Key result
Deep learning BP measurement matches manual auscultation but reads diastolic ~3 mmHg higher during slow inflation.
Why the study?
The study was conducted to evaluate the performance of a deep learning-based method for measuring SBPs and DBPs, and the effects of cuff inflation and deflation rates compared with the manual auscultatory method.
Does a deep learning-based automatic blood pressure measurement method accurately measure SBP and DBP compared to the manual auscultatory method under various cuff deflation and inflation rates in healthy subjects?
Population
Forty healthy subjects
Comparison
Deep learning-based method vs manual auscultatory method under four cuff conditions
Design
Pilot evaluation study
Authors
Loading...
Hypothesis-generating for deep learning BP methods across rates; prospective validation needed before clinical use.
Observational (n=40)
Randomized measurement order
No
Does a deep learning-based automatic blood pressure measurement method accurately measure SBP and DBP compared to the manual auscultatory method under various cuff deflation and inflation rates in healthy subjects?
p-value: p=<0.05
A deep learning-based method can achieve accurate blood pressure measurement under various deflation and inflation rates, comparable to manual auscultation in most conditions.
Pan et al. (2020) conducted an observational in Normotensive (n=40). Deep learning-based automatic blood pressure measurement vs. Manual auscultatory method was evaluated on Difference in diastolic blood pressure during slow inflation (p=<0.05). The deep learning-based blood pressure measurement method achieved accurate readings comparable to the manual auscultatory method, with diastolic blood pressure measuring 2.56 mmHg higher during slow inflation.