Objective: Recreating the study logic of randomized trials as observational studies. Translating protocols into reproducible cohort definitions, phenotypes, and analyses suitable for a real-world evidence.
Task: Take two trials, deconstruct their protocols, and show how each could be re-emulated using longitudinal patient records. Include phenotype validity, confounding control, and the limits of what observational data can answer.
Deliverables: Slides decks + Presentation
Couturaud, Francis, et al. "Extended treatment of venous thromboembolism with reduced-dose versus full-dose direct oral anticoagulants in patients at high risk of recurrence: a non-inferiority, multicentre, randomised, open-label, blinded endpoint trial." The Lancet 405.10480 (2025): 725-735.
Packer, Milton, et al. "Cardiovascular and renal outcomes with empagliflozin in heart failure." New England Journal of Medicine 383.15 (2020): 1413-1424.
Evidence: Slides, recreated as interactive HTML below