Measurements with a miniature camera inside the coronary arteries can accurately predict whether someone will suffer a recurrent heart attack. Until now, interpreting these images was so complex that only specialized laboratories could perform it. A new study from Radboud university medical center shows that AI can reliably take over this analysis and rapidly assess arteries for weak spots.
A heart attack occurs when a coronary artery, which supplies the heart with blood, is blocked by a blood clot. This can occur when atherosclerosis causes artery narrowing, resulting in the heart receiving too little oxygen. Treatment typically involves angioplasty, where a cardiologist widens the artery with a small balloon, usually followed by the placement of a tiny tube, called a stent. In the Netherlands, this procedure is performed about 40,000 times per year.
Predicting recurring events
Nevertheless, about fifteen percent of patients who suffer from a heart attack experience another event within two years. To better identify vulnerable spots within the artery that can trigger new infarctions, technical physician Jos Thannhauser and physician Rick Volleberg of Radboudumc, together with their team, conducted a study. They analyzed the coronary arteries of 438 patients using a miniature camera and specially developed AI, and followed these patients for two years.
The study shows that AI detects vulnerable spots in the arterial wall just as well as specialized laboratories-the international gold standard-and even predicts new infarctions or death within two years more accurately. What does this mean for patients? Volleberg explains: 'If we know who has high-risk plaques and where they are located, we may in the future be able to tailor medication or even place preventive stents.'
Looking inside the artery wall
The miniature camera uses a technique called optical coherence tomography (OCT). Inserted through the arm into the bloodstream, it captures images of arteries using near-infrared light, visualizing the vessel wall at microscopic resolution.
This technique is already used in clinical practice to guide angioplasty and to check whether a stent has been placed correctly. It has been shown that OCT reduces the risk of new infarctions and complications. But in those cases, physicians only look at a very small part of an artery-the site of the infarction. Our study shows that this technique, combined with AI, has much greater potential to map entire vessels."
Jos Thannhauser, Radboudumc
Towards clinical application with AI
'One of the challenges with this technique is that it is extremely difficult for physicians to interpret OCT images', says Thannhauser. That's not surprising-each procedure produces hundreds of images. Even assessing just the stent placement is challenging. Analyzing entire coronary arteries produces far too many images to evaluate manually. 'Currently, only a handful of specialized labs can interpret these images, and even they cannot review everything. Moreover, it's too expensive and labor-intensive to implement this manually in routine clinical care.'
That is why Thannhauser's team developed AI that can analyze all images reliably and much faster than humans. 'AI can already assist physicians during stent placement with OCT', Thannhauser explains. 'Thanks to our AI, we are now a step closer to scanning entire coronary arteries for vulnerable spots in clinical practice. I do expect, however, that it will take a number of years before this becomes reality.'
The CARA Lab
Thannhauser leads the CARA Lab-Cardiology lab with Abbott, Radboudumc and Amsterdam UMC. Together with Niels van Royen (Radboudumc) and Ivana Išgum (Amsterdam UMC), his team received a grant from the Dutch Research Council (NWO). The present study is one of its results.
Volleberg, R. H. J. A., et al. (2025). Artificial intelligence-based identification of thin-cap fibroatheromas and clinical outcomes: the PECTUS-AI study. European Heart Journal. doi.org/10.1093/eurheartj/ehaf595
