Andrea Cipriani, MD, PhD, from the University of Oxford.

Andrea Cipriani, MD, PhD

PETRUSHKA Tool Improves Antidepressant Persistence in MDD, With Andrea Cipriani, MD, PhD

A recent study found that the PETRUSHKA decision-support tool improved antidepressant treatment persistence in 

. In an accompanying interview, Andrea Cipriani, MD, PhD, professor of psychiatry at the University of Oxford, emphasized its potential to extend personalized treatment into primary care and other nonpsychiatric settings through structured, shared decision-making.

“If you don't have a psychiatric or specific knowledge in the field, like family doctors or other specialties—neurology, cardiology, oncology, whatever—using the tool is much better than the clinical judgment of the known specialist.” Cipriani told 

Antidepressant selection in routine care often reflects clinician familiarity rather than individualized prediction, particularly in primary care where most prescriptions originate. This pattern has limited implementation of guideline-recommended personalization strategies, despite longstanding recognition of heterogeneity in treatment response and tolerability.

The PETRUSHKA platform generates a ranked list of antidepressants using routinely collected clinical and demographic variables, including symptom severity, comorbidities, and prior treatment history, combined with patient preferences regarding adverse effects. This approach supports a 2-fold strategy of broadening pharmacologic consideration while actively incorporating patient priorities into treatment selection.

The multicenter PETRUSHKA randomized clinical trial enrolled 540 adults with MDD across 47 sites in Brazil, Canada, and the UK.¹ Participants were randomized 1:1 to a web-based decision-support system or usual care. The primary endpoint, all-cause treatment discontinuation at 8 weeks, occurred in 17% (41/241) of the PETRUSHKA group versus 27% (69/252) under usual care (adjusted relative risk, 0.62; 95% CI, 0.44-0.88; 

 =.007). This absolute difference of approximately 10 percentage points reflects a clinically relevant improvement in early treatment persistence.

Secondary outcomes further supported clinical benefit at 24 weeks. Mean PHQ-9 scores were 7.1 (SD, 5.4) in the PETRUSHKA group versus 9.2 (SD, 6.5) in usual care (adjusted mean difference, −1.92; 95% CI, −3.06 to −0.78; 

 <.001). Anxiety symptoms improved similarly, with GAD-7 scores of 4.6 versus 5.8 (adjusted mean difference, −1.39; 95% CI, −2.26 to −0.52; 

 =.002). These findings suggest downstream clinical benefit associated with improved early treatment matching and persistence.

Treatment discontinuation due to adverse events at 8 weeks occurred in 9% (n = 22) of the PETRUSHKA group compared with 16% (n = 39 in usual care (adjusted relative risk, 0.59; 95% CI, 0.36-0.97; 

 =.04). No new safety signals were identified, and serious adverse events were not attributed to the intervention or selected treatments.

Cipriani emphasized the broader significance of these findings in a field constrained by limited biomarkers. He noted the tool demonstrates meaningful gains using routinely available clinical and demographic inputs, improving prediction without reliance on advanced biological markers. He added that future development efforts aim to integrate additional data layers, including genetic and imaging information, to further refine treatment selection.

The study reinforces a shift toward shared decision-making in mental health care. The PETRUSHKA tool facilitates real-time collaboration between clinician and patient, incorporating individual preferences related to tolerability into final treatment selection. Cipriani described this as a move away from clinician-centered prescribing toward a more collaborative model, with particular relevance in primary care, neurology, cardiology, and oncology settings.

Limitations include the open-label design and missing data for some secondary outcomes, which may affect interpretability. In addition, findings may not fully generalize to specialty psychiatric settings, although subgroup analyses suggested greater benefit in primary care environments.

“The big challenge is what we call external validity, so to use the prediction for people that are not included in the building up of the prediction model. That's one word of caution for people not to trust automatically any kind of tool. We need to raise the bar in the level because we need to prove that these tools are effective in delivering what we want,” Cipriani said. “The second thing [that] is crucial is a shared decision-making process.”

Cipriani has no relevant reported disclosures.

Cipriani A, Fernandes KBP, Mulsant BH, et al. A Decision-Support System to Personalize Antidepressant Treatment in Major Depressive Disorder: A Randomized Clinical Trial. 

Videos

Study showed the PETRUSHKA decision-support tool reduced antidepressant discontinuation, supporting personalized treatment approaches.

PETRUSHKA Tool Improves Antidepressant Continuation, With Andrea Cipriani, MD, PhD

A digital decision-support tool that integrates predictive modeling with patient preference data improved antidepressant continuation and longer-term symptom outcomes in adults with 

, 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 

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; 

 =.007). Discontinuation due to adverse events was also reduced (9% vs 16%; RR, 0.59; 95% CI, 0.36 – 0.97; 

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; 

 <.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; 

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.”

In a randomized trial, PETRUSHKA improved antidepressant continuation and 24-week symptom outcomes by integrating clinical data with patient preferences.

Andrea Cipriani, MD, PhD

Articles