Artificial intelligence may soon play a critical role in choosing which depression therapy is best for patients.
Wouldn’t it be great if patients no longer had to suffer the terrible process of pharmaceutical trial and error? A national trial which was set up by UT Southwestern, back in 2011, aimed to gain a deeper understanding as to how mood disorders come about. The ground breaking research, which was published in the journal, Nature Biotechnology: “has produced what scientists are calling the project’s flagship finding: a computer that can accurately predict whether an antidepressant will work based on a patient’s brain activity.”
This very important finding adds to a few other vital studies from the trial, all of which indicate just how beneficial these cutting-edge tech strategies could be for helping countless millions of patients, thereby allowing them to receive an objective diagnosis and prescription for personalized depression treatments. And while it has to be said that putting these approaches into general medical practise will take time: “researchers predict tools such as AI, brain imaging, and blood tests will revolutionize the field of psychiatry in the coming years.”
An End to the Guessing Game
“Antidepressant use in the US has increased nearly 65% over a decade & a half – from 7.7% in 1999-2002 to 12.7% in 2011-2014”
The UT Southwestern psychiatrist, Madhukar Trivedi, M.D., who oversaw the multiple site trial concerning Harvard, Stanford, and other leading institutions, noted: “These studies have been a bigger success than anyone on our team could have imagined. We provided abundant data to show we can move past the guessing game of choosing depression treatments and alter the mindset of how the disease should be diagnosed and treated.”
Trivedi’s main objective, was to confront the disturbing findings from a previous research project he headed. – This showed that, when given their very first antidepressant, as many as two-thirds of patients suffering from depression, do not respond in an adequate fashion. He remarked: “We went into this thinking, wouldn’t it be better to identify at the beginning of treatment which treatments would be best for which patients? It can be devastating for a patient when an antidepressant doesn’t work.”
A New Frontier: EEG-Based Predictions
The research project involved over 300 individuals who were suffering from depression. They were randomly selected, and either given the most common form of antidepressant – a selective serotonin reuptake inhibitor (SSRI), or a placebo. Prior to starting treatment, the scientists used an EEG in order to calculate the level of electrical activity in the subjects’ cortex. Then, the researchers formulated a machine-learning algorithm, so that they could study and utilize the information from the scan, in order to forecast which of the participants would gain from the drug within an eight week period.
The results, which were backed up by three other patient groups, indicated that: Not only did the AI accurately predict outcomes, further research suggested that patients who were doubtful to respond to an antidepressant were likely to improve with other interventions such as psychotherapy or brain stimulation.