Loading…
Loading…
Loading…
Loading…
Loading…
Loading…
Loading…
Loading…
Loading…
Loading…
Loading…
Loading…
- Study: DRAGON, pivotal global Phase 3. - Population: adolescents with Stargardt disease type 1 (STGD1). - Randomization: 2:1 tinlarebant vs placebo; double-masked; placebo-controlled; multi-center. - Duration: 24 months. - Primary endpoint: % reduction (tinlarebant vs placebo) in growth rate of retinal lesions measured as definitely decreased autofluorescence (DDAF) by fundus autofluorescence imaging (study eye), with fellow-eye analysis also reported. - Key secondary endpoint: % reduction in decreased autofluorescence (DAF = DDAF + QDAF) lesion growth (study eye and fellow eye).
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.
Belite Bio reported that the global Phase 3 DRAGON trial met its primary endpoint: tinlarebant reduced study-eye DDAF lesion growth rate by 35.7% versus placebo, with a 33.6% reduction reported in the fellow eye. The company also reported benefit on the key secondary endpoint DAF lesion growth (DAF = DDAF + QDAF): 33.7% reduction in the study eye and 32.7% reduction in the fellow eye. Pharmacodynamically, the 5 mg daily dose reduced RBP4 by a mean of ~80% relative to baseline, and the press release reported four treatment-related discontinuations.
Resolution fingerprint: 72acaa60b6121e9f559c5e90c55405928f699703e9b70fc1c1dda718403b66e4
It asks AI models to forecast the outcome of the DRAGON Phase 3 trial before the readout is public, in Stargardt disease. 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.