Accurate ECG interpretation is vital, yet complex cardiac data and "black-box" AI models limit clinical utility. Inspired by Transformer architectures' success in NLP for understanding sequential data, we frame ECG as the heart's unique "language" of temporal patterns. We present CardioPatternFormer, a novel Transformer-based model for interpretable ECG classification. It employs a sophisticated attention mechanism to precisely identify and classify diverse cardiac patterns, excelling at discerning subtle anomalies and distinguishing multiple co-occurring conditions. This pattern-guided attention provides clear insights by highlighting influential signal regions, effectively allowing the "heart to talk" through transparent interpretations. CardioPatternFormer demonstrates robust performance on challenging ECGs, including complex multi-pathology cases. Its interpretability via attention maps enables clinicians to understand the model's rationale, fostering trust and aiding informed diagnostic decisions. This work offers a powerful, transparent solution for advanced ECG analysis, paving the way for more reliable and clinically actionable AI in cardiology.
View on arXiv@article{uğraş2025_2505.20481,
title={ CardioPatternFormer: Pattern-Guided Attention for Interpretable ECG Classification with Transformer Architecture },
author={ Berat Kutay Uğraş and Ömer Nezih Gerek and İbrahim Talha Saygı },
journal={arXiv preprint arXiv:2505.20481},
year={ 2025 }
}