Key result
AI-enabled CT left atrial volumetry outperforms CHARGE-AF and NT-proBNP in predicting 1-year AF with ~0.84 AUC.
Why the study?
Coronary artery calcium scans contain actionable information beyond CAC scores that is not currently reported.
Does AI-enabled left atrial volumetry from non-contrast CAC scans improve the prediction of incident atrial fibrillation compared to the CHARGE-AF Risk Score and NT-proBNP in asymptomatic individuals?
Cohort (n=5,535)
Yes
Does AI-enabled left atrial volumetry from non-contrast CAC scans improve the prediction of incident atrial fibrillation compared to the CHARGE-AF Risk Score and NT-proBNP in asymptomatic individuals?
Absolute Event Rate: 0.836% vs 0.742%
p-value: p=<0.02
AI-enabled left atrial volumetry derived opportunistically from routine non-contrast CAC scans significantly improves the prediction of incident atrial fibrillation compared to traditional risk scores and biomarkers.
May aid AF prediction from routine CAC scans; hypothesis-generating and requires prospective validation before practice change.
Background: Coronary artery calcium (CAC) scans contain actionable information beyond CAC scores that is not currently reported. Methods: We have applied artificial intelligence-enabled automated cardiac chambers volumetry to CAC scans (AI-CAC), taking on average 21 seconds per CAC scan, to 5535 asymptomatic individuals (52.2% women, ages 45-84) that were previously obtained for CAC scoring in the baseline examination (2000-2002) of the Multi-Ethnic Study of Atherosclerosis (MESA). We used the 5-year outcomes data for incident atrial fibrillation (AF) and compared the time-dependent AUC of AI-CAC LA volume with known predictors of AF, the CHARGE-AF Risk Score and NT-proBNP (BNP). The mean follow-up time to an AF event was 2.9±1.4 years. Results: At 1,2,3,4, and 5 years follow-up 36, 77, 123, 182, and 236 cases of AF were identified, respectively. The AUC for AI-CAC LA volume was significantly higher than CHARGE-AF or BNP at year 1 (0.836, 0.742, 0.742), year 2 (0.842, 0.807,0.772), and year 3 (0.811, 0.785, 0.745) (p<0.02), but similar for year 4 (0.785, 0.769, 0.725) and year 5 (0.781, 0.767, 0.734) respectively (p>0.05). AI-CAC LA volume significantly improved the continuous Net Reclassification Index for prediction of AF over years 1-5 when added to CAC score (0.74, 0.49, 0.53, 0.39, 0.44), CHARGE-AF Risk Score (0.60, 0.28, 0.32, 0.19, 0.24), and BNP (0.68, 0.44, 0.42, 0.30, 0.37) respectively (p<0.01). Conclusion: AI-CAC LA volume enabled prediction of AF as early as one year and significantly improved on risk classification of CHARGE-AF Risk Score and BNP.
No takes yet. Share an insight, caveat, or question.
Naghavi et al. (2024) conducted a cohort in Asymptomatic individuals at risk for incident Atrial Fibrillation (n=5,535). AI-enabled automated left atrial volumetry (AI-CAC) vs. CHARGE-AF Risk Score and NT-proBNP was evaluated on Prediction of incident atrial fibrillation at 1 year (AUC) (p=<0.02). AI-enabled left atrial volumetry from cardiac CT scans predicted incident atrial fibrillation with an AUC of 0.836 at 1 year, significantly outperforming the CHARGE-AF Risk Score and NT-proBNP.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: