Why the study?
Atrial fibrillation needs accurate monitoring, but the presence of premature atrial and ventricular contractions can lead to false AF detection on photoplethysmography signals.
Does a CNN-based algorithm using Time-Frequency spectra and Poincare plots improve the accuracy of detecting AF, NSR, and PAC/PVC from smartwatch PPG data?
Does a CNN-based algorithm using Time-Frequency spectra and Poincare plots improve the accuracy of detecting AF, NSR, and PAC/PVC from smartwatch PPG data?
A novel deep learning and signal processing approach using smartwatch PPG data can accurately distinguish atrial fibrillation from normal sinus rhythm and premature contractions.
May enhance smartwatch PPG arrhythmia detection but requires validation; leaves open prospective trials before clinical use.
Atrial Fibrillation (AF) with high mortality rate needs to be monitored and detected accurately. AF is indicated as varying pulse-to-pulse intervals in a PPG signal. To record Photoplethysmography (PPG) signal, wrist-watches are used. AF detection is made using features, discriminating AF from Normal Sinus Rhythm (NSR). The presence of Premature Atrial and Ventricular Contraction <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">(PAC/PVC)</tex> in subjects due to its randomness may lead to false AF detection. The proposed methodology utilizes Convolutional Neural Network (CNN) on Time-Frequency spectra (TFS) along with signal processing for classification of PPG signal into AF, NSR and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PAC/PVC</tex>, The Poincare plot based <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PAC/PVC</tex> detection implemented in this paper not only separates <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PAC/PVC</tex> from NSR and AF but also improves the accuracy of AF and NSR detection. The results for training and testing are validated on UMass Simband dataset (Smartwatch PPG Data with AF, NSR, PAC, PVC) and MIMIC III dataset (Finger Tips Pulse Oximetry PPG data with AF, NSR, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PAC/PVC)</tex>., The experimental results have shown that the proposed system gives higher accuracy, sensitivity and specificity values for both datasets.
No takes yet. Share an insight, caveat, or question.
Javed et al. (2023) studied Atrial Fibrillation, Premature Atrial and Ventricular Contraction. Convolutional Neural Network (CNN) on Time-Frequency spectra (TFS) and Poincare plot was evaluated on Classification accuracy, sensitivity, and specificity.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: