Cite Article

Re-implementation of Convolutional Neural Network for Arrhythmia Detection

Choose citation format

BibTeX

@article{IJASEIT13435,
   author = {Muhammad Ilham Rizqyawan and Yahdi Siradj and M Faizal Amri and Agus Pratondo},
   title = {Re-implementation of Convolutional Neural Network for Arrhythmia Detection},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {12},
   number = {4},
   year = {2022},
   pages = {1319--1326},
   keywords = {Arrhythmia classification; convolutional neural network; electrocardiography; heartbeat classification.},
   abstract = {Arrhythmia is an irregular heartbeat that may cause serious problems such as cardiac arrest and heart failure if left untreated. A dozen of studies have been conducted to make an automated arrhythmia detector. The classification approach uses a simple rule-based model, traditional machine learning, to a modern deep-learning technique. However, comparing an arrhythmia classifier performance is not an easy task. There are several different datasets, classification standards, data splitting schemes, and metrics. To assess the real performance of the developed models, it is important to train and evaluate the model in a standardized method such as the result score can become standard too. In this study, a set of CNN models from Acharya were re-implemented by re-training and re-evaluating it in a more standardized method. The model uses a raw ECG waveform with 260 samples around the QRS peaks and classifies it into five arrhythmia classes. The experiment was conducted using three configurations, using both intra-patient and inter-patient schemes. The experimental results show good performance for the intra-patient scheme but not for the inter-patient. There is a reduction of sensitivity and precision in the intra-patient scheme using a standardized method in this study compared to the original paper. This result indicates biased results caused by the oversampled test data in the original paper. In addition to the intra-patient result, the inter-patient result is also provided for a standardized comparison to other works in the future.},
   issn = {2088-5334},
   publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},
   url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13435},
   doi = {10.18517/ijaseit.12.4.13435}
}

EndNote

%A Rizqyawan, Muhammad Ilham
%A Siradj, Yahdi
%A Amri, M Faizal
%A Pratondo, Agus
%D 2022
%T Re-implementation of Convolutional Neural Network for Arrhythmia Detection
%B 2022
%9 Arrhythmia classification; convolutional neural network; electrocardiography; heartbeat classification.
%! Re-implementation of Convolutional Neural Network for Arrhythmia Detection
%K Arrhythmia classification; convolutional neural network; electrocardiography; heartbeat classification.
%X Arrhythmia is an irregular heartbeat that may cause serious problems such as cardiac arrest and heart failure if left untreated. A dozen of studies have been conducted to make an automated arrhythmia detector. The classification approach uses a simple rule-based model, traditional machine learning, to a modern deep-learning technique. However, comparing an arrhythmia classifier performance is not an easy task. There are several different datasets, classification standards, data splitting schemes, and metrics. To assess the real performance of the developed models, it is important to train and evaluate the model in a standardized method such as the result score can become standard too. In this study, a set of CNN models from Acharya were re-implemented by re-training and re-evaluating it in a more standardized method. The model uses a raw ECG waveform with 260 samples around the QRS peaks and classifies it into five arrhythmia classes. The experiment was conducted using three configurations, using both intra-patient and inter-patient schemes. The experimental results show good performance for the intra-patient scheme but not for the inter-patient. There is a reduction of sensitivity and precision in the intra-patient scheme using a standardized method in this study compared to the original paper. This result indicates biased results caused by the oversampled test data in the original paper. In addition to the intra-patient result, the inter-patient result is also provided for a standardized comparison to other works in the future.
%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13435
%R doi:10.18517/ijaseit.12.4.13435
%J International Journal on Advanced Science, Engineering and Information Technology
%V 12
%N 4
%@ 2088-5334

IEEE

Muhammad Ilham Rizqyawan,Yahdi Siradj,M Faizal Amri and Agus Pratondo,"Re-implementation of Convolutional Neural Network for Arrhythmia Detection," International Journal on Advanced Science, Engineering and Information Technology, vol. 12, no. 4, pp. 1319-1326, 2022. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.12.4.13435.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Rizqyawan, Muhammad Ilham
AU  - Siradj, Yahdi
AU  - Amri, M Faizal
AU  - Pratondo, Agus
PY  - 2022
TI  - Re-implementation of Convolutional Neural Network for Arrhythmia Detection
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 12 (2022) No. 4
Y2  - 2022
SP  - 1319
EP  - 1326
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - Arrhythmia classification; convolutional neural network; electrocardiography; heartbeat classification.
N2  - Arrhythmia is an irregular heartbeat that may cause serious problems such as cardiac arrest and heart failure if left untreated. A dozen of studies have been conducted to make an automated arrhythmia detector. The classification approach uses a simple rule-based model, traditional machine learning, to a modern deep-learning technique. However, comparing an arrhythmia classifier performance is not an easy task. There are several different datasets, classification standards, data splitting schemes, and metrics. To assess the real performance of the developed models, it is important to train and evaluate the model in a standardized method such as the result score can become standard too. In this study, a set of CNN models from Acharya were re-implemented by re-training and re-evaluating it in a more standardized method. The model uses a raw ECG waveform with 260 samples around the QRS peaks and classifies it into five arrhythmia classes. The experiment was conducted using three configurations, using both intra-patient and inter-patient schemes. The experimental results show good performance for the intra-patient scheme but not for the inter-patient. There is a reduction of sensitivity and precision in the intra-patient scheme using a standardized method in this study compared to the original paper. This result indicates biased results caused by the oversampled test data in the original paper. In addition to the intra-patient result, the inter-patient result is also provided for a standardized comparison to other works in the future.
UR  - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13435
DO  - 10.18517/ijaseit.12.4.13435

RefWorks

RT Journal Article
ID 13435
A1 Rizqyawan, Muhammad Ilham
A1 Siradj, Yahdi
A1 Amri, M Faizal
A1 Pratondo, Agus
T1 Re-implementation of Convolutional Neural Network for Arrhythmia Detection
JF International Journal on Advanced Science, Engineering and Information Technology
VO 12
IS 4
YR 2022
SP 1319
OP 1326
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 Arrhythmia classification; convolutional neural network; electrocardiography; heartbeat classification.
AB Arrhythmia is an irregular heartbeat that may cause serious problems such as cardiac arrest and heart failure if left untreated. A dozen of studies have been conducted to make an automated arrhythmia detector. The classification approach uses a simple rule-based model, traditional machine learning, to a modern deep-learning technique. However, comparing an arrhythmia classifier performance is not an easy task. There are several different datasets, classification standards, data splitting schemes, and metrics. To assess the real performance of the developed models, it is important to train and evaluate the model in a standardized method such as the result score can become standard too. In this study, a set of CNN models from Acharya were re-implemented by re-training and re-evaluating it in a more standardized method. The model uses a raw ECG waveform with 260 samples around the QRS peaks and classifies it into five arrhythmia classes. The experiment was conducted using three configurations, using both intra-patient and inter-patient schemes. The experimental results show good performance for the intra-patient scheme but not for the inter-patient. There is a reduction of sensitivity and precision in the intra-patient scheme using a standardized method in this study compared to the original paper. This result indicates biased results caused by the oversampled test data in the original paper. In addition to the intra-patient result, the inter-patient result is also provided for a standardized comparison to other works in the future.
LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13435
DO  - 10.18517/ijaseit.12.4.13435