Related Experiment Video
Updated: Mar 11, 2026
Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans
Published on: August 28, 2018
Characterization of biomarker profiles in patients with coronary artery disease: A prospective coronary computed
Emiliano Bianchini1, Sara Essa Alsubai2, Foziyah Alqahtani2
1Department of Cardiology, University Hospital and University of Galway, Galway, Ireland; Sharif Cardiovascular Research Group, University of Galway, Galway, Ireland; Discipline of Medical Technologies and Artificial Intelligence, School of Medicine, University of Galway, Galway, Ireland; CURAM, University of Galway, Galway, Ireland.
Insights
Conventional biomarkers like LDL and HDL may miss coronary artery disease (CAD) risks. This study used machine learning to identify high-risk patient groups based on multiple biomarkers, revealing patterns beyond traditional assessments.
Area of Science:
- Cardiovascular Medicine
- Biomarker Discovery
- Machine Learning in Healthcare
Background:
- Conventional lipid biomarkers (LDL, HDL) have limitations in identifying significant coronary artery disease (CAD) risk.
- There is a need for advanced methods to stratify patients based on comprehensive biomarker profiles.
Purpose of the Study:
- To evaluate associations between multiple biomarkers and CAD phenotypes.
- To explore patient clustering using machine learning based on biomarker data.
Main Methods:
- Prospective analysis of 787 primary prevention patients from the ACTION registry.
- Coronary computed tomography angiography (CTA) and simultaneous testing of multiple biomarkers including LDL, HDL, Triglycerides, Apolipoprotein A-1 (ApoA-1), Apolipoprotein B (ApoB), Lipoprotein(a) [Lp(a)], glycated hemoglobin (HbA1c), and high-sensitivity C-reactive protein (hs-CRP).
- Unsupervised machine learning for patient clustering based on biomarker profiles.
Main Results:
- 48.5% of patients had Coronary Artery Calcium (CAC) = 0, with 11% showing coronary plaque.
- Patients with plaque and CAC=0 had higher Lp(a) levels compared to those without plaque, despite similar SCORE2 risk.
- Machine learning identified three distinct biomarker clusters; two clusters showed significantly higher prevalence of severe CAD (CAD-RADS≥3) compared to the favorable cluster.
- High-risk biomarker signatures were independently associated with severe CAD prevalence.
Conclusions:
- Distinct biomarker signatures correlate with varying CAD prevalence and severity, surpassing conventional lipid marker capabilities.
- Lipoprotein(a) [Lp(a)] is crucial for detecting early plaque in patients with no calcification (CAC=0).
- Comprehensive biomarker assessment aids in identifying high-risk subgroups missed by standard evaluations.
Background And Aims:
Conventional biomarkers such as low-density lipoprotein (LDL) and high-density lipoprotein 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.
Methods And Results:
We included 787 patients on primary prevention from the prospective ACTION registry (January 2024 to June 2025). All patients underwent coronary CTA and simultaneous biomarker testing, including LDL, high-density lipoprotein, triglyceride, apolipoprotein A-1, apolipoprotein B, lipoprotein(a) [Lp(a)], glycated hemoglobin (HbA1c), and high-sensitivity C-reactive protein. Of 382 patients (48.5%) with coronary artery calcium = 0, 42 (11%) had coronary plaque. These patients showed higher Lp(a) vs those without plaque (16.5 vs 11.5, P = .030), despite comparable SCORE2 risk (3.5% vs 3.0%, P = .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-Reporting and Data System (RADS) ≥ 3 (9.9%). Cluster 2 and 3, despite their significant intercluster 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 = .001). High-risk biomarker signatures were significantly associated to the prevalence of CAD-RADS ≥ 3, independently from the baseline SCORE2 (adjusted odds ratio 2.25; 95% confidence interval 1.32-3.82).
Conclusions:
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 coronary artery calcium = 0 patients. A comprehensive biomarker evaluation may help identifying high-risk subgroups overlooked by a conventional assessment.
More Related Videos
10:03Coronary Progenitor Cells and Soluble Biomarkers in Cardiovascular Prognosis after Coronary Angioplasty
Published on: January 28, 2020
13:07Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
Published on: January 15, 2022
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:28Imaging Studies for Cardiovascular System V: CT
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:30Coronary Artery Disease III: Clinical Manifestations
01:19Acute Coronary Syndrome II: Pathophysiology and Clinical Manifestations
01:27Coronary Artery Disease V: Interprofessional Care