An algorithm may be able to identify patients who best respond to antidepressants before they start treatment, a study published in Psychological Medicine found.
Researchers at Belmont, Mass.-based McLean Hospital set out to determine which patients with depression are best suited for antidepressants, which led to developing the statistical algorithm.
The study grew from data gathered in a multisite clinical trial of antidepressant medications, called Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care.
The study team gathered demographic and clinical characteristics of the EMBARC participants before the start of treatment. Participants also received computer-based tasks, said study co-author Christian Webb, PhD.
Using this information, the research team created an algorithm estimating that about one-third of individuals would see a meaningful therapeutic benefit from antidepressant medications relative to a placebo pill. The researchers randomly assigned participants to a common antidepressant medication or a placebo.
Similar to previous clinical trials, "we found relatively little difference in average symptom improvement between those individuals randomly assigned to the medication vs. placebo," Dr. Webb said.
However, "for the one-third of individuals predicted to be better suited to antidepressants, they had significantly better outcomes if they happened to be assigned to the medication rather than the placebo," he said.
The study found the latter group of patients showed higher depression severity and negative emotionality. These patients were also older, more likely to be employed and showed better cognitive control on a computerized task.
"Our mission is to use these data-driven algorithms to provide clinicians and patients with useful information about which treatment is expected to yield the best outcome for this specific individual," Dr. Webb said. "Rather than using a one-size-fits-all approach, we'd like to optimize our treatment recommendations for individual patients."