A deep learning AI model based on mammographic features can predict cardiovascular risk in women with accuracy comparable to traditional risk scores.
Key Details
- 1Researchers from the George Institute for Global Health developed a deep-learning algorithm using mammogram images and patient age.
- 2The model was trained on 49,196 women with a median follow-up of 8.8 years, 3,392 of whom experienced a major cardiovascular event.
- 3The AI algorithm (DeepSurv) achieved a concordance index of 0.72; traditional risk models range from 0.73 to 0.79.
- 4Combining mammogram radiomics with clinical data increased the concordance index to 0.75.
- 5The model is designed for integration into routine breast cancer screening to provide additional cardiovascular risk information.
Why It Matters
This work demonstrates the potential for mammography-based AI to serve as a dual-purpose screening tool, improving both cancer and cardiovascular disease prevention in women by leveraging existing imaging data. If implemented, it could enhance patient care without adding screening burden or workload.
Source
AuntMinnie
Related News
•HealthExec
New Report Highlights Clinical AI Performance, Sustainability, and Adoption Challenges
A multi-institutional review details key challenges, progress, and sustainability concerns in deploying clinical AI in real-world healthcare settings.
•AuntMinnie
LLM Boosts Terminology Expansion in Radiology Reports Over RadLex
A large language model (LLM) significantly outperforms RadLex in expanding terms for radiology report language standardization.
•Radiology Business
Google Releases MedGemma 1.5 and MedASR AI Models for Medical Imaging
Google has launched MedGemma 1.5 and MedASR, two new open-access AI models tailored for healthcare and medical imaging use cases.