Key result
AI detects ~98% of aortic valve calcification on chest CT vs. 16% documented by radiology reports.
Why the study?
The prevalence, burden, and radiology documentation of aortic valve calcification on routine noncontrast chest CT remain uncertain, and artificial intelligence may enable systematic detection.
Does artificial intelligence enable systematic detection of undocumented aortic valve calcification on routine noncontrast, non-ECG-gated chest CT in adults aged ≥50 years compared with manual quantification and routine radiology reporting?
Cohort (n=440)
2 blinded readers
No
Does artificial intelligence enable systematic detection of undocumented aortic valve calcification on routine noncontrast, non-ECG-gated chest CT in adults aged ≥50 years compared with manual quantification and routine radiology reporting?
Aortic valve calcification is present in nearly 40% of routine noncontrast chest CTs in adults ≥50 years but documented in only 15.7% of radiology reports; AI-assisted case finding can identify 98.3% of evaluable cases (89.9% end-to-end sensitivity) to facilitate opportunistic screening.
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“According to Ofir Koren, MD, FACC; Raj R. Makkar, MD, FACC, et al., “AVC was common but infrequently documented on routine chest CT.” They noted that AI detected most cases among evaluable scans and that “prospective studies should assess clinical pathways.””
AVC often goes undocumented on routine chest CT; leaves open whether AI-assisted detection improves clinical outcomes or documentation.
Background Routine noncontrast chest computed tomography (CT) may reveal aortic valve calcification (AVC) outside aortic stenosis evaluation. Its prevalence, burden, and documentation remain uncertain. Artificial intelligence (AI) may enable systematic detection. Objectives The study aims to evaluate AVC prevalence and burden, clinical correlates, radiology documentation, and AI-assisted case finding. Methods This retrospective single-center study screened 511 consecutive noncontrast, non–electrocardiographically gated chest CT examinations in adults aged ≥50 years. After 15 protocol exclusions and 56 software-designated nonevaluable examinations, 440 underwent quantification by 2 blinded readers. AVC was defined as >10 AU using a 130-Hounsfield-unit threshold adjusted for blood-pool attenuation and image noise when needed. Locked HealthAVC V1.0 was a secondary comparator. Results Manual quantification identified AVC in 172 of 440 scans (39.1%; 95% CI: 34.6%-43.7%); 97 of 440 (22.0%) had ≥100 AU. Inter-reader agreement at >10 AU was 99.5% (kappa = 0.990). Age (adjusted OR: 1.92 per 5 years; 95% CI: 1.63-2.26) and male sex (adjusted OR: 2.09; 95% CI: 1.32-3.30) were associated with AVC. Reports documented 27 of 172 positive scans (15.7%; 95% CI: 11.0%-21.9%). AI detected 169 of 172 manually confirmed cases (98.3%) among 440 evaluable scans, including 142 of 145 undocumented cases. Of 496 submitted scans, 56 (11.3%) were nonevaluable. End-to-end sensitivity counting positive rejected scans as missed was 89.9%. Among 86 AI-positive patients with echocardiography, 10 (11.6%) had mild-or-greater aortic stenosis. Conclusions AVC was common but infrequently documented on routine chest CT. AI detected most cases among evaluable scans; 11.3% were nonevaluable, yielding 89.9% end-to-end sensitivity. Prospective studies should assess clinical pathways.
No takes yet. Share an insight, caveat, or question.
Koren et al. (2026) conducted a cohort in Aortic valve calcification (AVC) on routine noncontrast chest CT (n=440). Artificial intelligence (AI) detection (Locked HealthAVC V1.0) vs. Manual quantification by 2 blinded readers (and routine radiology report documentation) was evaluated on Detection of manually confirmed aortic valve calcification (>10 AU) on routine noncontrast chest CT. AI detected 98.3% (169/172) of manually confirmed aortic valve calcification cases on evaluable routine chest CTs (89.9% end-to-end sensitivity), whereas radiology reports documented only 15.7%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: