ECG Heartbeat Classification: A Deep Transferable Representation (2018-04-19T00:00:00.000000Z)

TL;DR

A method based on deep convolutional neural networks for the classification of heartbeats which is able to accurately classify five different arrhythmias in accordance with the AAMI EC57 standard is proposed.

Abstract

Electrocardiogram (ECG) can be reliably used as a measure to monitor the functionality of the cardiovascular system. Recently, there has been a great attention towards accurate categorization of heartbeats. While there are many commonalities between different ECG conditions, the focus of most studies has been classifying a set of conditions on a dataset annotated for that task rather than learning and employing a transferable knowledge between different tasks. In this paper, we propose a method based on deep convolutional neural networks for the classification of heartbeats which is able to accurately classify five different arrhythmias in accordance with the AAMI EC57 standard. Furthermore, we suggest a method for transferring the knowledge acquired on this task to the myocardial infarction (MI) classification task. We evaluated the proposed method on PhysionNet's MIT-BIH and PTB Diagnostics datasets. According to the results, the suggested method is able to make predictions with the average accuracies of 93.4% and 95.9% on arrhythmia classification and MI classification, respectively.

Authors

Mohammad Kachuee

1 papers

Shayan Fazeli

1 papers

M. Sarrafzadeh

1 papers

TL;DR

Abstract

Authors

References37 items

Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals

A deep convolutional neural network model to classify heartbeats

Nonlinear Cuffless Blood Pressure Estimation of Healthy Subjects Using Pulse Transit Time and Arrival Time

Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks

Non-invasive blood pressure estimation using phonocardiogram

Classification of normal and abnormal ECG records using lead convolutional neural network and rule inference

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Cuffless Blood Pressure Estimation Algorithms for Continuous Health-Care Monitoring

Personalized Risk Scoring for Critical Care Prognosis Using Mixtures of Gaussian Processes

ECG Classification Using Wavelet Packet Entropy and Random Forests

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks

Deep Residual Learning for Image Recognition

A novel electrocardiogram parameterization algorithm and its application in myocardial infarction detection

Prediction of acute myocardial infarction with artificial neural networks in patients with nondiagnostic electrocardiogram

Multiscale Energy and Eigenspace Approach to Detection and Localization of Myocardial Infarction

Adam: A Method for Stochastic Optimization

A New Pattern Recognition Method for Detection and Localization of Myocardial Infarction Using T-Wave Integral and Total Integral as Extracted Features from One Cycle of ECG Signal

Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks

Application of Higher Order cumulant Features for Cardiac Health Diagnosis using ECG signals

ANSI/AAMI EC57:2012/(R)2020; Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms

ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection

Rectified Linear Units Improve Restricted Boltzmann Machines

Robust Detection of Premature Ventricular Contractions Using a Wave-Based Bayesian Framework

Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet

Heart Diseases and Disorders

Robust Neural-Network-Based Classification of Premature Ventricular Contractions Using Wavelet Transform and Timing Interval Features

The impact of the MIT-BIH Arrhythmia Database

Visualizing Data using t-SNE

Physionet: components of a new research resource for complex physiologic signals

Ecg heartbeat classification: A deep transferable representation

Finding the set of all local maximums based on zero-crossings of the ﬁrst derivative

Splitting the continuous ECG signal to 10 s windows and select a 10 s window from an ECG signal

Finding the median of R-R time intervals as the nominal heartbeat period of that window ( T )

Normalizing the amplitude values to the range of be-tween zero and one

Finding the set of ECG R-peak candidates by applying a threshold of 0 . 9 on the normalized value of the local maximums

For each R-peak, selecting a signal part with the length equal to 1 . 2 T

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names