AI model detects cardiovascular risks using routine mammograms

artificial intelligence mammography cardiovascular disease breast cancer screening deep learning

Researchers from Chaim Sheba Medical Center and Tel Aviv University have developed a deep learning model capable of identifying cardiovascular disease risks through routine mammograms. Presented at the European Society of Cardiology Congress in Munich, the study suggests that mammography could serve a dual purpose: screening for breast cancer and providing early warnings for cardiovascular issues.

The retrospective study analyzed 97,364 mammograms from 29,921 women, with a median age of 54. The AI model demonstrated significant accuracy in identifying key conditions: 86% for stroke, 79% for hypertension, and 78% for coronary heart disease. These results remained consistent regardless of the patient's age or existing cancer diagnosis.

Additionally, separate research findings indicated that AI could potentially identify subtle signs of breast cancer up to six years before a clinical diagnosis. By leveraging existing screening infrastructure, this technology offers a scalable approach to early detection without requiring additional imaging or radiation exposure.

Entities

Chaim Sheba Medical Center · European Society of Cardiology · Munich · Panteleis Yalias · Radiological Society of North America · Tel Aviv University · Viana Copeland

Claims

What the coverage asserts, and how many sources carry each claim.

[● 12 SOURCES] Researchers at Chaim Sheba Medical Center and Tel Aviv University developed a deep learning model to identify cardiovascular risks from mammograms. www.comcantabria.es · www.gesund.at · www.hospimedica.com · www.diepresse.com · www.lifo.gr · +7 more
[● 2 SOURCES] The study found that AI could also identify breast cancer signs up to six years before clinical diagnosis. www.evimaserres.gr
[● 12 SOURCES] The research was presented at the European Society of Cardiology (ESC) Congress in Munich. www.comcantabria.es · www.gesund.at · www.hospimedica.com · www.diepresse.com · www.lifo.gr · +7 more
[● 12 SOURCES] The AI model achieved 79% accuracy for high blood pressure and 78% for coronary heart disease. www.comcantabria.es · www.gesund.at · www.hospimedica.com · www.diepresse.com · www.lifo.gr · +7 more
[● 12 SOURCES] The study analyzed 97,364 mammograms from 29,921 women with a median age of 54. www.comcantabria.es · www.gesund.at · www.hospimedica.com · www.diepresse.com · www.lifo.gr · +7 more
[● 12 SOURCES] The study results were consistent regardless of a woman's age or whether she had been diagnosed with cancer. www.comcantabria.es · www.gesund.at · www.hospimedica.com · www.diepresse.com · www.lifo.gr · +7 more
[● 12 SOURCES] The AI model achieved 86% accuracy in identifying women who had experienced a stroke. www.comcantabria.es · www.gesund.at · www.hospimedica.com · www.diepresse.com · www.lifo.gr · +7 more