Abstract 4141370: Artificial Intelligence for Predicting Primary Antegrade Wiring Success of Chronic Total Occlusion Crossing

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.