Key result
A deep belief network-deep neural network model yielded lower standard deviation of error, mean error, and mean absolute error for blood pressure estimation compared with conventional methods.
Why the study?
Does a DBN-DNN-based regression model improve the accuracy of oscillometric blood pressure estimation compared to conventional methods?
Does a DBN-DNN-based regression model improve the accuracy of oscillometric blood pressure estimation compared to conventional methods?
A novel deep learning approach using DBN-DNN improves the accuracy of oscillometric blood pressure estimation from small datasets.
No takes yet. Share an insight, caveat, or question.
May support research accuracy in BP estimation; leaves open clinical validation before practice adoption.
Lee et al. (2016) studied Blood pressure estimation. DBN-DNN-based regression model vs. Conventional methods was evaluated on Standard deviation of error, mean error, and mean absolute error for SBP and DBP. A deep belief network-deep neural network model yielded lower standard deviation of error, mean error, and mean absolute error for blood pressure estimation compared with conventional methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: