Predicting cardiovascular events from routine mammograms using machine learning
Authors' conclusion
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.
Study context
- Population
- Women with at least one screening mammogram linked to hospitalisation and death databases (Lifepool cohort)women included
- Participants
- 49,196 womenEvents: 3392
- Predictors
- DeepSurv model using mammography features and participant age
- Predicted outcome
- major cardiovascular events
Model performance
As reported in the abstract
Concordance index
DeepSurv model (mammography features and age)
0.72(95% CI 0.71 to 0.73)
- Median follow-up 8.8 years (IQR 7.7-10.6)
Further findings
Comparison with standard risk prediction models
- Similar performance to modern models containing age and clinical variables including the New Zealand ‘PREDICT’ tool and the American Heart Association ‘PREVENT’ equations
Original publication
Predicting cardiovascular events from routine mammograms using machine learning. Heart. Published 16 September 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →