MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

TL;DR

MINA introduces a multilevel attention model that integrates medical domain knowledge with ECG data, enhancing interpretability and accuracy in cardiac abnormality diagnosis, and demonstrating robustness against noise.

Contribution

This work presents MINA, a novel multilevel attention network that incorporates medical knowledge into ECG analysis for improved interpretability and performance.

Findings

MINA achieved PR-AUC 0.9436, outperforming baselines by 5.51%.

MINA maintained robustness under signal distortion and noise.

The model provides intuitive explanations aligned with medical knowledge.

Abstract

Electrocardiography (ECG) signals are commonly used to diagnose various cardiac abnormalities. Recently, deep learning models showed initial success on modeling ECG data, however they are mostly black-box, thus lack interpretability needed for clinical usage. In this work, we propose MultIlevel kNowledge-guided Attention networks (MINA) that predict heart diseases from ECG signals with intuitive explanation aligned with medical knowledge. By extracting multilevel (beat-, rhythm- and frequency-level) domain knowledge features separately, MINA combines the medical knowledge and ECG data via a multilevel attention model, making the learned models highly interpretable. Our experiments showed MINA achieved PR-AUC 0.9436 (outperforming the best baseline by 5.51%) in real world ECG dataset. Finally, MINA also demonstrated robust performance and strong interpretability against signal distortion and noise contamination.