Swedish MASAI trial: AI-supported mammography finds more cancer with 44% less reading
By Kristina Lång and colleagues (Lund University, Skåne University Hospital)Built and shared by Kristina Lång and colleagues (Lund University, Skåne University Hospital), not by me. Summarised from the public sources below. Check them before you rely on a number.
- Who
- Kristina Lång and colleagues (Lund University, Skåne University Hospital)
- Category
- Research & science
- Source
- Web
- Dates
- Published Jan 2026 · Found 17 Oct 2026
Lund University ran a randomised trial with about 106,000 women in the Swedish screening programme, comparing AI-supported mammography with standard double reading. AI found 29% more cancers, cut radiologists' reading workload by 44%, and a 2026 Lancet follow-up showed higher sensitivity with no rise in interval cancers.
What they built
AI was used to triage screening exams to single or double reading by radiologists and to mark suspicious areas as detection support. Women were randomly assigned 1:1 to AI-supported screening or standard double reading without AI, and the researchers followed up on interval cancers over two years.
The result
AI-supported screening found 338 cancers vs 262 with standard screening (29% more) and cut the screen-reading workload by 44.2%. Interval cancer rate was non-inferior (1.55 vs 1.76 per 1,000), sensitivity rose to 80.5% from 73.8%, and specificity was unchanged at 98.5%.
Sources
Novo Nordisk cuts clinical study documentation from 10+ weeks to 10 minutes
By Novo Nordisk (Waheed Jowiya, Louise Lind Skov)
Novo Nordisk built NovoScribe, an AI documentation platform that writes regulatory-grade clinical study reports and other trial documents. According to Anthropic's case study, producing clinical study documentation went from more than ten weeks to ten minutes.
GPT-5 supplied the key step in a proof in quantum complexity theory
By Scott Aaronson (UT Austin)
Computer scientist Scott Aaronson says that a central technical step in the proof in his new paper on QMA amplification came from GPT-5 Thinking. It is the first time this has happened in his career.
DTU researcher co-designs AI proteins that protect mice from lethal snake venom
By Timothy Patrick Jenkins (DTU Bioengineering) and David Baker (University of Washington)
Timothy Patrick Jenkins of DTU and David Baker's lab at the University of Washington used deep learning to design new proteins that bind and neutralise cobra toxins. The designed proteins protected mice from lethal doses, which could lead to cheaper and safer antivenoms.
Want this in
your business?
Tell me which case caught your eye. I will tell you straight whether it fits, and what it would take.
Start a conversation →