Key result
The 1D deep convolutional neural network achieved 95.10% accuracy, 94.60% sensitivity, and 95.20% specificity for classifying atrial fibrillation on an unseen PPG dataset.
Why the study?
Medical-grade ECG devices for AF detection are expensive and require clinical settings, creating a need for accessible AF classification models that generalize across both ECG and wearable PPG modalities.
Does a 1D deep convolutional neural network accurately classify atrial fibrillation using short-term HRV/PRV features from smart wearable PPG sensors?
Does a 1D deep convolutional neural network accurately classify atrial fibrillation using short-term HRV/PRV features from smart wearable PPG sensors?
A deep learning model trained on gold-standard ECG HRV features can be effectively adapted via transfer learning to detect atrial fibrillation from consumer wearable PPG sensors.
May enable wearable PPG AF screening in research; leaves open prospective clinical validation before practice change.
Atrial fibrillation (AF) is a type of cardiac arrhythmia affecting millions of people every year. This disease increases the likelihood of strokes, heart failure, and even death. While dedicated medical-grade electrocardiogram (ECG) devices can enable gold-standard analysis, these devices are expensive and require clinical settings. Recent advances in the capabilities of general-purpose smartphones and wearable technology equipped with photoplethysmography (PPG) sensors increase diagnostic accessibility for most populations. This work aims to develop a single model that can generalize AF classification across the modalities of ECG and PPG with a unified knowledge representation. This is enabled by approximating the transformation of signals obtained from low-cost wearable PPG sensors in terms of Pulse Rate Variability (PRV) to temporal Heart Rate Variability (HRV) features extracted from medical-grade ECG. This paper proposes a one-dimensional deep convolutional neural network that uses HRV-derived features for classifying 30-s heart rhythms as normal sinus rhythm or atrial fibrillation from both ECG and PPG-based sensors. The model is trained with three MIT-BIH ECG databases and is assessed on a dataset of unseen PPG signals acquired from wrist-worn wearable devices through transfer learning. The model achieved the aggregate binary classification performance measures of accuracy: 95.50%, sensitivity: 94.50%, and specificity: 96.00% across a five-fold cross-validation strategy on the ECG datasets. It also achieved 95.10% accuracy, 94.60% sensitivity, 95.20% specificity on an unseen PPG dataset. The results show considerable promise towards seamless adaptation of gold-standard ECG trained models for non-ambulatory AF detection with consumer wearable devices through HRV-based knowledge transfer.
No takes yet. Share an insight, caveat, or question.
Ramesh et al. (2021) studied Atrial fibrillation. One-dimensional deep convolutional neural network using HRV/PRV features was evaluated on Classification accuracy for atrial fibrillation on unseen PPG dataset. The 1D deep convolutional neural network achieved 95.10% accuracy, 94.60% sensitivity, and 95.20% specificity for classifying atrial fibrillation on an unseen PPG dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: