By Oliver Wilson-
Brain scans that can predict the effect of antidepressants A bio technologist discovered that an AI can predict from people’s brainwaves whether an antidepressant is likely to help them. The technique may offer a new approach to prescribing medicines for mental illnesses.
Researchers at the top Stanford University in California, renowned for their world class research, set out to discover what a machine-learning algorithm could predict from the brain scans of people diagnosed with depression, and who was most likely to respond to treatment with the antidepressant sertraline. Their findings were relatively conclusive. They found that a large percentage of those who will respond well to anti-depressants could be predicted, but not all of them. It goes a fair way to understanding how radically different human minds are.
Antidepressants don’t always work, and we aren’t sure why. “We have a central problem in psychiatry because we characterise diseases by their end point, such as what behaviours they cause,” says Amit Etkin at Stanford University in California. “You tell me you’re depressed, and I don’t know any more than that. I don’t really know what’s going on in the brain and we prescribe medication on very little information.”
Etkin said his mission was to discover if a machine-learning algorithm could predict from the brain scans of people diagnosed with depression who was most likely to respond to treatment with the antidepressant sertraline. The drug is typically effective in only a third of the people who take it.
Etkin and his team gathered electroencephalogram (EEG) recordings showing the brainwaves of 228 people aged between 18 and 65 with depression. All the participants had previously tried antidepressants, but were not on such drugs at the start of the study. About 50% of the participants were given sertraline, while the rest got a placebo. The researchers then monitored the participants’ mood over eight weeks, measuring any changes using a depression rating scale.
Researchers compared the EEG recordings of those who responded well to the drug with those who did not. It led to the machine-learning algorithm to identify a specific pattern of brain activity linked with a higher likelihood of finding sertraline helpful. After testing the algorithm on a different group of 279 people. 41 per cent of overall participants responded well to sertraline, the experiment accurately predicted 76 per cent of those who would benefit.
Etkin has founded a company called Alto Neuroscience to develop the technology. He hopes it results in more efficient sertraline prescription by giving doctors “the tools to make decisions about their patients using objective tests, decisions that they’re currently making by chance”, says Etkin.
This AI “could have potential future relevance to patients with depression”, says Christian Gluud at the Copenhagen Trial Unit in Denmark. But the results need to be replicated by other researchers “before any transfer to clinical practice can be considered”, he says.