Published 17:14 IST, September 30th 2019

AI predicts effectiveness of antidepressants in patients: Study

Researchers use artificial intelligence (AI) to identify patterns of brain activity that make people less responsive to certain antidepressants. Full details

Follow: Google News Icon
  • share
null | Image: self
Advertisement

Researchers use artificial intelligence (AI) to identify patterns of brain activity that make people less responsive to certain antidepressants. In two studies, one published in journal American Journal of Psychiatry and ar in Nature Human Behavior, scientists showed y could use imaging of a patient's brain to decide wher a medication is likely to be effective. Both studies include latest findings from a large national trial -- EMBARC -- intended to establish objective strategies to treat mood disorders based on biology, and minimise prescription of treatments in a trial and error fashion. researchers, including those from UT Southwestern's Center for Depression Research and Clinical Care in US, plan to develop a range of tests such as brain imaging and blood analyses to improve odds of finding best treatment for mood disorders.

"We need to end guessing game and find objective measures for prescribing interventions that will work," said Madhukar Trivedi, who oversees EMBARC.

Correlations between how brain was wired

Trivedi added that people with depression already suffer from hopelessness, and that problem could become worse if y took ineffective medication. In studies, each with more than 300 participants, researchers used imaging techniques to examine brain activity in both a resting state, and during processing of emotions.   researchers said that participants were divided into a healthy control group, and people with depression who eir received antidepressants or a placebo. researchers found correlations between how brain was wired, and wher a participant was likely to improve within two months of taking an antidepressant.

Advertisement

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 more relevant data will come from ir brains' resting state, while in ors emotional processing could be a critical component and a better predictor for wher an antidepressant would work.

"Depression is a complex disease that affects people in different ways," he said.

According to Trivedi, studies are proof that we can use imaging to identify specific signatures of depression in people, much like how techlogy can identify people through fingerprints and facial scans. Nature study applied AI to determine links between an antidepressant's effectiveness, and how a patient's brain processed emotional conflict. In study, participants undergoing brain imaging were shown photographs in quick succession that offered sometimes conflicting messs such as an angry face with word "happy," or vice versa. study ted that each participant was asked to read word on photograph before clicking to next im.

Advertisement

Instead of observing only neural regions kwn to be relevant for predicting effectiveness of antidepressants, Trivedi and his team used machine learning to analyse activity in entire brain.   study ted that AI identified specific brain regions - for example in lateral prefrontal cortices - that were most important in predicting wher participants would benefit from an antidepressant.  Based on findings, researchers said that participants with abrmal neural responses during emotional conflict were less likely to improve within eight weeks of starting medication.

16:50 IST, September 30th 2019