- My News
- All News
- Most Popular
According to study findings published Monday in Nature Biotechnology, researchers have developed a machine-learning algorithm that can accurately predict whether an antidepressant will work based on a patient's brain activity. Co-author Amit Etkin said that "this study takes previous research, showing that we can predict who benefits from an antidepressant, and actually brings it to the point of practical utility."
The study included 309 participants with major depression who were randomly assigned to placebo or the selective serotonin reuptake inhibitor sertraline. Researchers used electroencephalography (EEG) to measure electrical activity in the participants' cortex before treatment was initiated. The algorithm was applied to the EEG data to predict which patients would benefit from sertraline within two months, with results validated in three additional patient groups.
The authors said "symptom improvement was robustly predicted in a manner both specific for the antidepressant sertraline…and generalisable across different study sites and EEG equipment." They noted that in addition to "[reflecting] general antidepressant medication responsivity," the sertraline-predictive EEG signature also "related differentially to a repetitive transcranial magnetic stimulation treatment outcome."
Study leader Madhukar Trivedi said "we provided abundant data to show we can move past the guessing game of choosing depression treatments and alter the mindset of how the disease should be diagnosed and treated." The next steps include developing an artificial-intelligence (AI) interface that can be widely integrated with EEGs across the US and eventually seeking FDA approval.
Did you like this article?