B-PO05-041 DETECTION OF ATRIAL FIBRILLATION USING A WRIST PHOTOPLETHYSMOGRAM A PROSPECTIVE STUDY ON PATIENTS UNDERGOING CATHETER ABLATION OR ELECTRICAL CARDIOVERSION

Abstract

Atrial fibrillation (AF) is associated with an increased risk of mortality. The electrocardiogram (ECG)-based strategy of screening for AF has some limitations. Photoplethysmography (PPG) is used in AF detection algorithms. The objectives of this study were (1) to investigate whether quantitative analysis of wrist PPG waveforms can clearly distinguish AF from the sinus rhythm and (2) to determine the appropriate data length of the PPG waveforms for feature extraction to optimize the PPG analytics program for AF detection. Continuous waveforms of ECG recorded using an electrophysiology recording system and PPG signals using a wrist-worn smartwatch were simultaneously collected from patients undergoing catheter ablation or electrical cardioversion for AF. The PPG features (temporal, spectral, or morphological) were extracted from 10, 25, 40, or 80 heartbeats of split segments. Machine learning with a support vector machine (SVM) approach was used to detect AF. Receiver operating characteristic (ROC) curves were calculated to evaluate the diagnostic accuracy. A total of 116 patients were evaluated. We collected and annotated more than 117 hours of PPG waveforms. A total of 6478 and 3957 segments of 25-beat pulse-to-pulse interval (PPI) were annotated as AF and sinus rhythm, respectively. A total of eight features were extracted to distinguish AF. The accuracy of all eight PPG features extracted from the 25 PPI yielded a test area under the receiver operating characteristic curve (AUC) of 0.9676, which was significantly better than the AUC for the 10 PPI (0.9453; P<.001). Quantitative analysis of PPG waveforms can clearly discriminate the signals of AF from those of sinus rhythm. The appropriate data length of the PPG to optimize the PPG analytics program was 25 heartbeats.