- Study: VITESSE (NCT05741476), Phase 3, randomized, double-blind, placebo-controlled. - Population: children age 4–7 years with peanut allergy. - Randomization: 2:1 active (VIASKIN Peanut patch 250 µg) vs placebo. - Duration: 12-month double-blind treatment period, then optional open-label extension. - Primary endpoint: difference in % of treatment responders at Month 12 (active minus placebo). - Responder definition (DBPCFC eliciting dose, ED): - baseline ED ≤ 30 mg and Month-12 ED ≥ 300 mg, OR - baseline ED = 100 mg and Month-12 ED ≥ 600 mg.
How AI models scored forecasting this event. Lower Brier and log loss are better; higher accuracy and quality are better. Skill is the Brier Skill Score versus always predicting the base rate (>0 means the model beats that baseline); accuracy shows its 95% confidence interval and Brier its standard error so you can judge how much data each row rests on. Models are ranked by Brier Skill Score — how decisively each model's probability beat the base rate — with the accuracy interval as the tiebreaker.
This benchmark is open for forecasting. Run a model in the Arena to be among the first results recorded here.
DBV Technologies reported that the pivotal Phase 3 VITESSE trial in peanut-allergic children aged 4–7 years met its primary endpoint at 12 months: responder rates were 46.6% on VIASKIN® Peanut patch vs 14.8% on placebo (difference 31.8%; 95% CI 24.5% to 39.0%), exceeding the prespecified 15% lower-bound threshold. Safety was described as consistent with prior VIASKIN Peanut experience, with discontinuations due to TEAEs of 3.2% (active) vs 0.5% (placebo). The press release reported no treatment-related serious adverse events and treatment-related anaphylaxis of 0.5% (n=2), with both children continuing treatment. Overall compliance was reported as 96.2%.
Resolution fingerprint: 1769cec5c8ec2787e40cb320c10b2f1917bc8cb7a2770149f8fe1ce4a87927c2
It asks AI models to forecast the outcome of the VITESSE Phase 3 trial before the readout is public, in Peanut allergy. Predictions are scored against the verified result using accuracy, Brier score, and log loss.
Yes — this benchmark is resolved. The ground-truth readout and its sources are listed in the Resolution section, and a tamper-evident fingerprint lets anyone verify it was not changed after scoring.
Use the "Cite" button above to copy a citation, or download the frozen JSON snapshot of the recorded predictions. Each benchmark is modeled as a schema.org Dataset for machine citation.