Key result
AI-CAC model detects coronary calcium on chest X-rays with 0.90 AUC and predicts ASCVD events.
Why the study?
The study aimed to develop a deep-learning-based system to detect subclinical atherosclerosis using plain frontal chest X-rays.
Does a deep-learning algorithm (AI-CAC model) accurately detect subclinical atherosclerosis on chest X-ray compared to chest CT in primary prevention patients?
Observational (n=540)
No
Does a deep-learning algorithm (AI-CAC model) accurately detect subclinical atherosclerosis on chest X-ray compared to chest CT in primary prevention patients?
Effect estimate: AUC 0.90 (95% CI 0.84-0.97)
An AI-based deep learning model can accurately detect coronary artery calcium on routine chest X-rays, providing an opportunistic method for cardiovascular risk stratification.
May support opportunistic CAC detection on chest X-rays; leaves open prospective validation for ASCVD risk stratification in primary prevention.
Aims To develop a deep-learning-based system for recognition of subclinical atherosclerosis on a plain frontal chest X-ray. Methods and results A deep-learning algorithm to predict coronary artery calcium (CAC) score (the AI-CAC model) was developed on 460 chest X-ray (80% training cohort, 20% internal validation cohort) of primary prevention patients [58.4% male, median age 63 (51–74) years] with available paired chest X-ray and chest computed tomography (CT) indicated for any clinical reason and performed within 3 months. The CAC score calculated on chest CT was used as ground truth. The model was validated on a temporally independent validation cohort of 90 patients from the same institution (external validation). The diagnostic accuracy of the AI-CAC model assessed by the area under the curve (AUC) was the primary outcome. Overall, median AI-CAC score was 35 (0–388) and 28.9% patients had no AI-CAC. AUC of the AI-CAC model to identify a CAC >0 was 0.90 (95%CI 0.84–0.97) in the internal validation cohort and 0.77 (95%CI 0.67–0.86) in the external validation cohort. Sensitivity was consistently above 92% in both cohorts. In the overall cohort (n = 540), among patients with AI-CAC = 0, a single ASCVD event occurred, after 4.3 years. Patients with AI-CAC > 0 had significantly higher Kaplan Meier estimates for ASCVD events (13.5% vs. 3.4%, log-rank = 0.013). Conclusion The AI-CAC model seems to accurately detect subclinical atherosclerosis on chest X-ray with high sensitivity, and to predict ASCVD events with high negative predictive value. Adoption of the AI-CAC model to refine CV risk stratification or as an opportunistic screening tool requires prospective evaluation.
No takes yet. Share an insight, caveat, or question.
Gallone et al. (2025) conducted an observational in Subclinical atherosclerosis (n=540). AI-CAC deep-learning model on chest X-ray vs. Chest CT (ground truth) was evaluated on Diagnostic accuracy of the AI-CAC model assessed by the area under the curve (AUC) to identify a CAC >0 (AUC 0.90, 95% CI 0.84-0.97). The AI-CAC deep-learning model accurately detected coronary artery calcium >0 on chest X-rays (AUC 0.90) and predicted higher ASCVD events in patients with AI-CAC >0 (13.5% vs 3.4%; P=0.013).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: