OR WAIT null SECS
PETRUSHKA Tool Improves Antidepressant Continuation, With Andrea Cipriani, MD, PhD
In a randomized trial, PETRUSHKA improved antidepressant continuation and 24-week symptom outcomes by integrating clinical data with patient preferences.
A digital decision-support tool that integrates predictive modeling with patient preference data improved antidepressant continuation and longer-term symptom outcomes in adults with major depressive disorder (MDD), according to findings from a recent multicenter randomized clinical trial.
“The bottom line is that we can personalize treatment, and this means better adherence and clinical improvement for patients,” Andrea Cipriani, MD, PhD, from the University of Oxford, said in an interview with HCPLive.
In the trial, 520 adults with MDD were randomized across 47 sites in Brazil, Canada, and the United Kingdom to receive either usual care or antidepressant selection guided by the PETRUSHKA (Personalizing Antidepressant Treatment for Unipolar Depression Combining Individual Choices, Risks and Big Data) tool. The system uses clinical and demographic variables alongside patient-reported preferences regarding adverse effects to generate individualized antidepressant rankings intended to support shared decision-making.
The PETRUSHKA algorithm produces a ranked list of antidepressants based on predicted efficacy and tolerability using variables such as symptom severity, prior treatment history, comorbid conditions, and demographic factors. This ranking is then modified based on patient preferences related to adverse effects, including sedation, gastrointestinal symptoms, and sexual dysfunction, to support individualized treatment selection during the clinical encounter.
At 8 weeks, all-cause antidepressant discontinuation was significantly lower in the PETRUSHKA group compared with usual care (17% vs 27%; adjusted relative risk [RR], 0.62; 95% CI, 0.44 – 0.88; P =.007). Discontinuation due to adverse events was also reduced (9% vs 16%; RR, 0.59; 95% CI, 0.36 – 0.97; P =.04).
Cipriani noted that this outcome reflects a pragmatic measure of treatment success. Staying on treatment for at least two months is a meaningful indicator that the medication is both tolerated and potentially effective, he said.
No significant differences in depressive or anxiety symptom scores were observed at 8 weeks. However, at 24 weeks, patients in the PETRUSHKA arm demonstrated greater improvement in depressive symptoms measured by the PHQ-9 compared with usual care (mean 7.1 vs 9.2; adjusted mean difference, −1.92; 95% CI, −3.06 to −0.78; P <.001). Anxiety symptoms measured by the GAD-7 were also lower at 24 weeks (mean 4.6 vs 5.8; adjusted mean difference, −1.39; 95% CI, −2.26 to −0.52; P =.002).
Antidepressant selection patterns differed between groups. While PETRUSHKA more frequently recommended mirtazapine, escitalopram, and vortioxetine, usual care more often involved sertraline and citalopram.
The findings suggest potential utility for decision-support tools in primary care and other nonpsychiatric settings where most depression is treated. Cipriani noted that structured systems may help clinicians navigate antidepressant selection more consistently.
An unresolved question is whether improved outcomes are driven primarily by better pharmacologic matching or by enhanced engagement through shared decision-making. Cipriani acknowledged that the study design cannot distinguish between these mechanisms because the trial was open-label.
“We would need a much larger sample size, a different design, like a factorial trial,” he said. “We did not focus on this as the main question for our study, but in the next study that we are currently designing, we will use a double blind design so we will be able to understand whether [shared decision-making] is the active ingredient of the personalization: the asking, eliciting preferences from patients, or a combination of the two.”
Cipriani has no relevant reported disclosures.
References
