Tail-AwareNet: An ECG-Based classification network for accessory pathway locations

Key Points

• The research aims to develop and validate a machine learning model for classifying accessory pathway locations using ECG data.
• Developed an ECG-based classification neural network called Tail-AwareNet.
• Analyzed a dataset of ECGs to train and test the model's predictive accuracy.
• Used a performance comparison with traditional classification methods.
• Achieved an accuracy rate of 92% in correctly classifying accessory pathways.
• Demonstrated a statistically significant improvement over previous methods (p=0.004).
• Showed robustness across diverse ECG recordings, indicating broad applicability.