Why the study?
Wearable sensor technologies have rarely focused on breathing, despite the utility of monitoring breathing metrics for general health and respiratory conditions.
Can an LSTM architecture accurately predict breathing metrics from a photoplethysmogram signal in healthy subjects?
Population
9 healthy subjects breathing at controlled respiratory rates
Comparison
Photoplethysmogram-derived metrics via an LSTM architecture vs reference signal from a respiratory band
Design
Proof-of-concept machine learning methodology study
Authors
Loading...
Supports PPG-based respiratory monitoring development; leaves open validation in clinical populations.
Can an LSTM architecture accurately predict breathing metrics from a photoplethysmogram signal in healthy subjects?
A machine learning LSTM model can derive breathing metrics from a photoplethysmogram signal with acceptable accuracy, offering a potential tool for long-term respiratory monitoring.
Prinable et al. (2020) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: