Deep Convolutional Neural Networks and Learning ECG Features for Screening Paroxysmal Atrial Fibrillation Patients

By Bahareh Pourbabaee, Mehrsan Javan Roshtkhari, K. Khorasani. IEEE Transactions on Systems, Man & Cybernetics. Systems, 2018

342 citations recorded by the source corpus.

In this paper, a novel computationally intelligent-based electrocardiogram (ECG) signal classification methodology using a deep learning (DL) machine is developed. The focus is on patient screening and identifying patients with paroxysmal atrial fibrillation (PAF), which represents a life threatening cardiac arrhythmia. The proposed approach operates with a large volume of raw ECG time-series data as inputs to a deep convolutional neural networks (CNN). It autonomously learns representative and key features of the PAF to be used by a classification module. The features are therefore learned directly from the large time domain ECG signals by using a CNN with one fully connected layer. The learned features can effectively replace the traditional ad hoc and time-consuming user’s hand-crafted features. Our experimental results verify and validate the effectiveness and capabilities of the learned features for PAF patient screening. The main advantages of our proposed approach are to simplify the feature extraction process corresponding to different cardiac arrhythmias and to remove the need for using a human expert to define appropriate and critical features working with a large time-series data set. The extensive simulations and case studies conducted indicate that combining the learned features with other classifiers will significantly improve the performance of the patient screening system as compared to an end-to-end CNN classifier. The effectiveness and capabilities of our proposed ECG DL classification machine is demonstrated and quantitative comparisons with several conventional machine learning classifiers are also provided.

Subfields: Cardiology and Cardiovascular Medicine, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/84e95ef743988552886cc7e988815651988058d1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Cognitive Neuroscience

Citations in the corpus

A review on deep learning methods for ECG arrhythmia classification (2020, background): “, 2018) l Paroxysmal Atrial Fibrillation (PAF) (Pourbabaee et al., 2017) m Normal Sinus Rhythm (NSR) Ventricular Fibrillation (VFib) Ventricular Tachycardia (VT) (Acharya et al.”
Multi-head CNN-RNN for multi-time series anomaly detection: An industrial case study (2019, neutral): “Unlike other CNN’s for time series classiﬁcation [78, 32, 79], no sub-sampling layer is used after the convolution.”
Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets (2021, methodology): “[46] suggested a five-layered CNN to detect paroxysmal AFib using the PAF Prediction Challenge Database [47].”
Deep learning for healthcare applications based on physiological signals: A review (2018, background): “, 2017 [132] Features for Screening Paroxysmal Atrial Fibrillatio CNN The PAF prediction challenge database [133] Precision=93.”
Deep Learning on 1-D Biosignals: a Taxonomy-based Survey (2018, methodology): “All papers, except one [61], used the publicly available standard ECG databases to evaluate the performance of their proposed methods.”