ECG Abnormalities Recognition Using Convolutional Network With Global Skip Connections and Custom Loss Function

The latest trends in clinical care and telemedicine suggest a demand for a reliable automated electrocardiogram (ECG) signal classification methods. In this paper, we present customized deep learning model for ECG classification as a part of the Physionet/CinC Challenge 2020. The method is based on...

Full description

Saved in:
Bibliographic Details
Main Authors: Vicar, Tomas, Hejc, Jakub, Novotna, Petra, Ronzhina, Marina, Janousek, Oto
Format: Conference Proceeding
Language:English
Subjects:
Electrocardiography
Optimization
Pathology
Pattern classification
Reliability
Telemedicine
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The latest trends in clinical care and telemedicine suggest a demand for a reliable automated electrocardiogram (ECG) signal classification methods. In this paper, we present customized deep learning model for ECG classification as a part of the Physionet/CinC Challenge 2020. The method is based on modified ResNet type convolutional neural network and is capable to automatically recognize 24 cardiac abnormalities using 12-lead ECG. We have adopted several preprocessing and learning techniques including custom tailored loss function, dedicated classification layer and Bayesian threshold optimization which have major positive impact on the model performance. At the official phase of the Challenge, our team - BUTTeam - reached a challenge validation score of 0.696, and the full test score of 0.202, placing us 21 out of 40 in the official ranking. This implies that our method performed well on data from the same source (reached first place with validation score), however, it has very poor generalization to data from different sources.
ISSN:2325-887X
DOI:10.22489/CinC.2020.189