MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

05/27/2019

∙

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 performance and strong interpretability against signal distortion and noise contamination.

READ FULL TEXT

MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

Interpretable ECG classification via a query-based latent space traversal (qLST)

Interpretable Tsetlin Machine-based Premature Ventricular Contraction Identification

Method of diagnosing heart disease based on deep learning ECG signal

Nonlinear and statistical analysis of ECG signals from Arrhythmia affected cardiac system through the EMD process

Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery

HAN-ECG: An Interpretable Atrial Fibrillation Detection Model Using Hierarchical Attention Networks

ASCNet-ECG: Deep Autoencoder based Attention aware Skip Connection network for ECG filtering

MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

Related Research

Interpretable ECG classification via a query-based latent space traversal (qLST)

Interpretable Tsetlin Machine-based Premature Ventricular Contraction Identification

Method of diagnosing heart disease based on deep learning ECG signal

Nonlinear and statistical analysis of ECG signals from Arrhythmia affected cardiac system through the EMD process

Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery

HAN-ECG: An Interpretable Atrial Fibrillation Detection Model Using Hierarchical Attention Networks

ASCNet-ECG: Deep Autoencoder based Attention aware Skip Connection network for ECG filtering