Automatic detection of electrocardiographic arrhythmias by parallel continuous neural networks implemented in FPGA

Mariel Alfaro-Ponce, Isaac Chairez, Ralph Etienne-Cummings

Research output: Contribution to journalArticleResearchpeer-review

2 Citations (Scopus)

Abstract

© 2017, The Natural Computing Applications Forum. In the developed world, heart diseases are the major cause of death among adults. Often, the sufferers of heart disease are not aware of their condition until a catastrophic medical event occurs. Therefore, early online detection and continuous monitoring of abnormal heart rhythms shall reduce this occurrence. There are four main types of arrhythmia: ventricular arrhythmia, supraventricular arrhythmia, premature beats and asynchronous arrhythmia. In this study, an algorithm for automatic detection of atrial premature contraction, supraventricular tachyarrhythmias, fusion of ventricular and normal beat (FUSION), isolated QRS-like artifact (ARFCT), ST change, T-wave change, premature or ectopic supraventricular beat and normal beat (NORMAL) using a continuous neural network (CoNN) is presented. This kind of continuous classifier offers an online detection of classical arrhythmia observed in electrocardiographic (EKG) signals. Typically, due to its complexity and recursive nature of arrhythmia classification algorithms, they are difficult to be implemented in real time. In this work, automatic signal classification was attained by implementing a parallel CoNN algorithm using fixed point arithmetic on a field-programmable gate array (FPGA). First, the classification algorithm using a floating-point MATLAB implementation was developed and validated. This procedure served as a benchmark for the fixed point FPGA implementation on a Xilinx Zinq board. The performance of the classification algorithm was evaluated by using a fivefold cross-validation method, achieving a 93.80% accuracy and a sensitivity (TPR) average of 98% when performing the classification of the entire set of EKG signal samples.
Original languageAmerican English
Pages (from-to)363-375
Number of pages325
JournalNeural Computing and Applications
DOIs
StatePublished - 14 Feb 2019

Fingerprint

Field programmable gate arrays (FPGA)
Cardiac Arrhythmias
Neural networks
Atrial Premature Complexes
Electrocardiography
Fixed point arithmetic
Heart Diseases
Benchmarking
MATLAB
Tachycardia
Classifiers
Fusion reactions
Artifacts
Cause of Death
Monitoring

Cite this

@article{a27b84c2e8494c51891ae7274e770fbf,
title = "Automatic detection of electrocardiographic arrhythmias by parallel continuous neural networks implemented in FPGA",
abstract = "{\circledC} 2017, The Natural Computing Applications Forum. In the developed world, heart diseases are the major cause of death among adults. Often, the sufferers of heart disease are not aware of their condition until a catastrophic medical event occurs. Therefore, early online detection and continuous monitoring of abnormal heart rhythms shall reduce this occurrence. There are four main types of arrhythmia: ventricular arrhythmia, supraventricular arrhythmia, premature beats and asynchronous arrhythmia. In this study, an algorithm for automatic detection of atrial premature contraction, supraventricular tachyarrhythmias, fusion of ventricular and normal beat (FUSION), isolated QRS-like artifact (ARFCT), ST change, T-wave change, premature or ectopic supraventricular beat and normal beat (NORMAL) using a continuous neural network (CoNN) is presented. This kind of continuous classifier offers an online detection of classical arrhythmia observed in electrocardiographic (EKG) signals. Typically, due to its complexity and recursive nature of arrhythmia classification algorithms, they are difficult to be implemented in real time. In this work, automatic signal classification was attained by implementing a parallel CoNN algorithm using fixed point arithmetic on a field-programmable gate array (FPGA). First, the classification algorithm using a floating-point MATLAB implementation was developed and validated. This procedure served as a benchmark for the fixed point FPGA implementation on a Xilinx Zinq board. The performance of the classification algorithm was evaluated by using a fivefold cross-validation method, achieving a 93.80{\%} accuracy and a sensitivity (TPR) average of 98{\%} when performing the classification of the entire set of EKG signal samples.",
author = "Mariel Alfaro-Ponce and Isaac Chairez and Ralph Etienne-Cummings",
year = "2019",
month = "2",
day = "14",
doi = "10.1007/s00521-017-3051-3",
language = "American English",
pages = "363--375",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",

}

Automatic detection of electrocardiographic arrhythmias by parallel continuous neural networks implemented in FPGA. / Alfaro-Ponce, Mariel; Chairez, Isaac; Etienne-Cummings, Ralph.

In: Neural Computing and Applications, 14.02.2019, p. 363-375.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Automatic detection of electrocardiographic arrhythmias by parallel continuous neural networks implemented in FPGA

AU - Alfaro-Ponce, Mariel

AU - Chairez, Isaac

AU - Etienne-Cummings, Ralph

PY - 2019/2/14

Y1 - 2019/2/14

N2 - © 2017, The Natural Computing Applications Forum. In the developed world, heart diseases are the major cause of death among adults. Often, the sufferers of heart disease are not aware of their condition until a catastrophic medical event occurs. Therefore, early online detection and continuous monitoring of abnormal heart rhythms shall reduce this occurrence. There are four main types of arrhythmia: ventricular arrhythmia, supraventricular arrhythmia, premature beats and asynchronous arrhythmia. In this study, an algorithm for automatic detection of atrial premature contraction, supraventricular tachyarrhythmias, fusion of ventricular and normal beat (FUSION), isolated QRS-like artifact (ARFCT), ST change, T-wave change, premature or ectopic supraventricular beat and normal beat (NORMAL) using a continuous neural network (CoNN) is presented. This kind of continuous classifier offers an online detection of classical arrhythmia observed in electrocardiographic (EKG) signals. Typically, due to its complexity and recursive nature of arrhythmia classification algorithms, they are difficult to be implemented in real time. In this work, automatic signal classification was attained by implementing a parallel CoNN algorithm using fixed point arithmetic on a field-programmable gate array (FPGA). First, the classification algorithm using a floating-point MATLAB implementation was developed and validated. This procedure served as a benchmark for the fixed point FPGA implementation on a Xilinx Zinq board. The performance of the classification algorithm was evaluated by using a fivefold cross-validation method, achieving a 93.80% accuracy and a sensitivity (TPR) average of 98% when performing the classification of the entire set of EKG signal samples.

AB - © 2017, The Natural Computing Applications Forum. In the developed world, heart diseases are the major cause of death among adults. Often, the sufferers of heart disease are not aware of their condition until a catastrophic medical event occurs. Therefore, early online detection and continuous monitoring of abnormal heart rhythms shall reduce this occurrence. There are four main types of arrhythmia: ventricular arrhythmia, supraventricular arrhythmia, premature beats and asynchronous arrhythmia. In this study, an algorithm for automatic detection of atrial premature contraction, supraventricular tachyarrhythmias, fusion of ventricular and normal beat (FUSION), isolated QRS-like artifact (ARFCT), ST change, T-wave change, premature or ectopic supraventricular beat and normal beat (NORMAL) using a continuous neural network (CoNN) is presented. This kind of continuous classifier offers an online detection of classical arrhythmia observed in electrocardiographic (EKG) signals. Typically, due to its complexity and recursive nature of arrhythmia classification algorithms, they are difficult to be implemented in real time. In this work, automatic signal classification was attained by implementing a parallel CoNN algorithm using fixed point arithmetic on a field-programmable gate array (FPGA). First, the classification algorithm using a floating-point MATLAB implementation was developed and validated. This procedure served as a benchmark for the fixed point FPGA implementation on a Xilinx Zinq board. The performance of the classification algorithm was evaluated by using a fivefold cross-validation method, achieving a 93.80% accuracy and a sensitivity (TPR) average of 98% when performing the classification of the entire set of EKG signal samples.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85027079726&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85027079726&origin=inward

U2 - 10.1007/s00521-017-3051-3

DO - 10.1007/s00521-017-3051-3

M3 - Article

SP - 363

EP - 375

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

ER -