Arrhythmia detection based on patient-specific normal ECGs using deep learning

Abstract

Most traditional studies regarding arrhythmia detection using electrocardiogram (ECG) have proposed general methods applicable to various patients. Because patients have their own unique ECG patterns, abnormalities undetected by general methods can be detected if a new arrhythmia detection method tailored to each patient is developed. Furthermore, the new method can effectively support doctors in their diagnosis if it can provide the basis for determining abnormalities. Herein, we propose an individualized ECG abnormality judgment method using an autoencoder and a convolutional neural network. This method allows the autoencoder to learn only normal waveforms that can be easily collected and obtains the characteristics of the individual's unique normal waveforms. Our method compares the features acquired from the ECG pattern to be analyzed with those of the normal waveform and determines whether they are normal or abnormal. In addition, we aim to construct a system that can demonstrate the basis for the judgment of whether a feature is normal or abnormal by showing the acquired features.

Deep Learning Autoencoder Study on ECG Signals

“…The MITDB database serves as a reference for arrhythmias, while the AFDB database is specifically a reference for Atrial Fibrillation (AF). Notably, two datasets in AFDB, i.e, data 00735 and 03665, will be excluded from our research due to being empty datasets, as noted by [4,20].…”

“…Arrhythmias, including more severe forms like Atrial Fibrillation (AF), can significantly contribute to the progression of heart disease. Atrial fibrillation (AF) is identified as the most prevalent clinical arrhythmia, carrying substantial risks to patient health and markedly increasing morbidity, mortality, and healthcare costs [4]. The main signal utilized for examining arrhythmias is the electrocardiogram (ECG) signal.…”

“…The main method in medical practice for evaluating the electrical activity of the human heart is through the recording and analysis of the Electrocardiogram (ECG) signal [4,5]. The identification of morphological changes in ECG signals serves as a crucial tool for doctors in detecting and predicting heart diseases, including arrhythmias.…”