Key result
An artificial neural network model using only photoplethysmography signals estimated blood pressure with a mean absolute error of 4.02 ± 2.79 mmHg for systolic and 2.27 ± 1.82 mmHg for diastolic BP.
Why the study?
Does a neural network model using PPG without ECG accurately estimate blood pressure?
Comparison
Blood pressure estimation using… vs Previous approaches
Design
Other
Authors
Loading...
May support cuffless wearable BP monitoring; leaves open prospective validation before clinical use.
Does a neural network model using PPG without ECG accurately estimate blood pressure?
Effect estimate: MAE 4.02 ± 2.79 mmHg (SBP) and 2.27 ± 1.82 mmHg (DBP)
A novel neural network model using only PPG signals can estimate systolic and diastolic blood pressure with low mean absolute error, offering potential for noninvasive wearable BP monitoring.
Wang et al. (2018) studied Blood pressure estimation. Artificial neural network (ANN) model using photoplethysmography (PPG) signal vs. Previous approaches was evaluated on Mean absolute error for systolic and diastolic blood pressure estimation (MAE 4.02 ± 2.79 mmHg (SBP) and 2.27 ± 1.82 mmHg (DBP)). An artificial neural network model using only photoplethysmography signals estimated blood pressure with a mean absolute error of 4.02 ± 2.79 mmHg for systolic and 2.27 ± 1.82 mmHg for diastolic BP.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: