Algorithm identifies patients best suited for antidepressants

July 17, 2018 by Christopher Peterson, McLean Hospital
Algorithm identifies patients best suited for antidepressants
Results of this study bring us closer to identifying individuals likely to benefit from antidepressants. Credit: McLean Hospital

McLean Hospital researchers have completed a study that sought to determine which individuals with depression are best suited for antidepressant medications. Their findings, published in Psychological Medicine on July 2, 2018, have led to the development of a statistical algorithm that identifies patients who may best respond to antidepressants—before they begin treatment.

Christian A. Webb, Ph.D., director of the Treatment and Etiology of Depression in Youth Laboratory at McLean Hospital, is one of the study's coauthors, along with Diego A. Pizzagalli, Ph.D., director of McLean's Center for Depression, Anxiety and Stress Research. Webb explained how their paper, "Personalized Prediction of Antidepressant v. Placebo Response: Evidence from the EMBARC Study," grew from data derived from a large and recently completed multi-site clinical trial of called Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC). Demographic and clinical characteristics of individuals who took part in the EMBARC study were collected prior to the start of by the study team across four sites (Columbia University, Massachusetts General Hospital, the University of Michigan, and UT Southwestern Medical Center). Participants were also administered computer-based tasks.

Using this information, Webb and his colleagues developed an algorithm predicting that approximately one-third of individuals would derive a meaningful therapeutic benefit from antidepressant medications relative to placebo. In the study, participants were randomly assigned to a common antidepressant or a placebo pill.

The results, Webb said, were like many previous clinical trials in that "we found relatively little difference in average symptom improvement between those individuals randomly assigned to the medication vs. placebo." However, he explained, "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." The latter group of patients were characterized by higher depression severity and negative emotionality, were older, more likely to be employed, and exhibited better cognitive control on a computerized task.

"These results bring us closer to identifying groups of patients very likely to benefit preferentially from an SSRI and could realize the goal of personalizing antidepressant treatment selection," added UT Southwestern Medical Center's Madhukar Trivedi, MD, coordinating principal investigator for the EMBARC study.

Building on these findings, Webb said, his team is now looking to adapt the algorithm for use in "real-world" clinics. Specifically, he reported, the researchers are looking to collaborate with the University of Pennsylvania on a study that would test the algorithm in psychiatric clinics treating suffering from depression by comparing two or more viable treatments—for example, two different classes of antidepressants, or antidepressants vs. psychotherapy.

"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," Webb said. He explained that research like this may further the goal of creating "personalized medicine" in health care. "Rather than using a one-size-fits-all approach, we'd like to optimize our treatment recommendations for individual patients," he said.

Explore further: Brain activity can predict success of depression treatment

More information: Christian A. Webb et al. Personalized prediction of antidepressant v. placebo response: evidence from the EMBARC study, Psychological Medicine (2018). DOI: 10.1017/S0033291718001708

Related Stories

Brain activity can predict success of depression treatment

April 11, 2018
McLean Hospital and Harvard Medical School researchers believe they have uncovered a method that could be useful in predicting a depressed patient's treatment prognosis, prior to starting treatment.

National trial: EEG brain tests help patients overcome depression

May 15, 2018
Imagine millions of depressed Americans getting their brain activity measured and undergoing blood tests to determine which antidepressant would work best. Imagine some of them receiving "brain training" or magnetic stimulation ...

Study identifies a link between antidepressant treatment resistance and inflammation

June 11, 2018
Researchers at Emory University have found that depressed patients who have not responded to multiple antidepressants exhibit evidence of increased inflammation. Findings were recently published online in the journal, Psychoneuroendocrinology.

New study rebuts the claim that antidepressants do not work

August 18, 2017
A theory that has gained considerable attention in international media, including Newsweek and the CBS broadcast 60 minutes, suggests that antidepressant drugs such as the SSRIs do not exert any actual antidepressant effect. ...

Better prediction for effectiveness of paroxetine

April 13, 2017
A third of patients with depression do not respond to the first antidepressant medication prescribed. Currently, the only approach available is one of trial and error. In this study, Max Planck scientists have identified ...

Recommended for you

Suicide risk in abused teen girls linked to mother-daughter conflict

October 18, 2018
Teenage girls who were maltreated as children are more likely to entertain suicidal thoughts if the relationship with their mother is poor and the degree of conflict between the two of them high.

Study shows how bias can influence people estimating the ages of other people

October 17, 2018
A trio of researchers from the University of New South Wales and Western Sydney University has discovered some of the factors involved when people make errors in estimating the ages of other people. In their paper published ...

Infants are more likely to learn when with a peer

October 16, 2018
Infants are more likely to learn from on-screen instruction when paired with another infant as opposed to viewing the lesson alone, according to a new study.

Researchers use brain cells in a dish to study genetic origins of schizophrenia

October 16, 2018
A study in Biological Psychiatry has established a new analytical method for investigating the complex genetic origins of mental illnesses using brain cells that are grown in a dish from human embryonic stem cells. Researchers ...

Income and wealth affect the mental health of Australians, study shows

October 16, 2018
Australians who have higher incomes and greater wealth are more likely to experience better mental health throughout their lives, new research led by the Bankwest Curtin Economics Centre has found.

Study suggests biological basis for depression, anxiety, sleep disturbances in older adults

October 15, 2018
UC San Francisco researchers, in collaboration with the unique Brazilian Biobank for Aging Studies (BBAS) at the University of São Paulo, have shown that the earliest stages of the brain degeneration associated with Alzheimer's ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.