BP-Net: Efficient Deep Learning for Continuous Arterial Blood Pressure Estimation using Photoplethysmogram

TL;DR

BP-Net is an end-to-end deep learning model that accurately estimates blood pressure from PPG signals, achieving high standards and real-time performance on low-power devices.

Contribution

The paper introduces BP-Net, a novel deep learning approach that eliminates explicit feature engineering for cuffless BP estimation from PPG signals.

Findings

Achieves Grade A for DBP and MAP, Grade B for SBP under BHS standards.

Meets AAMI criteria with MAE of 5.16 mmHg (SBP) and 2.89 mmHg (DBP).

Runs inference in 4.25 ms on Raspberry Pi 4.

Abstract

Blood pressure (BP) is one of the most influential bio-markers for cardiovascular diseases and stroke; therefore, it needs to be regularly monitored to diagnose and prevent any advent of medical complications. Current cuffless approaches to continuous BP monitoring, though non-invasive and unobtrusive, involve explicit feature engineering surrounding fingertip Photoplethysmogram (PPG) signals. To circumvent this, we present an end-to-end deep learning solution, BP-Net, that uses PPG waveform to estimate Systolic BP (SBP), Mean Average Pressure (MAP), and Diastolic BP (DBP) through intermediate continuous Arterial BP (ABP) waveform. Under the terms of the British Hypertension Society (BHS) standard, BP-Net achieves Grade A for DBP and MAP estimation and Grade B for SBP estimation. BP-Net also satisfies Advancement of Medical Instrumentation (AAMI) criteria for DBP and MAP estimation and achieves Mean Absolute Error (MAE) of 5.16 mmHg and 2.89 mmHg for SBP and DBP, respectively. Further, we establish the ubiquitous potential of our approach by deploying BP-Net on a Raspberry Pi 4 device and achieve 4.25 ms inference time for our model to translate the PPG waveform to ABP waveform.