Both the studies include the latest findings from a large national trial – EMBARC – intended to establish objective strategies to treat mood disorders based on biology, and minimize the prescription of treatments in a trial and error fashion.
The researchers, including those from UT Southwestern's Center for Depression Research and Clinical Care in the US, plan to develop a range of tests such as brain imaging and blood analyses to improve the odds of finding the best treatment for mood disorders.
"We need to end the guessing game and find objective measures for prescribing interventions that will work," said Madhukar Trivedi, who oversees EMBARC.
Trivedi added that people with depression already suffer from hopelessness, and that the problem could become worse if they took ineffective medication.
In the studies, each with more than 300 participants, the researchers used imaging techniques to examine the brain activity in both a resting state, and during the processing of emotions.
The researchers said that the participants were divided into a healthy control group, and people with depression who either received antidepressants or a placebo.
The researchers found correlations between how the brain was wired, and whether a participant was likely to improve within two months of taking an antidepressant.
Trivedi said that brain imaging during various states was important to get a more accurate picture of how depression manifested in a particular patient.
For some people, he added that the more relevant data will come from their brains' resting state, while in others the emotional processing could be a critical component and a better predictor for whether an antidepressant would work.
"Depression is a complex disease that affects people in different ways," he said.
According to Trivedi, the studies are proof that we can use imaging to identify specific signatures of depression in people, much like how technology can identify people through fingerprints and facial scans.
The Nature study applied AI to determine the links between an antidepressant's effectiveness, and how a patient's brain processed emotional conflict.
In the study, participants undergoing brain imaging were shown photographs in quick succession that offered sometimes conflicting messages such as an angry face with the word "happy," or vice versa.
The study noted that each participant was asked to read the word on the photograph before clicking to the next image.
Instead of observing only neural regions known to be relevant for predicting the effectiveness of antidepressants, Trivedi and his team used machine learning to analyze activity in the entire brain.
The study noted that the AI identified specific brain regions – for example in the lateral prefrontal cortices – that were most important in predicting whether participants would benefit from an antidepressant.
Based on the findings, the researchers said that participants with abnormal neural responses during emotional conflict were less likely to improve within eight weeks of starting the medication.