A new AI algorithm can predict anti-depressant efficacy within a week for patients with major depressive disorder. The algorithm developed by researchers at the Amsterdam University Medical Centre and the Radboudumc can identify and predict which patients will respond well to the SSRI sertraline.
Specifically, this algorithm analyses the blow flow from the anterior cingulate cortex to the brain and other relevant patient information like symptoms. It does this to calculate whether the patient would be a good fit for sertraline. This is a big deal because it can potentially reduce unnecessary prescriptions by spotting non-responders to the medication faster.
“This is important news for patients. Normally, it takes 6 to 8 weeks before it is known whether an antidepressant will work,” Professor of Neuroradiology at Amsterdam UMC Liesbeth Reneman said in a statement.
The hypothesis for the research team was whether it was possible to predict the effects of sertraline. To investigate, 229 patients were given either sertraline or a placebo. These patients were given an MRI scan before and after a week of treatment, and what the researchers did was develop an alogrithm and apply it to this patient data in order to to try and predict how they would react to sertraline.
The resulting AI analysis suggested that only 1/3 of patients would respond to sertraline as a treatment.“With this method, we can already prevent 2/3 of the number of ‘erroneous’ prescriptions of sertraline, thus offering better quality of care for the patient. Because the drug also has side effects,” Reneman added.
“The algorithm suggested that blood flow in the anterior cingulate cortex, the area of the 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,” Radboudumc psychiatrist Eric Ruhé added.