Because of AI, Swedish mammography screening found 29% more cancers with 44% less radiologist reading time, and 12% fewer cancers surfaced between screens.

MASAI, the first RCT of AI in cancer screening (105,934 women; Lancet, Jan 2026), reported interval cancers of 1.55 vs 1.76 per 1,000 with AI-supported reading vs standard double reading, with fewer invasive, T2+, and non-luminal-A interval cancers, on top of earlier results showing higher detection and lower workload at the same specificity.

The trial was designed for non-inferiority; the 12% interval-cancer reduction was not statistically significant (ratio 0.88, 95% CI 0.65–1.18, p=0.41), mortality wasn't measured, and screening took place in 2021–2022.

Compared with

AI-supported single/double reading vs standard double reading, individually randomized

Effect

12% fewer interval cancers (n.s.); 29% more screen-detected cancers; 44% workload reduction (1.55 vs 1.76 interval cancers per 1,000 (0.21 per 1,000 difference))

Reach

105,934 women, Sweden national screening programme

Domain

Medicine · Classic ML

Conflicts

ScreenPoint Medical (Transpara) provided the software and publicized results; academic sponsor Lund University.

What would move the grade

Breast-cancer-specific mortality follow-up, or a replication powered for superiority.

Sources

• primaryLancet 2026;407:505-514 (ScienceDirect) (sciencedirect.com)
• secondaryASCO Post summary with interval cancer rates (ascopost.com)
• secondaryCancer (Wiley) summary (acsjournals.onlinelibrary.wiley.com)

Editor's notes

verify: exact screening enrollment dates from the Lancet methods.

History

• Oct 22, 2026Added.

Cite this entry