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.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“The low reporting rate may reflect the fact that most CT scans were performed for unrelated indications, alongside challenges in assessing aortic valve calcification and the lack of clearly defined clinical pathways for incidental findings. AI-based clinical decision support could help address these challenges by providing consistent detection and quantitative assessment, potentially improving the recognition and reporting of AVC in routine practice. At the same time, we need to establish clearer, evidence-based recommendations for further evaluation and follow-up, particularly for patients with high calcium burden or findings suggestive of severe aortic stenosis.”
“Aortic valve sclerosis and calcification are the earliest detectable stage of the AS pathway. Recognizing and reporting it creates a critical opportunity for risk stratification, surveillance and timely intervention.”
“We're trying to standardize the way we treat cardiovascular disease. The goal is early disease detection so appropriate patients can see a cardiologist and begin a surveillance program.”
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.
Journal, society, and media accounts. Useful signal, not independent expert judgment.
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, whereas radiology reports documented only 15.7%.
Synapse has enriched 10 related papers. Consider them for comparative context: