DistantNews
Support us
๐Ÿ‡ฆ๐Ÿ‡น Austria /Health & Science

Mammograms could detect heart disease in women, Israeli study suggests

From Die Presse · () German

Translated from German and summarized by DistantNews. Read the original for the full story.

At a glance

News Sources not specified New plan
  • Israeli scientists have developed an AI-based system that uses mammograms to help detect cardiovascular diseases in women.
  • Cardiovascular diseases are the leading cause of death for women, yet often underdiagnosed and undertreated.
  • The study, presented at the European Cardiology Congress, showed promising results in identifying hypertension, ischemic heart disease, and stroke risk from mammography data.

Cardiovascular diseases remain the leading cause of death for women worldwide, yet they are frequently underdiagnosed and undertreated. Viana Copeland from the Chaim Sheba Medical Center in Tel Aviv highlighted this critical gap, noting that by the time women seek medical help for heart conditions, the disease is often advanced. This situation, coupled with the regularity of breast cancer screenings through mammography, has spurred research into a potential dual benefit of the imaging technology.

Israeli scientists have now developed an artificial intelligence (AI)-based system that analyzes mammography data to identify signs of cardiovascular disease. The study, presented at the European Cardiology Congress in Munich, involved a re-analysis of data from nearly 30,000 women who had undergone over 97,000 mammograms. The participants had an average age of 54.

Although cardiovascular diseases are the most common cause of death for women worldwide, women are constantly underdiagnosed and undertreated for these diseases.

โ€” Viana CopelandExplaining the problem of underdiagnosis and undertreatment of heart disease in women.

Researchers collected clinical information on three common cardiovascular conditions: hypertension, ischemic heart disease (coronary artery disease), and stroke. They then trained a deep-learning model to identify women with these conditions based on features within their mammograms. The model achieved promising results, with AUROC (Area Under the Receiver Operating Characteristic curve) values indicating its predictive accuracy.

The AI model demonstrated strong performance, achieving an AUROC of 0.79 for hypertension, 0.78 for coronary artery disease, and 0.86 for a history of stroke. These figures suggest that mammography, when analyzed with AI, could serve as a valuable tool for the early detection of heart disease in women who are already undergoing screening for breast cancer. This could pave the way for earlier preventive strategies and improved health outcomes.

A common finding in our medical center and worldwide is that cardiovascular disease is already advanced when women seek medical help. On the other hand, many women regularly participate in breast cancer screening. We investigated whether mammography, with the help of Artificial Intelligence, could serve an additional purpose in this group - the early detection of cardiovascular diseases. This could enable preventive strategies.

โ€” Viana CopelandDescribing the rationale behind using mammography for heart disease detection.
About this summary

Originally published by Die Presse in German. Translated, summarized, and contextualized automatically by DistantNews, with a note on how the source frames the story. Not individually reviewed before publishing. How this works.