A deep learning method for continuous noninvasive blood pressure monitoring using photoplethysmography.

Researchers

Journal

Modalities

Models

Abstract

The aim of the study is to investigate continuous blood pressure waveforms estimation from plethysmography (PPG) signal, thus can provide more human cardiovascular status information than traditional cuff-based methods.the proposed method utilizes the feature extraction ability of convolution neural network to estimate BP from PPG signals without the need for waveform analysis and signal feature extraction.the network achieved mean absolute errors and standard deviations of 2.55 ± 3.92 mmHg for systolic blood pressure (SBP), 1.66 ± 2.76 mmHg for diastolic blood pressure (DBP), and 2.52 ± 3.02 mmHg for overall pressure waveform. The results meet the best level under British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI) protocols.the proposed method shows promise for non-invasive continuous blood pressure monitoring in hospital wards and daily life, which can assist in clinical diagnosis, disease treatment, and rehabilitation.© 2023 Institute of Physics and Engineering in Medicine.