A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal

Ullah, Amin; Rehman, Sadaqat Ur; Tu, Shanshan; Mehmood, Raja Majid; Fawad, Fawad; Ehatisham-ul-Haq, Muhammad

doi:10.3390/s21030951

Cited by 84 publications

(21 citation statements)

References 62 publications

(76 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have utilized AI techniques to detect cardiac problems from ECG data. Some of these studies [ [45] , [46] , [47] ] employed 1-D ECG signals to classify the anomalies. Other research articles [ [48] , [49] , [50] , [51] , [52] ] transformed ECG signals to 2-D images using numerous methods such as wavelet transform and short-term frequency transform to detect abnormalities.…”

Section: Related Workmentioning

confidence: 99%

ECG-BiCoNet: An ECG-based pipeline for COVID-19 diagnosis using Bi-Layers of deep features integration

Attallah

2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

The accurate and speedy detection of COVID-19 is essential to avert the fast propagation of the virus, alleviate lockdown constraints and diminish the burden on health organizations. Currently, the methods used to diagnose COVID-19 have several limitations, thus new techniques need to be investigated to improve the diagnosis and overcome these limitations. Taking into consideration the great benefits of electrocardiogram (ECG) application, this paper proposes a new pipeline called ECG-BiCoNet to investigate the potential of using ECG data for diagnosing COVID-19. ECG-BiCoNet employs five deep learning models of distinct structural design. ECG-BiCoNet extracts two levels of features from two different layers of each deep learning technique. Features mined from higher layers are fused using discrete wavelet transform and then integrated with lower-layers features. Afterward, a feature selection approach is utilized. Finally, an ensemble classification system is built to merge predictions of three machine learning classifiers. ECG-BiCoNet accomplishes two classification categories, binary and multiclass. The results of ECG-BiCoNet present a promising COVID-19 performance with an accuracy of 98.8% and 91.73% for binary and multiclass classification categories. These results verify that ECG data may be used to diagnose COVID-19 which can help clinicians in the automatic diagnosis and overcome limitations of manual diagnosis.

show abstract

Section: Related Workmentioning

confidence: 99%

ECG-BiCoNet: An ECG-based pipeline for COVID-19 diagnosis using Bi-Layers of deep features integration

Attallah

2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

show abstract

“…Electrocardiograms (ECGs) are the most commonly used bioelectric signal. ECGs are used for cardiovascular disease screening and assessing heart or cardiovascular functions [1][2][3][4][5][6]. Additionally, they have become increasingly critical in lifestyle and consumer applications, including exercise monitoring [7,8], fatigue detection [9,10], and stress monitoring [11,12].…”

Section: Introductionmentioning

confidence: 99%

Novel Stable Capacitive Electrocardiogram Measurement System

Chen

Lin

Wang³

2021

Sensors

View full text Add to dashboard Cite

This study presents a noncontact electrocardiogram (ECG) measurement system to replace conventional ECG electrode pads during ECG measurement. The proposed noncontact electrode design comprises a surface guard ring, the optimal input resistance, a ground guard ring, and an optimal voltage divider feedback. The surface and ground guard rings are used to reduce environmental noise. The optimal input resistor mitigates distortion caused by the input bias current, and the optimal voltage divider feedback increases the gain. Simulated gain analysis was subsequently performed to determine the most suitable parameters for the design, and the system was combined with a capacitive driven right leg circuit to reduce common-mode interference. The present study simulated actual environments in which interference is present in capacitive ECG signal measurement. Both in the case of environmental interference and motion artifact interference, relative to capacitive ECG electrodes, the proposed electrodes measured ECG signals with greater stability. In terms of R–R intervals, the measured ECG signals exhibited a 98.6% similarity to ECGs measured using contact ECG systems. The proposed noncontact ECG measurement system based on capacitive sensing is applicable for use in everyday life.

show abstract

“…Some other works transformed 1D ECGs into gray-scale images by considering ECG traces as black pixels, while the background were filled with white pixels [ 26 ]. In addition, Ullah et al [ 27 ] used continuous wavelet to decompose the 1D ECG and stacked the obtained wavelet coefficients (along multiple scales) as a 2D image. Notably, it is difficult to fully preserve the diagnostic information in the ECG by using spatial information of pixels in the converted image (e.g., [ 23 , 24 , 25 , 26 ]), as the time and frequency information in the ECG signal could be blurred and interrupted.…”

Section: Introductionmentioning

confidence: 99%

“…Notably, it is difficult to fully preserve the diagnostic information in the ECG by using spatial information of pixels in the converted image (e.g., [ 23 , 24 , 25 , 26 ]), as the time and frequency information in the ECG signal could be blurred and interrupted. Additionally, the spectrogram representation of ECG (i.e., [ 27 ]) generates redundant information in the converted image (due to the continuous change in the position and scale of the wavelet), which makes the spatial correlation of image pixels less interpretable.…”

Section: Introductionmentioning

confidence: 99%

Tensor-Based ECG Anomaly Detection toward Cardiac Monitoring in the Internet of Health Things

Zhou

Chen

2021

Sensors

View full text Add to dashboard Cite

Advanced heart monitors, especially those enabled by the Internet of Health Things (IoHT), provide a great opportunity for continuous collection of the electrocardiogram (ECG), which contains rich information about underlying cardiac conditions. Realizing the full potential of IoHT-enabled cardiac monitoring hinges, to a great extent, on the detection of disease-induced anomalies from collected ECGs. However, challenges exist in the current literature for IoHT-based cardiac monitoring: (1) Most existing methods are based on supervised learning, which requires both normal and abnormal samples for training. This is impractical as it is generally unknown when and what kind of anomalies will occur during cardiac monitoring. (2) Furthermore, it is difficult to leverage advanced machine learning approaches for information processing of 1D ECG signals, as most of them are designed for 2D images and higher-dimensional data. To address these challenges, a new sensor-based unsupervised framework is developed for IoHT-based cardiac monitoring. First, a high-dimensional tensor is generated from the multi-channel ECG signals through the Gramian Angular Difference Field (GADF). Then, multi-linear principal component analysis (MPCA) is employed to unfold the ECG tensor and delineate the disease-altered patterns. Obtained principal components are used as features for anomaly detection using machine learning models (e.g., deep support vector data description (deep SVDD)) as well as statistical control charts (e.g., Hotelling T2 chart). The developed framework is evaluated and validated using real-world ECG datasets. Comparing to the state-of-the-art approaches, the developed framework with deep SVDD achieves superior performances in detecting abnormal ECG patterns induced by various types of cardiac disease, e.g., an F-score of 0.9771 is achieved for detecting atrial fibrillation, 0.9986 for detecting right bundle branch block, and 0.9550 for detecting ST-depression. Additionally, the developed framework with the T2 control chart facilitates personalized cycle-to-cycle monitoring with timely detected abnormal ECG patterns. The developed framework has a great potential to be implemented in IoHT-enabled cardiac monitoring and smart management of cardiac health.

show abstract

A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal

Cited by 84 publications

References 62 publications

ECG-BiCoNet: An ECG-based pipeline for COVID-19 diagnosis using Bi-Layers of deep features integration

ECG-BiCoNet: An ECG-based pipeline for COVID-19 diagnosis using Bi-Layers of deep features integration

Novel Stable Capacitive Electrocardiogram Measurement System

Tensor-Based ECG Anomaly Detection toward Cardiac Monitoring in the Internet of Health Things

Contact Info

Product

Resources

About