Key result
AI-CAC automated left atrial volumetry predicts 15-year incident AF comparably to expert-measured cardiac MRI.
Why the study?
It was unknown how AI-CAC automated LA volumetry performs compared with expert-measured CMRI LA volume, CHARGE-AF risk score, Agatston score, and BNP for predicting AF.
Does AI-automated left atrial volumetry from non-contrast CAC scans predict incident atrial fibrillation comparably to CMRI in asymptomatic individuals?
Cohort (n=3,552)
Yes
Does AI-automated left atrial volumetry from non-contrast CAC scans predict incident atrial fibrillation comparably to CMRI in asymptomatic individuals?
Absolute Event Rate: 0.807% vs 0.808%
p-value: p=0.60
AI-automated left atrial volumetry from routine non-contrast CAC scans predicts incident atrial fibrillation over 15 years as accurately as gold-standard cardiac MRI, offering a scalable opportunistic screening tool.
May support opportunistic AF screening from routine CAC scans; hypothesis-generating, needs prospective validation before practice change.
Background Applying artificial intelligence to coronary artery calcium computed tomography scan (AI-CAC) provides more actionable information beyond the Agatston coronary artery calcium (CAC) score. We have recently shown that AI-CAC automated left atrial (LA) volumetry enabled prediction of atrial fibrillation (AF) in as early as one year. In this study we evaluated the performance of AI-CAC automated LA volumetry versus LA volume measured by human experts using cardiac magnetic resonance imaging (CMRI) for predicting AF, and compared them with CHARGE-AF risk score, Agatston score, and NT-proBNP (BNP). Methods We used 15-year outcome data from 3552 asymptomatic individuals (52.2% women, ages 45-84 years) who underwent both CAC scans and CMRI in the baseline examination (2000-2002) of the Multi-Ethnic Study of Atherosclerosis (MESA). AI-CAC took on average 21 seconds per scan. CMRI LA volume was previously measured by human experts. Data on BNP, CHARGE-AF risk score and the Agatston score were obtained from MESA. Results Over 15 years follow-up, 562 cases of AF accrued. The ROC AUC for AI-CAC versus CMRI and CHARGE-AF were not significantly different (AUC 0.807, 0.808, 0.800 respectively, p=0.60). The AUC for BNP (0.707) and Agatston score (0.694) were significantly lower than the rest (p<.0001). AI-CAC and CMRI significantly improved the continuous Net Reclassification Index (NRI) for prediction of AF when added to CHARGE-AF risk score (0.28, 0.31), BNP (0.43, 0.32), and Agatston score (0.69, 0.41) respectively (p for all<0.0001). Conclusion AI-CAC automated LA volumetry and CMRI LA volume measured by human experts similarly predicted incident AF over 15 years.
No takes yet. Share an insight, caveat, or question.
Naghavi et al. (2024) conducted a cohort in Atrial Fibrillation (n=3,552). AI-CAC automated left atrial volumetry vs. Cardiac magnetic resonance imaging (CMRI) left atrial volume was evaluated on Prediction of incident atrial fibrillation (ROC AUC) (p=0.60). AI-CAC automated left atrial volumetry predicted incident atrial fibrillation over 15 years comparably to cardiac MRI measured by human experts (AUC 0.807 vs 0.808, p=0.60).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: