Trials have found that people whose antidepressant was selected using the AI tool experienced better mental health outcomes.
An AI-driven tool that tailors antidepressant treatment to individual patients has been shown to improve outcomes for people with depression, compared to standard treatment. It is the first time that a mental health clinical prediction tool has been demonstrated as effective.
The PETRUSHKA tool, developed by the University of Oxford and funded by the National Institute for Health and Care Research (NIHR), supports clinicians and patients to choose the antidepressant that is better tailored to each individual. It uses AI to combine clinical and demographic information with patient preferences, particularly around side effects, to support treatment personalisation and shared decision-making in routine care.
The tool was tested in a large international randomised clinical trial across Brazil, Canada and the UK involving more than 500 adults with major depressive disorder (MDD) and launched in 2024. It found that people whose antidepressant was selected using PETRUSHKA were significantly more likely to continue their treatment and experienced better mental health outcomes compared with usual care up to six months.
“Mental health is lagging behind other fields of medicine, and for too long, antidepressant treatment has relied on trial and error. PETRUSHKA shows that by combining the best available evidence with patients’ own preferences, we can personalise antidepressant treatment from the outset and help more people in the NHS stay on the medication that is right for them,” said NIHR research professor Andrea Cipriani, the lead investigator of the study.
Problems with side effects
Choosing the right antidepressant remains a major challenge in everyday practice, with many people stopping treatment early because of side effects or a lack of perceived benefit. PETRUSHKA was designed to address this by using evidence from clinical trials and real-world data alongside what matters most to patients, helping to identify the most suitable options from the outset.
In the trial, participants using PETRUSHKA were around 40% less likely to discontinue their antidepressant within the first eight weeks of treatment. Fewer people stopped treatment because of adverse effects, and by 24 weeks, those in the PETRUSHKA group also reported greater improvements in depressive and anxiety symptoms.
The tool was co-produced with people with lived experience of depression. It takes three minutes to be administered and is designed to be easy to use in everyday clinical settings, including primary care. Clinicians and patients use PETRUSHKA together during a consultation, either in person or remotely, ensuring that treatment decisions reflect both clinical evidence and individual priorities.
“This study shows the real power of combining digital technology and personalised treatment,” said Mike Lewis, NIHR’s scientific director for innovation.
“By harnessing data and embracing cutting-edge digital tools, we can tailor care more precisely to each patient – improving outcomes for individuals. Forward-thinking research such as this shows the impact of using innovative technologies to ensure patients across the UK receive smarter, more effective care,” he added.
