Study of Arrhythmia Classification Algorithms on Electrocardiogram Using Deep Learning DOI Creative Commons

Rezki Fauzan Arifin,

Satria Mandala

SinkrOn, Journal Year: 2023, Volume and Issue: 8(3), P. 1753 - 1760

Published: July 20, 2023

Arrhythmia is a heart disease that occurs due to disturbance in the heartbeat causes rhythm become irregular. In some cases, arrhythmias can be life-threatening if not detected immediately. The method used detect electrocardiogram (ECG) signal analysis. To avoid misdiagnosis by cardiologists and ease workload, methods are proposed classify utilizing Artificial Intelligence (AI). recent years, there has been lot of research on detection this disease. However, many such studies more likely use machine learning algorithms classification process, most accuracy results still do reach optimal levels general. Therefore, study aims using deep algorithms. There several stages performing arrhythmia detection, namely, preprocessing, feature extraction, classification. focus only stage, where Long Short-Term Memory (LSTM) algorithm proposed. After going through series experiments, performance further analyzed compare accuracy, specificity, sensitivity with other based previous research, aim obtaining an for detection. Based study, managed outperform 98.47%, 99.24%, 97.67%, respectively.

Language: Английский

Study of Arrhythmia Classification Algorithms on Electrocardiogram Using Deep Learning DOI Creative Commons

Rezki Fauzan Arifin,

Satria Mandala

SinkrOn, Journal Year: 2023, Volume and Issue: 8(3), P. 1753 - 1760

Published: July 20, 2023

Arrhythmia is a heart disease that occurs due to disturbance in the heartbeat causes rhythm become irregular. In some cases, arrhythmias can be life-threatening if not detected immediately. The method used detect electrocardiogram (ECG) signal analysis. To avoid misdiagnosis by cardiologists and ease workload, methods are proposed classify utilizing Artificial Intelligence (AI). recent years, there has been lot of research on detection this disease. However, many such studies more likely use machine learning algorithms classification process, most accuracy results still do reach optimal levels general. Therefore, study aims using deep algorithms. There several stages performing arrhythmia detection, namely, preprocessing, feature extraction, classification. focus only stage, where Long Short-Term Memory (LSTM) algorithm proposed. After going through series experiments, performance further analyzed compare accuracy, specificity, sensitivity with other based previous research, aim obtaining an for detection. Based study, managed outperform 98.47%, 99.24%, 97.67%, respectively.

Language: Английский

Citations

1