What’s New in Psychology?

Artificial Intelligence and the Prediction of Medication Effect

Jim Windell

          The rapid advances in artificial intelligence (AI) development over the past few decades have resulted in AI applications to help those in various fields make better and quicker decisions. This is particularly true in medicine where there is already substantial experience in using AI. And it is especially true in medicine that AI can be rather loosely defined as machines that can accomplish tasks that people would typically accomplish through thinking.

          Actually, when a business writer said that AI is like analytics on steroids, it seems especially apropos to medicine, psychology, and psychiatry. AI cannot make decisions for professionals, but it can help us make better informed decisions.

            One important area related to mental health is making the determination as to whether a treatment approach is working. It may often be critical to the adjustment – sometimes even the life – of a patient to make more rapid decisions in terms of the use of psychiatric medications.

          A research team at Amsterdam UMC, a renowned hospital in the Netherlands, where cutting-edge medicine and top-tier medical research is often carried on, wanted to discover if they could predict the effect of the antidepressant sertraline, usually prescribed as the drug Zoloft. Zoloft is one of the most commonly prescribed drugs in both the U.S. and Europe.

          In a previous study conducted in the U.S., MRI scans and clinical data were administered to 229 patients with major depression before and after a week of treatment with sertraline or a placebo. The Amsterdam researchers then developed and applied an algorithm to this data to investigate whether they could predict the treatment response to sertraline.

          The results, recently published in the American Journal of Psychiatry, showed that one-thirdof patients would respond to the drug, while two-thirds would not respond to it.  

            According to Liesbeth Reneman, one of the researchers and Professor of Neuroradiology at Amsterdam UMC, with the help of an AI algorithm, a brain scan and an individual's clinical information, researchers could see up to eight weeks faster whether or not the medication would work. “This is important news for patients,” Dr. Reneman says. “Normally, it takes six to eight weeks before it is known whether an antidepressant will work.”

            Dr. Reneman went on to say that with this method, they could prevent two-thirds of the number of “erroneous” prescriptions of sertraline and thus offer better quality of care for the patient. She said that this is important “Because the drug also has side effects.”

          Co-researcher Eric Ruhé, a psychiatrist at Radboud University Medical Center, also in the Netherlands, added: “The algorithm suggested that blood flow in the anterior cingulate cortex, the area of brain involved in emotion regulation, would be predictive of the efficacy of the drug. And at the second measurement, a week after the start, the severity of their symptoms turned out to be additionally predictive.”

           The researchers point out that in the future, this new method may help to better tailor sertraline treatment to the individual patient. Currently, there is no exact prediction tool. The patient is usually given the medication and after six to eight weeks – and at times often over the course of several months – it is checked whether the medication works. If the symptoms do not subside, the patient is given another antidepressant, and this process can repeat itself several times. By cutting the time considerably this method employing AI saves society significant costs because as long as the patient continues to suffer from the serious depressive symptoms he or she cannot fully participate in society.

          To read the original article, find it with this reference:

Poirot, M. G., Ruhe, H. G., Mutsaerts, H. J. M., Maximov, I. I., Groote, I. R., Bjørnerud, A., Marquering, H.A., Reneman, L. & Caan, M. W. (2024). Treatment Response Prediction in Major Depressive Disorder Using Multimodal MRI and Clinical Data: Secondary Analysis of a Randomized Clinical Trial. American Journal of Psychiatry,