Key result
The i-PRExT model achieved over 90% correlation and low error (NRMSE~0.2) with reference respiration signals, while respiration rate tracking had almost 100% correlation even under motion artifacts.
Why the study?
Noninvasive monitoring of respiratory activity is an emerging research area in biomedical health monitoring.
The i-PRExT neural network model accurately extracts respiration signals and tracks respiratory rate from PPG data, outperforming existing published methods even under motion artifacts.
May enable motion-robust PPG respiration monitoring in wearables; leaves open prospective clinical validation.
Noninvasive monitoring of respiratory activity is an emerging research area in biomedical health monitoring. This article describes a neural network-based model, intelligent Photoplethysmography derived Respiration signal Extraction, and Tracking (i-PRExT). Here, an ensemble empirical mode decomposition (EEMD) is used to select the appropriate intrinsic mode functions (IMFs) through filtering in the respiration band and reconstruct by a linear weighted sum to obtain the photoplethysmography derived respiration (PDR) signal. The weight factors are derived by a multilayer perceptron neural network (MLPNN) fed with respiratory induced amplitude variation (RIAV) features extracted by a deep autoencoder (DAE). The tracking of respiration rate (RR) is done by an adaptive filter-based predictor. i-PRExT was tested and validated with BIDMC data set under PhysioNet and 30 volunteers' data collected under resting condition. The PDRs achieved over 90% correlation and low error (NRMSE~0.2) with reference respiration signal, while RRs have almost 100% correlation even under motion artifact (MA) corrupted photoplethysmography (PPG). The PDR shows improved performance, while RR tracking outperforms the published research on respiration signal extraction based on PPG.
No takes yet. Share an insight, caveat, or question.
Roy et al. (2020) studied Respiratory activity monitoring (n=30). i-PRExT (intelligent Photoplethysmography derived Respiration signal Extraction, and Tracking) vs. Reference respiration signal was evaluated on Correlation and normalized root mean square error (NRMSE) with reference respiration signal. The i-PRExT model achieved over 90% correlation and low error (NRMSE~0.2) with reference respiration signals, while respiration rate tracking had almost 100% correlation even under motion artifacts.