Deep CNN-based detection of cardiac rhythm disorders using PPG signals from wearable devices.

Cardiac rhythm disorders can manifest in various ways, such as the heart rate being too fast (tachycardia) or too slow (bradycardia), irregular heartbeats (like atrial fibrillation-AF, ventricular fibrillation-VF), or the initiation of heartbeats in different areas from the norm (extrasystole). Arrhythmias can disrupt the balanced circulation, leading to serious complications like heart attacks, strokes, and sudden death. Medical devices like electrocardiography (ECG) and Holter monitors are commonly used for diagnosing and monitoring cardiac rhythm disorders. However, in recent years, the development of wearable devices has played a significant role in the detection and diagnosis of rhythm disorders through the use of photoplethysmography (PPG) signals. Wearable devices enable patients to continuously monitor their health status and allow doctors to provide earlier diagnoses and interventions. In this study, a 1D-CNN model is proposed to detect arrhythmias using PPG signals. A dataset prepared by the University of Massachusetts Medical Center (UMMC) containing both ECG and PPG signal data was utilized. In this dataset, ECG signals are filtered with a bandpass filter and raw PPG signals are divided into 30-second segments. Accuracy values were obtained by classifying ECG and PPG signals using a 1D CNN model. ECG signals were used as a reference. The proposed model achieved a 95.17% accuracy rate in detecting normal sinus rhythm (NSR), atrial fibrillation (AF), and premature atrial contractions (PAC) from PPG signals. Datasets are available for download on https://www.synapse.org/pulsewatch. The codes used in this study are available on the https://github.com/miraygunay/PPG-Code.git website.