• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

AI Identifies Risk of Fatal Heart Attack 5 Years Before the Event


The technology has the potential to lead to early care and could save lives.

heart attack

Artificial intelligence (AI)-enabled technology can identify patients at high risk of a fatal heart attack at least five years before it happens, according to the findings of a study published in the European Heart Journal.

Researchers used machine learning to develop a biomarker, or fingerprint, called the fat radiomic profile, that detects red flags in the perivascular space lining blood vessels. The fingerprint identifies inflammation, scarring and changes to blood vessels, which all point to future heart attack, according to the researchers.

“By harnessing the power of AI, we’ve developed a fingerprint to find ‘bad’ characteristics around people’s arteries,” said Charalambos Antoniades, M.D., Ph.D., professor of cardiovascular medicine at the University of Oxford. “This has huge potential to detect the early signs of disease and to be able to take all preventive steps before a heart attack strikes, ultimately saving lives.”

Researchers developed the technology to predict cardiac risk by analyzing the radiomic profile of coronary perivascular adipose tissue developed and validated in patient cohorts from three different studies.

In the first study, the research team used fat biopsies from 167 patients undergoing cardiac surgery. The investigators analyzed the gene expressions linked with inflammation, scarring and new blood vessel formation. The expressions were matched to coronary CT angiography scan images to determine the features that best indicate changes to the fat surrounding the heart vessels.

Researchers then compared the coronary CT angiography scans of 101 patients who had a heart attack or cardiovascular death within five years of having a scan to matched controls who did not.

Using machine learning, the investigators developed the fat radiomic profile fingerprint to capture the risk level. The more scans added, the more accurate the predictions, the study authors noted.

The research team tested the fingerprint in 1,575 participants in the SCOT-HEART trial where it predicted major adverse cardiac events beyond traditional clinical practice, the researchers reported.

“The new ‘fingerprint’ extracts additional information about underlying biology from scans used routinely to detect narrowed arteries,” said Metin Avkiran, Ph.D., associate medical director at the British Heart Foundation. “Such AI-based technology to predict an impending heart attack with greater precision could represent a big step forward in personalized care for people with suspected coronary artery disease.”

The technology has the potential to revolutionize how providers identify people at risk of a heart attack, Avkiran added.

The findings of the study are being presented at the European Society of Cardiology Congress.

Get the best insights in digital health directly to your inbox.


AI Models ID Advanced Depression

The Hype and the Upside of AI in Healthcare: A Conversation

Using Supercomputers and Machine Learning to Discover Defective Amino Acids that Cause Diseases

Recent Videos
Image: Ron Southwick, Chief Healthcare Executive
George Van Antwerp, MBA
Edmondo Robinson, MD
Craig Newman
Related Content
© 2024 MJH Life Sciences

All rights reserved.