Key result
AI-derived chamber volumetry from non-gated chest CTs was noninferior to ECG-gated scans for predicting incident HF and AF (left atrial volume C-index 0.75 vs 0.74; P<0.001 for noninferiority).
Why the study?
Most chest CTs are non-gated, prompting evaluation of whether AI-derived cardiac chamber volumetry from non-gated CTs can reliably predict HF and AF.
Does AI-derived cardiac chamber volumetry from non-gated chest CTs reliably predict incident HF and AF compared to ECG-gated CTs?
Observational (n=7,802)
Yes
Does AI-derived cardiac chamber volumetry from non-gated chest CTs reliably predict incident HF and AF compared to ECG-gated CTs?
Absolute Event Rate: 0.75% vs 0.74%
p-value: p=0.001, non-inferiority p<0.001
AI-based evaluation of non-gated chest CTs provides reliable cardiac chamber volumetry and predicts incident HF and AF comparably to ECG-gated scans, enabling opportunistic screening.
May enable opportunistic AF/HF risk stratification on routine non-gated CTs; leaves open prospective validation before clinical adoption.
Background We previously demonstrated that AI-derived cardiac chamber volumetry in ECG-gated CT scans predicts atrial fibrillation (AF) and heart failure (HF). Since most chest CTs are non-gated, and the American Heart Association recently highlighted their value for opportunistic cardiovascular risk assessment using AI-based coronary artery calcium scoring, we extended this concept to evaluate whether AI-derived chamber volumetry from non-gated CTs can reliably predict HF and AF. Methods We compared AI-derived chamber volumetry from non-gated and ECG-gated chest CTs in 2,053 Multi-Ethnic Study of Atherosclerosis (MESA) Exam 5 participants using mean and standard-deviation of absolute differences, intraclass correlation coefficients (ICC), and Cohen's κ. Variability between paired ECG-gated scans was determined by analyzing scans acquired 2 minutes apart in 5,749 MESA Exam 1 participants. Predictive performance for incident HF and AF was compared using cumulative incidence curves, age- and sex-adjusted C-indices, and non-inferiority testing (δ=0.05). Results Non-gated scans demonstrated excellent overall agreement with ECG-gated scans, with comparable performance for detecting cardiac chamber enlargement (98.8–99.2%, κ=0.76–0.84), relative to agreement observed between paired ECG-gated scans (98.6–98.9%, κ=0.72–0.77). Cumulative incidence curves for HF and AF stratified by quartiles showed substantial overlap. Age- and sex-adjusted C-indices were comparable for left atrial volume (0.75 vs 0.74, p=0.001, non-inferiority p<0.001), ventricular volume (both 0.77, p=0.97, non-inferiority p<0.001), and ventricular ratio (both 0.74, p=0.57, non-inferiority p<0.001) in predicting AF and HF. Conclusion AI-based evaluation of non-gated chest CT may provide reliable cardiac chamber volumetry and cardiovascular outcome prediction, enabling opportunistic screening for HF and AF risk.
No takes yet. Share an insight, caveat, or question.
Mirjalili et al. (2026) conducted an observational in Heart failure and atrial fibrillation (n=7,802). AI-derived cardiac chamber volumetry from non-gated chest CTs vs. ECG-gated chest CTs was evaluated on Age- and sex-adjusted C-indices for predicting incident HF and AF using left atrial volume (p=p=0.001, non-inferiority p<0.001). AI-derived chamber volumetry from non-gated chest CTs was noninferior to ECG-gated scans for predicting incident HF and AF (left atrial volume C-index 0.75 vs 0.74; P<0.001 for noninferiority).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: