Artificial Intelligence Detection of Aortic Valve Calcification on Routine Noncontrast Chest CT: A Real-World Cohort

Koren, O; Patel, V; Wimpfheimer, O; Kukuev, A; Chu, P; Jain, H; Suruga, K; Shitan, H; Hassid, S; Ng, D; Hofstetter, S; Makkar, RR

doi:10.1016/j.jacadv.2026.103446

Valvular & structural heart disease

Artificial Intelligence Detection of Aortic Valve Calcification on Routine Noncontrast Chest Computed Tomography (CT): A Real-World Cohort

JACC AdvPublished 16 Oct 2026retrospective single-center study

Read the original article ↗PubMed

Cite

Authors' conclusion

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.

Study context

Population: Adults aged ≥50 years undergoing noncontrast, non-electrocardiographically gated chest CT examinationsunderwent quantification by 2 blinded readers, 511 screened, 15 protocol exclusions and 56 software-designated nonevaluable examinations
Participants: 440 adults

Index test or model: Locked HealthAVC V1.0 was a secondary comparator to manual quantification by 2 blinded readers
Manual quantificationn = 440
Target condition: aortic valve calcification (AVC)

Methodological detailsconsecutive, 2 blinded readers

Consecutive
2 blinded readers

Performance

As reported in the abstract

Artificial intelligence (AI) detected manually confirmed cases among 440 evaluable scans

169 of 172

98.3%

AI detected undocumented cases

142 of 145

End-to-end sensitivity counting positive rejected scans as missed

89.9%

Further findings

Associations with aortic valve calcification (AVC)

	← Lower ←→ Higher →	Estimate
Age	0.20.5125	adjusted OR per 5 years 1.92 (95% CI 1.63–2.26)
Male sex	0.20.5125	adjusted OR 2.09 (95% CI 1.32–3.30)
	0.20.5125Ratio (log scale)

AVC prevalence by manual quantification

AVC: 172 of 440 scans (39.1%; 95% CI: 34.6%-43.7%)
≥100 AU: 97 of 440 (22.0%)

Inter-reader agreement at >10 AU

Agreement: 99.5%
Kappa: 0.990

Radiology report documentation of AVC

Reports documented positive scans: 27 of 172 positive scans (15.7%; 95% CI: 11.0%-21.9%)

Mild-or-greater aortic stenosis among AI-positive patients with echocardiography

Among 86 AI-positive patients with echocardiography: 10 (11.6%)

Original publication

Artificial Intelligence Detection of Aortic Valve Calcification on Routine Noncontrast Chest CT: A Real-World Cohort. JACC Adv. Published 16 October 2026. doi:10.1016/j.jacadv.2026.103446

Read the original article ↗

Composed by AI from the published abstract and checked against it. How Briefs are made →