Key result
A machine learning model using PPG signal features estimated systolic BP with a mean absolute error of 8.22 mmHg (r=0.78) and diastolic BP with a mean absolute error of 4.17 mmHg (r=0.72).
Why the study?
Does a machine learning model using specific photoplethysmogram (PPG) signal morphological features accurately estimate blood pressure?
Comparison
Machine learning model using PPG morphological features vs previously reported PPG-only methods
Authors
Loading...
Caution against clinical adoption without validation; leaves open PPG-based ML utility pending larger prospective studies.
Does a machine learning model using specific photoplethysmogram (PPG) signal morphological features accurately estimate blood pressure?
Effect estimate: Correlation coefficient 0.78 (SBP), 0.72 (DBP)
A novel machine learning algorithm using specific PPG morphological features can estimate blood pressure with moderate to high accuracy, achieving BHS Grade A for diastolic BP.
Hasanzadeh et al. (2019) studied Blood pressure estimation. Machine learning model using PPG signal morphological features vs. Real BP values was evaluated on Accuracy of systolic and diastolic BP estimation (mean absolute error and correlation coefficient) (Correlation coefficient 0.78 (SBP), 0.72 (DBP)). A machine learning model using PPG signal features estimated systolic BP with a mean absolute error of 8.22 mmHg (r=0.78) and diastolic BP with a mean absolute error of 4.17 mmHg (r=0.72).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: