October 4, 2020SensorsOpen Access

Generalized Deep Neural Network Model for Cuffless Blood Pressure Estimation with Photoplethysmogram Signal Only

View Full Paper

Ask AI

Bookmark

Why the study?

To enhance usability and reduce sensor cost, researchers sought to establish a generalized blood pressure estimation model using only photoplethysmogram signals rather than combined ECG and PPG data.

Does a deep neural network model using only PPG signals accurately estimate blood pressure?

Structured PICO

Does a deep neural network model using only PPG signals accurately estimate blood pressure?

Population

9000 subjects from a blood pressure database

Intervention

Deep neural network model extracting 32 features exclusively from photoplethysmogram (PPG) signals for blood pressure estimation

Outcome

Blood pressure estimation accuracy evaluated by root mean square error (RMSE), mean absolute error (MAE), AAMI standard, and BHS standardsurrogate

A deep neural network model using only PPG signals can estimate blood pressure with high accuracy, potentially enabling low-cost cuffless BP monitoring.

Implication

PPG-only deep learning model supports cuffless BP estimation; leaves open prospective validation before any clinical consideration.

Abstract

Due to the growing public awareness of cardiovascular disease (CVD), blood pressure (BP) estimation models have been developed based on physiological parameters extracted from both electrocardiograms (ECGs) and photoplethysmograms (PPGs). Still, in order to enhance the usability as well as reduce the sensor cost, researchers endeavor to establish a generalized BP estimation model using only PPG signals. In this paper, we propose a deep neural network model capable of extracting 32 features exclusively from PPG signals for BP estimation. The effectiveness and accuracy of our proposed model was evaluated by the root mean square error (RMSE), mean absolute error (MAE), the Association for the Advancement of Medical Instrumentation (AAMI) standard and the British Hypertension Society (BHS) standard. Experimental results showed that the RMSEs in systolic blood pressure (SBP) and diastolic blood pressure (DBP) are 4.643 mmHg and 3.307 mmHg, respectively, across 9000 subjects, with 80.63% of absolute errors among estimated SBP records lower than 5 mmHg and 90.19% of absolute errors among estimated DBP records lower than 5 mmHg. We demonstrated that our proposed model has remarkably high accuracy on the largest BP database found in the literature, which shows its effectiveness compared to some prior works.