered in the study showed no obvious differences in brain activity in the imaged regions compared to the activity of people without depression. Williams believes they probably haven’t explored the full range of brain biology underlying this disorder: their study focused on regions known to be involved in depression and anxiety, but there may be other types of dysfunction in this biotype that their images did not capture.
Williams and his team are expanding the imaging study to include more participants. She also wants to test more types of treatments across all six biotypes, including drugs that traditionally have not been used for depression.
His colleague Laura Hack, M.D., Ph.D., assistant professor of psychiatry and behavioral sciences, began using the imaging technique in her clinical practice at Stanford Medicine through an experimental protocol. The team also wants to establish easy-to-follow standards for the method so that other practicing psychiatrists can begin implementing it.
“To really move the field toward precision psychiatry, we need to identify the treatments that are most likely to be effective for patients and get them on that treatment as early as possible,” Ma said. “Have information about their brain function, especially the validated signatures we evaluated in this study would help provide more precise treatments and prescriptions for individuals.”
Machine learning identifies a new brain network signature of major depression
Using machine learning, researchers have identified new and distinct patterns of coordinated activity between different parts of the brain in people with major depressive disorder, even when different protocols are used to detect these brain networks. Ayumu Yamashita of the Advanced Telecommunications Research Institutes International in Kyoto, Japan, and colleagues present these findings in the open-access journal PLOS Biology.
Although major depression is usually simple to diagnose, a better understanding of the brain networks associated with depression could improve treatment strategies. Machine learning algorithms can be applied to data on brain activity in people with depression to find such associations. However, most studies have focused only on specific subtypes of depression, or have not taken into account differences in brain imaging protocols between healthcare institutions.
To address these challenges, Yamashita and colleagues used machine learning to analyze brain network data from 713 people, 149 of whom suffered from severe depression. This data was collected using a technique called resting-state functional MRI (rs-fMRI), which detects brain activity and produces images that reveal coordinated activity, or “functional connections,” between different parts of the brain. Imaging was performed at different institutions using different protocols.
The machine learning method identified key functional connections in the imaging data that could serve as a brain network signature for major depression. In fact, when the researchers applied that new signature to rs-fMRI data collected across institutions from 521 other people, they achieved 70% accuracy in identifying which of those new people had major depressive disorder.
The researchers hope that their new brain network signature, which can be applied to different imaging protocols, can serve as a basis for discovering brain network patterns associated with depression subtypes and for revealing relationships between depression and other disorders. A better understanding of brain network connections in major depression could help match patients with effective treatments and guide the development of new treatments.
#Depression #distinct #types #identified