Key result
Calculating respiratory quality indices for modulation-extracted respiratory rates decreased the mean absolute error of neural networks by up to 38.17%, achieving an MAE of 0.638 breaths per minute using 60-second segments.
Why the study?
Continuous non-invasive respiratory rate monitoring improves outcomes, but respiratory rate is currently under-recorded and often measured by manually counting breaths.
Does the inclusion of respiratory quality indices (RQIs) improve the accuracy of neural network-based respiratory rate estimation from ECG and PPG signals in ICU patients?
Does the inclusion of respiratory quality indices (RQIs) improve the accuracy of neural network-based respiratory rate estimation from ECG and PPG signals in ICU patients?
Combining respiratory quality indices with neural networks enables highly accurate, continuous, non-invasive respiratory rate monitoring from standard ECG and PPG signals.
Answers are grounded in this paper and cite their sources.
May improve continuous non-invasive respiratory monitoring from ECG/PPG in ICU; leaves open prospective clinical validation.
Continuous and non-invasive respiratory rate (RR) monitoring would significantly improve patient outcomes. Currently, RR is under-recorded in clinical environments and is often measured by manually counting breaths. In this work, we investigate the use of respiratory signal quality quantification and several neural network (NN) structures for improved RR estimation. We extract respiratory modulation signals from the electrocardiogram (ECG) and photoplethysmogram (PPG) signals, and calculate a possible RR from each extracted signal. We develop a straightforward and efficient respiratory quality index (RQI) scheme that determines the quality of each moonddulation-extracted respiration signal. We then develop NNs for the estimation of RR, using estimated RRs and their corresponding quality index as input features. We determine that calculating RQIs for modulation-extracted RRs decreased the mean absolute error (MAE) of our NNs by up to 38.17%. When trained and tested using 60-sec waveform segments, the proposed scheme achieved an MAE of 0.638 breaths per minute. Based on these results, our scheme could be readily implemented into non-invasive wearable devices for continuous RR measurement in many healthcare applications.
No takes yet. Share an insight, caveat, or question.
Baker et al. (2021) studied Intensive care unit patients requiring respiratory monitoring (n=8,781). BiLSTM neural network with respiratory quality indices (RQI) vs. BiLSTM neural network without RQI (RR features only) was evaluated on Mean absolute error (MAE) of respiratory rate estimation (60-second segments). Calculating respiratory quality indices for modulation-extracted respiratory rates decreased the mean absolute error of neural networks by up to 38.17%, achieving an MAE of 0.638 breaths per minute using 60-second segments.
Synapse has enriched 10 related papers. Consider them for comparative context: