Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Purpose: We aimed to evaluate the diagnostic performance of artificial intelligence (AI) in detecting coronary artery stenosis and calcified plaque on CT angiography (CTA), comparing its diagnostic performance with that of radiologists.
Methods: A thorough search of the literature was performed using PubMed, Web of Science, and Embase, focusing on studies published until October 2024. Studies were included if they evaluated AI models in detecting coronary artery stenosis and calcified plaque on CTA. A bivariate random-effects model was employed to determine combined sensitivity and specificity. Study heterogeneity was assessed using I statistics. The risk of bias was assessed using the revised quality assessment of diagnostic accuracy studies-2 tool, and the evidence level was graded using the Grading of Recommendations Assessment, Development and Evalutiuon (GRADE) system.
Results: Out of 1071 initially identified studies, 17 studies with 5560 patients and images were ultimately included for the final analysis. For coronary artery stenosis ≥50%, AI showed a sensitivity of 0.92 (95% CI: 0.88-0.95), specificity of 0.87 (95% CI: 0.80-0.92), and AUC of 0.96 (95% CI: 0.94-0.97), outperforming radiologists with sensitivity of 0.85 (95% CI: 0.67-0.94), specificity of 0.84 (95% CI: 0.62-0.94), and AUC of 0.91 (95% CI: 0.89-0.93). For stenosis ≥70%, AI achieved a sensitivity of 0.88 (95% CI: 0.70-0.96), specificity of 0.96 (95% CI: 0.90-0.99), and AUC of 0.98 (95% CI: 0.96-0.99). In calcified plaque detection, AI demonstrated a sensitivity of 0.93 (95% CI: 0.84-0.97), specificity of 0.94 (95% CI: 0.88-0.96), and AUC of 0.98 (95% CI: 0.96-0.99)."
Conclusion: AI-based CT demonstrated superior diagnostic performance compared to clinicians in identifying ≥50% stenosis in coronary arteries and showed excellent diagnostic performance in recognizing ≥70% coronary artery stenosis and calcified plaque. However, limitations include retrospective study designs and heterogeneity in CTA technologies. Further external validation through prospective, multicenter trials is required to confirm these findings.
Data Availability Statement: The original findings of this research are included in the article. For additional inquiries, please contact the corresponding authors.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.acra.2025.03.054 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Leveraging GPT-4o for Automated Extraction and Categorization of CAD-RADS Features From Free-Text Coronary CT Angiography Reports: Diagnostic Study.
JMIR Med Inform
September 2025
Departments of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, 600 Tianhe Road, Guangzhou, Guangdong, 510630, China, 86 18922109279, 86 20852523108.
Background: Despite the Coronary Artery Reporting and Data System (CAD-RADS) providing a standardized approach, radiologists continue to favor free-text reports. This preference creates significant challenges for data extraction and analysis in longitudinal studies, potentially limiting large-scale research and quality assessment initiatives.
Objective: To evaluate the ability of the generative pre-trained transformer (GPT)-4o model to convert real-world coronary computed tomography angiography (CCTA) free-text reports into structured data and automatically identify CAD-RADS categories and P categories.
Outcomes of no-touch vs conventionally harvested saphenous veins for coronary artery bypass surgery: A meta-analysis of randomized trials.
Eur J Cardiothorac Surg
September 2025
Department of Cardiothoracic Surgery, Weill Cornell Medicine, New York, NY, USA.
Objectives: The no-touch (NT) technique for saphenous vein (SV) harvesting in coronary artery bypass surgery preserves perivascular tissue and has been proposed to improve vein graft patency compared to conventional (CON) harvesting. However, recent large randomized clinical trials (RCTs) have reported conflicting results. We performed a meta-analysis of all available RCTs comparing graft patency and clinical outcomes between NT-SV and CON-SV harvesting techniques.
View Article and Find Full Text PDFDrug-coated balloon strategy following intravascular lithotripsy to treat coronary de novo lesion: mid-term clinical outcomes of a preliminary experience.
J Invasive Cardiol
September 2025
Department of Cardiology, Centre Hospitalier La Rochelle Ré Aunis, La Rochelle, France.
Objectives: The management of patients with calcified de novo lesions remains a major clinical challenge even in the era of drug-eluting stents (DES). Drug-coated balloon (DCB) therapy has emerged as an alternative to DES to treat de novo lesions. Nevertheless, the management of calcified lesions using intravascular lithotripsy (IVL) combined with DCB to treat de novo lesions has not been investigated.
View Article and Find Full Text PDFRight coronary artery takeoff plane and implications for brachiocephalic interventions and next generation transcatheter aortic valve intervention embolic protection devices.
J Invasive Cardiol
September 2025
Newark Beth Israel Medical Center, Newark, New Jersey.
Objectives: The authors hypothesized that the origin of the right coronary artery (RCA) is a direct continuation of the major aortic arch branches (MAAB) takeoff plane, which may have implications for brachiocephalic interventions and next generation transcatheter aortic valve intervention (TAVI) embolic protection devices (EPDs).
Methods: In this single-center, retrospective, cross-sectional study, the authors analyzed computed tomographic angiography (CTA) images from 92 patients undergoing TAVI evaluation to determine the spatial relationship between the origin of the RCA and the MAAB takeoff plane. Patients with prior cardiothoracic or aortic interventions and those with anomalous RCA origin were excluded.
Predicting the future risk and outcomes of severe heart failure and coronary artery disease with machine learning in the UK Biobank Cohort.
PLoS One
September 2025
Department of Medicine, The Red Rogers Centre for Heart Research, Peter Munk Cardiac Centre, University Health Network, University of Toronto, Toronto, Ontario, Canada.
Background: In order to seriously impact the global burden of heart failure (HF) and coronary artery disease (CAD), identifying at-risk individuals as early as possible is vital. Risk calculator tools in wide clinical use today are informed by traditional statistical methods that have historically yielded only modest prediction accuracy.
Methods: This study uses machine learning algorithms to generate predictions models for the development and progression of severe HF and CAD.