ScreenTrustCAD

Artificial intelligence for breast cancer detection in screening mammography in Sweden: a prospective, population-based, paired-reader, non-inferiority study

Patient / Population Intervention / Exposition Vergleich Endpunkt

In 55,581 women aged 40–74 years in population-based screening at one Stockholm hospital, double reading by one radiologist plus AI was non-inferior to standard double reading by two radiologists for screen-detected breast cancer within 3 months.

N
55.581
Design
Prospective paired-reader non-inferiority study (non-randomised), Sweden
Endpunkt
Screen-detected breast cancer within 3 months of mammography (non-inferiority margin: 0.15 relative reduction)
Relevanz
3
ErgebnisCancers detected 261 (0.5%) vs 250 (0.4%) (relative proportion 1.04, 95% CI 1.00–1.09; non-inferior). AI alone 246 vs 250 (0.98, 95% CI 0.93–1.04) and triple reading by two radiologists plus AI 269 vs 250 (1.08, 95% CI 1.04–1.11) were also non-inferior.
Dembrower K, et al. Lancet Digit Health. 2023;5(10):e703-e711. 10.1016/S2589-7500(23)00153-X
Diskussion & Kritik

First prospective evidence that AI can replace one of two radiologists without losing cancers — the radiologist-plus-AI reading model that MASAI then tested in a randomised design. Paired-reader design means every woman was read both ways, so there is no randomisation; a single hospital, partly industry-funded, and an outcome limited to screen-detected cancer at 3 months — interval cancers and overdiagnosis are unmeasured.