Key result
Machine learning outperforms cardiologists with ~73% accuracy in predicting CTO antegrade wiring success.
Why the study?
Does a machine learning model improve the accuracy of predicting primary antegrade wiring success in CTO PCI compared to interventional cardiologists?
Cross-Sectional (n=130)
Does a machine learning model improve the accuracy of predicting primary antegrade wiring success in CTO PCI compared to interventional cardiologists?
Answers are grounded in this paper and cite their sources.
A machine learning model demonstrated higher accuracy than interventional cardiologists in predicting primary antegrade wiring success for CTO PCI, suggesting potential utility in procedural planning.
Background: Incorporating artificial intelligence (AI)-based clinical decision support in the cardiac catheterization laboratory could revolutionize percutaneous coronary intervention (PCI) and interventional cardiology. Research Questions: To compare predictions for successful primary antegrade wiring (AW) of chronic total occlusion (CTO) lesions made by interventional cardiologists (ICs) with those from a machine learning model. Methods: We conducted a survey to assess the estimates of ICs regarding primary AW crossing success, on a scale of 0-100%, for 15 CTO PCIs. For the AI based prediction we used a machine learning model with an area under the curve of 0.780. The primary endpoint was the difference between AI-generated and human estimates. Results: A total of 130 ICs participated in the survey. Mean participant age was 51.7±10.6 years. The median difference between the AI and the human prediction was <20% for 7 cases; 20-30% for 6 cases; >30% for 2 cases. Successful AW-based crossing by an experienced CTO operator was observed in 8/15 cases. The operator predictions aligned with the real-life outcomes in 9/15 cases (60.0%), while AI correctly predicted the success/failure of primary AW CTO crossing in 11/15 cases (73.3%). Operators with more experience (>20 CTO PCIs annually) predicted higher success than less experienced operators for 5 cases. Operators who train dedicated advanced fellows predicted higher success for 6 cases and showed worse alignment with the AI prediction for 4 cases. Conclusions: Our study shows that, compared with physician’s estimations, a machine learning model could improve the accuracy of predictions for primary AW success and assist CTO PCI planning.
No takes yet. Share an insight, caveat, or question.
Alexandrou et al. (2024) conducted a cross-sectional in Chronic total occlusion (CTO) (n=130). Machine learning model vs. Interventional cardiologists was evaluated on Difference between AI-generated and human estimates. A machine learning model correctly predicted primary antegrade wiring success in 73.3% of chronic total occlusion cases, compared to 60.0% for interventional cardiologists.
Synapse has enriched 10 related papers. Consider them for comparative context: