Key result
A proposed evidential regression method for continuous blood pressure monitoring from PPG signals achieved state-of-the-art performance on the MIMIC II database while estimating prediction uncertainty.
Why the study?
Existing machine learning-based photoplethysmogram blood pressure measuring methods fall behind measurement guidelines and typically provide only point estimates of SBP and DBP.
Does a machine learning method with evidential regression improve continuous blood pressure monitoring accuracy and uncertainty estimation from PPG signals compared to existing methods?
Population
Data from the MIMIC II database
Comparison
Novel evidential regression PPG-based BP monitoring method vs existing machine learning-based methods
Design
Model development and validation study
Authors
Loading...
May support PPG-based continuous BP monitoring with uncertainty estimates; leaves open prospective clinical validation.
Does a machine learning method with evidential regression improve continuous blood pressure monitoring accuracy and uncertainty estimation from PPG signals compared to existing methods?
A novel machine learning method using evidential regression enables continuous, accurate blood pressure monitoring from PPG signals with reliable uncertainty estimation.
Kim et al. (2021) studied Blood pressure estimation. Evidential regression method for continuous BP monitoring from PPG signals vs. Existing machine learning-based BP measuring methods was evaluated on Blood pressure estimation performance and uncertainty representation. A proposed evidential regression method for continuous blood pressure monitoring from PPG signals achieved state-of-the-art performance on the MIMIC II database while estimating prediction uncertainty.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: