A randomised screening trial reports what AI-supported mammography actually changes

Assembled from 13 blocks · 1 evidence · 14 related

1. Story
2. Sweden's MASAI trial randomised over 100,000 women between AI-supported single reading and standard double reading. A clinical safety analysis appeared in The Lancet Oncology in 2023; the cancer-detection analysis reported a 29% higher screen-detected cancer detection rate and a 44.2% reduction in screen-reading workload — 48,444 fewer readings — with seven more false positives between the arms; and the full results in The Lancet reported a non-inferior interval-cancer rate, higher sensitivity, unchanged specificity, and fewer interval cancers with unfavourable characteristics. This is the strongest human-consequence evidence in the pack, and it is worth noting how much it cost to obtain: a population-scale randomised trial running for years, in one country, for one modality.
3. Knowledge
4. Machine learning in medical imaging
5. A randomised screening trial reports what AI-supported mammography actually changes
6. Connections
7. Machine learning in medical imaging
8. Deep learning
9. European Union Artificial Intelligence Act
10. Geoffrey Hinton
11. A randomised screening trial reports what AI-supported mammography actually changes
12. Evidence
13. MASAI is a randomised, controlled, non-inferiority, single-blinded, population-based screening trial in Sweden enrolling over 100,000 women. Reported results include a 29% higher screen-detected cancer detection rate with AI support, a 44.2% reduction in screen-reading workload (48,444 fewer readings), false-positive counts of 772 (1.5%) in the intervention arm against 765 (1.4%) in the control arm, and in the full results a non-inferior interval-cancer rate reported as about 12% lower, higher sensitivity, unchanged specificity and fewer interval cancers with unfavourable characteristics. V55 verification basis: none of the three papers was fetched — thelancet.com and sciencedirect.com are blocked to this session. The figures and the trial design were carried in search results attributing them to the named Lancet titles and to institutional press material about them; the publication dates of the final results are reported variously as late 2025 and early 2026 and were NOT resolved, and no DOI is asserted.