As well as to looking for breast most cancers, synthetic intelligence (AI) utilized in mammography reads could assist to detect widespread cardiovascular illnesses, in keeping with research findings offered on the ESC Congress 2026.
“As a result of mammography is already extensively used, analyzing the identical photographs for cardiovascular info might doubtlessly supply a scalable method with out requiring an extra imaging examination. Mammography additionally reaches many ladies in midlife, an essential interval for recognizing and addressing cardiovascular danger,” said presenting creator Viana Copeland, MBBS, of Chaim Sheba Medical Middle, Tel Aviv College in Ramat Gan, Israel.
Research Strategies
Researchers carried out a retrospective cohort research of girls who had undergone not less than one mammogram between 2011 and 2025 at a tertiary referral heart (n = 29,921).
They developed a deep studying–based mostly algorithm for detecting cardiovascular illnesses from mammography points and explored its diagnostic efficiency for detecting hypertension, ischemic coronary heart illness, and cerebrovascular accident, which have been outlined utilizing diagnoses extracted from digital well being information along with prescriptions, procedural findings, imaging findings, and in-hospital measurements.
“Regardless of being the main explanation for demise in girls worldwide, heart problems is persistently underdiagnosed and undertreated. A typical discovering in our medical heart, and all over the world, is that when girls do search medical assist, their heart problems is already superior. However, many ladies do attend routine breast most cancers screening, even after they have not sought take care of cardiovascular signs. We investigated whether or not AI might assist mammography serve an extra objective on this group—the early detection of heart problems—enabling preventive methods to be carried out,” Dr. Copeland stated.
The mannequin structure consisted of a convolutional neural community that predicted the presence of hypertension, ischemic coronary heart illness, or cerebrovascular accident.
Efficiency of the AI mannequin was examined utilizing space below the curve and receiver working attribute curves for every of the cardiovascular illnesses.
Key Findings
Among the many girls included within the evaluation, 18% had breast most cancers. Sufferers have been adopted for a median of seven.3 years (interquartile vary = 4.0–11.0 years).
The AI mannequin detected hypertension in 16% of girls, ischemic coronary heart illness in 2.5%, and cerebrovascular accident in 2.5%.
The algorithm achieved an space below the curve of 0.79 for hypertension detection, 0.78 for ischemic coronary heart illness detection, and 0.86 for cerebrovascular accident detection.
In sensitivity analyses, outcomes have been constant, however confirmed an improved efficiency for mediolateral indirect views, with areas below the curve enhancing to 0.80 for each hypertension and ischemic coronary heart illness and 0.88 for cerebrovascular accident.
Going ahead, the researchers are planning to enhance the mannequin’s accuracy and cut back the charges of false positives and false negatives. In addition they plan to discover if mammograms might be able to additionally detect different cardiovascular situations.
DISCLOSURES: For full disclosures of the research authors, go to esc365.escardio.org.
