Evaluation of Deep Learning Models for LBBB Classification in ECG Signals

TL;DR

This paper evaluates various deep learning models to classify ECG signals into healthy, LBBB, and sLBBB categories, aiming to improve clinical decision-making for cardiac therapy.

Contribution

It compares neural network architectures for ECG classification, highlighting their effectiveness in extracting spatial and temporal features for LBBB detection.

Findings

Deep learning models achieve high accuracy in LBBB classification.

Certain architectures outperform traditional methods.

Potential to enhance patient selection for CRT.

Abstract

This study explores different neural network architectures to evaluate their ability to extract spatial and temporal patterns from electrocardiographic (ECG) signals and classify them into three groups: healthy subjects, Left Bundle Branch Block (LBBB), and Strict Left Bundle Branch Block (sLBBB). Clinical Relevance, Innovative technologies enable the selection of candidates for Cardiac Resynchronization Therapy (CRT) by optimizing the classification of subjects with Left Bundle Branch Block (LBBB).