ECG-AuxNet: A Dual-Branch Spatial-Temporal Feature Fusion Framework with Auxiliary Learning for Enhanced Cardiac Disease Diagnosis

Key Result

ECG-AuxNet achieves robust generalizability and clinically aligned interpretability for cardiac disease diagnosis by integrating spatial-temporal features through auxiliary learning.

Key Points

• The aim is to develop a framework that improves cardiac disease diagnosis using spatial-temporal features.
• Utilized dual-branch architecture for feature fusion
• Implemented auxiliary learning to boost prediction accuracy
• Focused on enhancing the model's interpretability for clinical application
• Achieved robust performance in cardiac disease diagnosis
• Demonstrated strong generalizability across different datasets
• Aligned model interpretations with existing clinical expertise