Multiclass Arrhythmia Classification using Smartwatch Photoplethysmography Signals Collected in Real-life Settings
This work addresses the problem of accurate arrhythmia detection from wearable devices for healthcare monitoring, representing a strong incremental improvement over existing methods.
The paper tackled multiclass arrhythmia classification using noisy smartwatch PPG data, achieving 83% sensitivity for PAC/PVC detection and 97.31% accuracy for AF detection, outperforming prior methods by significant margins while being more computationally efficient.
Most deep learning models of multiclass arrhythmia classification are tested on fingertip photoplethysmographic (PPG) data, which has higher signal-to-noise ratios compared to smartwatch-derived PPG, and the best reported sensitivity value for premature atrial/ventricular contraction (PAC/PVC) detection is only 75%. To improve upon PAC/PVC detection sensitivity while maintaining high AF detection, we use multi-modal data which incorporates 1D PPG, accelerometers, and heart rate data as the inputs to a computationally efficient 1D bi-directional Gated Recurrent Unit (1D-Bi-GRU) model to detect three arrhythmia classes. We used motion-artifact prone smartwatch PPG data from the NIH-funded Pulsewatch clinical trial. Our multimodal model tested on 72 subjects achieved an unprecedented 83% sensitivity for PAC/PVC detection while maintaining a high accuracy of 97.31% for AF detection. These results outperformed the best state-of-the-art model by 20.81% for PAC/PVC and 2.55% for AF detection even while our model was computationally more efficient (14 times lighter and 2.7 faster).