Predicting cardiovascular events from routine mammograms using machine learning
A deep learning algorithm based on only mammographic features and age predicted cardiovascular risk with performance comparable to traditional cardiovascular risk equations. Risk assessments based on mammography may be a novel opportunity for improving cardiovascular risk screening in women.
Authors
- Kirsty Douglas (ORCID: https://orcid.org/0000-0003-0174-782X)
- Anthony Rodgers (ORCID: https://orcid.org/0000-0003-1282-1896)
- Blanca Gallego Luxan (ORCID: https://orcid.org/0000-0002-3704-7975)
- Robert A. Fletcher (ORCID: https://orcid.org/0000-0002-0885-1788)
- Nicholas I-Hsien Kuo (ORCID: https://orcid.org/0000-0001-8749-7280)
- Sebastiano Barbieri (ORCID: https://orcid.org/0000-0002-5919-372X)
- Patrick Brennan (ORCID: https://orcid.org/0000-0001-8611-7258)
- Mark Woodward (ORCID: https://orcid.org/0000-0001-9800-5296)
- Ziba Gandomkar (ORCID: https://orcid.org/0000-0001-6480-3572)
- Clare Arnott (ORCID: https://orcid.org/0000-0001-9370-9913)
- Jennifer Barraclough (ORCID: https://orcid.org/0000-0002-5093-9900)
- Bruce Charles Neal (ORCID: https://orcid.org/0000-0002-0490-7465)
- Louisa Jorm (ORCID: https://orcid.org/0000-0003-0390-661X)
- Katrina Poppe (ORCID: https://orcid.org/0000-0002-4418-4476)
Institutions
- Australian National University (AU)
- The University of Sydney (AU)
- University of Auckland (NZ)
- The University of Queensland (AU)
- The George Institute for Global Health (GB)
- UNSW Sydney (AU)
- The George Institute for Global Health (AU)
- Imperial College London (GB)
Publication Details
- Journal
- Heart
- Published
- 2025-09-16
- DOI
- https://doi.org/10.1136/heartjnl-2025-325705
- Citations
- 4
- Primary Topic
- Cardiovascular Health and Risk Factors
- Type
- article
- Field-Weighted Citation Impact
- 5.55