Characterization of Biomarker Profiles in Patients with Coronary Artery Disease: A Prospective Coronary Computed Tomography Angiography Study.
Authors
Affiliations (8)
Affiliations (8)
- Department of Cardiology, University Hospital and University of Galway, Newcastle Rd, Galway, H91 YR71, Ireland; Sharif Cardiovascular Research Group, University of Galway; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway; CURAM, University of Galway.
- Sharif Cardiovascular Research Group, University of Galway; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway; Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia.
- Department of Cardiology, University Hospital and University of Galway, Newcastle Rd, Galway, H91 YR71, Ireland; Sharif Cardiovascular Research Group, University of Galway; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway; CURAM, University of Galway; Division of Cardiology, Department of Medicine, Verona University Hospital, Piazzale A. Stefani 1, 37126 Verona, Italy; Division of Cardiology, University of Verona, Piazzale A. Stefani 1, 37126 Verona, Italy.
- Sharif Cardiovascular Research Group, University of Galway; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway.
- Sharif Cardiovascular Research Group, University of Galway; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway; II Department of Internal Medicine Therapy: Cardiology, Rheumatology, Hematology and Gastroenterology, Faculty, Trakia University, 6000 Stara Zagora, Bulgaria.
- Sharif Cardiovascular Research Group, University of Galway; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway; CURAM, University of Galway.
- Sharif Cardiovascular Research Group, University of Galway; University of Galway, School of Computer Science, Galway, Ireland; INSIGHT, Research Ireland Centre For Data Analytics, University of Galway, Galway, Ireland.
- Department of Cardiology, University Hospital and University of Galway, Newcastle Rd, Galway, H91 YR71, Ireland; Sharif Cardiovascular Research Group, University of Galway; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway; CURAM, University of Galway. Electronic address: [email protected].
Abstract
Conventional biomarkers such as Low-density Lipoprotein (LDL), and High-density Lipoprotein (HDL) may fail to identify patients' risk for significant coronary artery disease (CAD). This study evaluates the associations between multiple biomarkers and different CAD phenotypes exploring a machine-learning biomarker-based patient clustering. We included 787 patients on primary prevention from the prospective ACTION registry (January 2024-June 2025). All patients underwent coronary CTA and simultaneous biomarker testing including LDL, HDL, Triglyceride, Apolipoprotein A-1(ApoA-1), Apolipoprotein B (ApoB), Lipoprotein(a) [Lp(a)], glycated hemoglobin (HbA1c), and high-sensitivity C reactive protein (hs-CRP). Of 382 patients (48.5%) with CAC=0, 42 (11%) had coronary plaque. These patients showed higher Lp(a) vs. those without plaque (16.5 vs. 11.5, p=0.030), despite comparable SCORE2 risk (3.5% vs. 3.0%, p=0.284). Three biomarker-defined groups were identified after a machine learning unsupervised clustering: Cluster 1 had a favorable lipid profile with the lowest prevalence of CAD-RADS≥3 (9.9%). Cluster 2 and 3, despite their significant inter-cluster differences in terms of Lp(a), LDL and HbA1c levels both showed a significantly higher prevalence of CAD-RADS≥3 compared to cluster 1 (respectively 21.8% and 17.9%; vs. cluster 1 p=0.001). High risk biomarker signatures were significantly associated to the prevalence of CAD-RADs≥3, independently from the baseline SCORE2 (adjusted OR 2.25; 95%CI 1.32-3.82). Distinct biomarker signatures associate with distinct CAD prevalence and severity that conventional lipid markers fail to distinguish. Lp(a) appears relevant for early plaque detection in CAC=0 patients. A comprehensive biomarker evaluation may help identifying high-risk subgroups overlooked by a conventional assessment.