A team of Oxford researchers are testing an Artificial Intelligence algorithm to help treat depression. The system, known as PETRUSHKA, aims to personalise antidepressant treatment for adults with major depressive disorder.
Data unique to patients such as their age, gender, and symptoms are collected. This information is then used to recommend specific drugs based on previous outcomes for similar patients and preferred side effects.
According to the Oxford University Department of Psychiatry, the two most important factors of the trial are the side effects and perceived efficacy of any prescribed medication. The PETRUSHKA team believes the new system could help choose the right antidepressant for each patient and improve treatment adherence.
Professor Andrea Cipriani, Chief Investigator for PETRUSHKA, said: “We want to treat individuals, not averages. We want to be as precise as possible and identify the best treatment for each patient sooner based on what we know works for patients with similar characteristics.”
The research is funded by the National Institute for Health and Care Research (NIHR). Nyla Haque, the Trial Manager for PETRUSHKA, said: “The study lasts 24 weeks in total but after eight weeks we will see how many participants are still taking the allocated treatment.” Haque explains this measure will tell the PETRUSHKA team how acceptable and well tolerated a treatment is. Haque added: “We will also collect information from the participants about their mood, anxiety, quality of life and any side effects during the entire duration of the trial.”
Nearly nine million people in the UK are prescribed antidepressants every year, but, according to the PETRUSHKA team, approximately four out of five of them stop the treatment after several weeks. According to NIHR, Professor Cipriani said the reason for it is “In real world practice, antidepressants are usually prescribed based on the clinician’s knowledge.”
Cipriani added that of all the antidepressants available, “nine times out of ten, GPs prescribe one of just four antidepressants.” According to him, this means that “patients may not get the treatment that would be most effective or sustainable for them.”
The researchers are now looking for 200 volunteers to join over 500 people who have been used to test PETRUSHKA’s performance. People interested in joining the study must be between the ages of 18 to74 and agree to try antidepressants. After signing up, they will go through a screening process and, if found to fit the program’s requirements, could participate in person or remotely.
