Oxford University's Department of Psychiatry is trialing an AI-driven digital tool named 'Petrushka' to personalize antidepressant treatment for individuals suffering from depression. The tool leverages data from over one million individuals to provide real-time recommendations on the most suitable antidepressants for each patient during consultations. The study, funded by the National Institute for Health and Care Research, is also being conducted in Canada and Brazil.
The clinical trial aims to recruit approximately 200 participants by the summer, with a total of over 500 participants expected across all locations. Petrushka considers various patient-specific factors, including age, gender, and symptom severity, alongside potential side effects, to tailor treatment recommendations. Trial manager Nyla Haque noted that the study will last 24 weeks, with acceptability and tolerability of the treatment being assessed after eight weeks. Data on mood, anxiety, quality of life, and side effects will be collected throughout the trial duration.
Personalizing Treatment for Better Outcomes
Chief investigator Prof Andrea Cipriani emphasized the need to move away from a one-size-fits-all approach to antidepressant prescriptions. "In real-world practice, antidepressants are usually prescribed based on the clinician’s knowledge," he stated. He further explained that despite the availability of over 30 antidepressants, general practitioners often prescribe one of only four, potentially leading to suboptimal treatment outcomes for many patients. "We want to treat individuals, not averages," Prof Cipriani added, highlighting the goal of identifying the most effective treatment for each patient sooner by considering characteristics similar to those of patients who have responded well to specific treatments.
Empowering Patients and Improving Decision-Making
The researchers believe that Petrushka represents an "innovative way to empower patients and share decision-making during the treatment process." By providing clinicians with data-driven insights, the tool aims to reduce the time spent on less effective treatments. Patients can self-enroll in the trial and will undergo a brief screening process to determine eligibility.
