Artificial Intelligence - Based Opportunistic Coronary Artery Calcium Scoring on Routine Chest-CT Scan

Cardiovascular Risk, Coronary Artery Calcification, Coronary Artery Disease, Emergency Care, End-Stage Renal Disease Requiring Haemodialysis

Coronary Artery Calcification, Coronary Artery Disease, Opportunistic Screening, Artificial Intelligence, Deep Learning, Chest CT, Agatston Score, External Validation, Cardiovascular Risk Stratification, Hemodialysis, MACE

This retrospective, non-interventional study externally validates a pre-trained open-weight deep-learning algorithm (Swin-UNETR) for the opportunistic quantification of coronary artery calcium (CAC) on non-gated routine chest CT scans acquired at a German academic center, and evaluates the prognostic value of this automated imaging biomarker for cardiovascular risk stratification. Coronary calcium is an established predictor of cardiovascular risk, but is not routinely quantified on the tens of thousands of non-cardiac chest CTs performed each year. Because existing high-performing AI models were trained almost exclusively on U.S. cohorts, external validation on a European scanner fleet is required to exclude scanner bias (domain shift). The study comprises three linked analytic cohorts: (1) a validation cohort comparing the AI-CAC score against the ECG-gated cardiac CT Agatston reference; (2) a dialysis cohort assessing calcification progression and mortality; and (3) an emergency department cohort assessing short-term cardiovascular events. This is an investigator-initiated trial with no intervention on patients.

The study analyzes a retrospective cohort of routine clinical CT examinations at University Hospital Cologne. Data originate from the hospital information system and Picture Archiving and Communication System (PACS) and are provided in pseudonymized form via the Medical Data Integration Center (MeDIC), acting as an independent trusted third party; the re-identification key remains under the sole control of MeDIC. Deep-learning inference is performed locally on isolated, access-controlled graphics processing unit (GPU) clusters of the institution (privacy by design / zero data retention); an open-weight model (Swin-UNETR) is used. Three research questions are addressed in three analytic cohorts: * Validation (n ≈ 150): diagnostic agreement of the automatically extracted AI-CAC score (from the non-gated CT) with the reference Agatston score from a paired ECG-gated cardiac CT acquired within ≤ 12 months. * Dialysis (n ≈ 300): 150 hemodialysis patients plus 150 matched kidney-healthy controls with serial non-gated CTs; annualized calcification progression rate and all-cause mortality. * Emergency department (n ≈ 1,500): patients \> 50 years with non-gated chest CTs from the Emergency Department (without a primary cardiac focus); occurrence of in-hospital major adverse cardiac event (MACE) or cardiovascular readmission within 12 months. Extracted data include demographics (age at examination, sex), cardiovascular risk factors and comorbidities (ICD-10), long-term medication, laboratory values, examination metadata (date, scanner manufacturer, kilovolt peak (kVp), slice thickness), and outcome data (mortality, cardiovascular events, readmissions). Statistical analysis uses Spearman correlation, Cohen's kappa and Bland-Altman analysis for method comparison; t-test / Mann-Whitney-U for group differences in progression; and Kaplan-Meier (log-rank) plus multivariable Cox proportional-hazards and logistic regression for outcome prediction. Legal basis: § 6 (1) no. 2 Health Data Use Act of Germany (GDNG) in conjunction with Art. 9 (2) (j) and Art. 89 (1) GDPR (research privilege); no individual consent (disproportionate effort, Art. 14 (5) (b) GDPR). The AI (artificial intelligence) model carries no CE-marking and is used strictly as a research tool; AI-CAC scores are not systematically fed back into clinical care.

No related papers found yet.

None listed