Comparison of Artificial Intelligence Detection and Short-Term Breast Cancer Risk Models within and beyond Their Intended Use in Mammography Screening

Yao-Kuan Wang, Lesley Cockmartin, Tobias Wagner, Zan Klanecek, Nicholas Marshall, Valerie Celis, Chantal Van Ongeval, Andrej Studen, Robert Jeraj, Hilde Bosmans · 2026

Read Comparison of Artificial Intelligence Detection and Short-Term Breast Cancer Risk Models within and beyond Their Intended Use in Mammography Screening by Yao-Kuan Wang, Lesley Cockmartin, Tobias Wagner, Zan Klanecek, Nicholas Marshall, Valerie Celis, Chantal Van Ongeval, Andrej Studen, Robert Jeraj, Hilde Bosmans (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13620329.txt.

Description

AI tools for mammograms come in two flavors: some flag cancer in the current exam, others estimate the chance of cancer soon after a clear exam. Yao-Kuan Wang and co-authors compared four such models in 2026 on a Swedish screening dataset of more than twenty thousand exams. Each model was tested both in its intended role and in the other one.

One pair of models led on detection with equal top scores, and the detection model also gave the sharpest ruling-out at working sensitivity. For short-term risk, the risk model led, catching about half of interval cancers at a set specificity. The authors conclude that each kind performs best at the job it was built for, a caution for clinics tempted to swap roles.

Catalog record

CREATORYao-Kuan Wang, Lesley Cockmartin, Tobias Wagner, Zan Klanecek, Nicholas Marshall, Valerie Celis, Chantal Van Ongeval, Andrej Studen, Robert Jeraj, Hilde Bosmans
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE38 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13620329

Browse the full library · About the Tower of Babel