AI helps predict whether antidepressants will work for patients

AI helps predict whether antidepressants will work for patients

This article has been reviewed in accordance with Science

Fact check

Peer-reviewed publication


Credit: Pixabay/CC0 Public Domain

× Close

Credit: Pixabay/CC0 Public Domain

For patients with major depressive disorder, it is now possible to predict within a week whether an antidepressant will work or not thanks to the use of artificial intelligence (AI). With the help of an artificial intelligence algorithm, brain scans and an individual’s clinical information, researchers from the University of Amsterdam UMC and Radpodomc were able to find out whether the drug would work or not up to 8 weeks faster. The results of this study are published today in American Journal of Psychiatry.

“This is important news for patients. Usually, it takes 6 to 8 weeks before we know whether an antidepressant will work or not,” says Lisbeth Rennemann, professor of neuroradiology at the Medical University of Amsterdam.

The research team analyzed whether they could predict the effect of the antidepressant sertraline, one of the most commonly prescribed medications in the United States and Europe. In a previous study conducted in the United States, MRI scans and clinical data were performed on 229 patients with major depression before and after a week of treatment with sertraline or placebo. The researchers in Amsterdam then developed and applied an algorithm to this data to see if they could predict treatment response to sertraline.

This analysis showed that one-third of patients respond to the drug and two-thirds do not. “In this way, we can actually prevent two-thirds of the number of ‘wrong’ prescriptions for sertraline and thus provide better care for the patient. Because the drug also has side effects,” says Renemann.

The right medication, much faster

“The algorithm suggested that blood flow in the anterior cingulate cortex, an area of ​​the brain involved in regulating emotions, would predict the effectiveness of the drug. In the second measurement, a week after the start, the severity of symptoms changed. “In order to be additional predictive,” says Eric Ruhe. , the psychiatrist of Radboudumc.

In the future, this new method may help better tailor sertraline treatment to each individual patient. Currently, there is no accurate prediction tool. The patient is given the drug and after 6 to 8 weeks – in practice often up to several months – the effectiveness of the drug is verified.

If the symptoms do not subside, the patient is given another antidepressant, and this process may be repeated several times. This standard method often takes weeks, if not months. It also saves society’s costs, because as long as the patient continues to suffer from serious depressive symptoms, he or she cannot fully participate in society.

In one out of every three depressed patients, there is still no improvement in symptoms after several treatment steps. Therefore, there is an urgent need to find a solution that allows faster determination of the effectiveness of antidepressants in cases of major depression. In the coming period, researchers will improve the algorithm by adding additional information.

more information:
Predicting response to treatment in major depressive disorder using multimodal MRI and clinical data: secondary analysis of a randomized clinical trial, American Journal of Psychiatry (2024).

Magazine information:
American Journal of Psychiatry

Provided by the University Medical Center Amsterdam

You may also like...

Leave a Reply