Deep Learning CAC from routine Noncardiac CT Scans may predict cardiovascular risk: JACC

USA: Incidental findings of coronary artery calcium (CAC), detected using artificial intelligence (AI) algorithms during non-cardiac computed tomography (CT) scans, are prevalent and associated with an increased risk of death, according to recent research.

The study published in the Journal Of The American College Of Cardiology by Allison W. Peng and colleagues emphasises the importance of recognizing CAC in non-gated chest CT scans, which are often performed for noncardiac reasons, as it could lead to early prevention strategies.

The study examined data from 5,678 adults without known heart disease or metastatic cancer who underwent non-contrast, non-ECG-gated chest CT scans between 2014 and 2019.

The key findings include:

Approximately 52% of participants had CAC greater than zero as detected by an AI-enabled algorithm.

Among those with CAC, 33.4% had a CAC score of 100 or higher.

Individuals with a CAC score of 100 or higher were older, more likely to be male, and had a higher estimated 10-year atherosclerotic cardiovascular disease (ASCVD) risk.

Only 26.1% of patients with CAC levels of at least 100 were taking statins.

Over an average follow-up period of 4.8 years, individuals with a CAC score of 100 or higher had a significantly higher risk of all-cause death, cardiovascular events, and revascularization compared to those with no CAC.

The study underscores the potential of AI to identify incidental CAC during non cardiac CT scans, providing an opportunity for early intervention and preventive therapy. Encouraging radiologists and healthcare providers to recognize and report incidental CAC findings can lead to improved patient care and reduced cardiovascular disease burden.

The authors suggest that automated care pathways managed by pharmacists and advanced practice practitioners could help enhance outcomes for patients with incidental CAC findings. Additionally, there is an opportunity to develop more precise algorithms for quantifying CAC from chest CT scans with lower radiation exposure.

This research highlights the importance of leveraging AI and recognizing incidental findings during routine medical imaging, ultimately contributing to more proactive and effective healthcare strategies.

Reference:

Peng AW, Dudum R, Jain SS, et al. Association of coronary artery calcium detected by routine ungated CT imaging with cardiovascular outcomes. J Am Coll Cardiol. 2023;82:1192-1202.https://www.tctmd.com/news/cac-found-noncardiac-ct-scans-linked-prognosis