Key result
Novel deep learning model estimates respiratory rate from PPG signals within 2 breaths/min.
Why the study?
Manual respiratory rate counting is often unreliable and discontinuous, while current estimation algorithms either lack accuracy or demand extensive window sizes.
Does a novel deep learning model accurately estimate respiratory rate from photoplethysmogram signals with a reduced window size compared to classical and other deep learning algorithms?
Does a novel deep learning model accurately estimate respiratory rate from photoplethysmogram signals with a reduced window size compared to classical and other deep learning algorithms?
Absolute Event Rate: 2% vs 1.9%
A novel deep learning algorithm using convolutional and LSTM layers can accurately estimate respiratory rate from PPG signals using a short 7-second window.
Supports short-window PPG-based respiratory rate estimation; leaves open prospective clinical validation.
Respiratory rate (RR) is a critical vital sign that can provide valuable insights into various medical conditions, including pneumonia. Unfortunately, manual RR counting is often unreliable and discontinuous. Current RR estimation algorithms either lack the necessary accuracy or demand extensive window sizes. In response to these challenges, this study introduces a novel method for continuously estimating RR from photoplethysmogram (PPG) with a reduced window size and lower processing requirements. To evaluate and compare classical and deep learning algorithms, this study leverages the BIDMC and CapnoBase datasets, employing the Respiratory Rate Estimation (RRest) toolbox. The optimal classical techniques combination on the BIDMC datasets achieves a mean absolute error (MAE) of 1.9 breaths/min. Additionally, the developed neural network model utilises convolutional and long short-term memory layers to estimate RR effectively. The best-performing model, with a 50% train-test split and a window size of 7 s, achieves an MAE of 2 breaths/min. Furthermore, compared to other deep learning algorithms with window sizes of 16, 32, and 64 s, this study's model demonstrates superior performance with a smaller window size. The study suggests that further research into more precise signal processing techniques may enhance RR estimation from PPG signals.
No takes yet. Share an insight, caveat, or question.
Chin et al. (2024) studied Respiratory rate estimation. Deep learning model (CNN and LSTM) for RR estimation from PPG vs. Classical techniques and other deep learning algorithms was evaluated on Mean absolute error (MAE) of respiratory rate estimation. A novel deep learning model using convolutional and LSTM layers estimated respiratory rate from photoplethysmogram signals with a mean absolute error of 2 breaths/min using a 7-second window.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: