Key result
BP-Net estimates continuous arterial blood pressure from PPG signals with ~5 mmHg systolic absolute error.
Why the study?
Current non-invasive, cuffless continuous blood pressure monitoring approaches rely on explicit feature engineering around fingertip photoplethysmogram signals.
Does the BP-Net deep learning model accurately estimate continuous arterial blood pressure from photoplethysmogram waveforms?
Does the BP-Net deep learning model accurately estimate continuous arterial blood pressure from photoplethysmogram waveforms?
BP-Net provides an efficient, end-to-end deep learning approach for continuous, cuffless blood pressure estimation from PPG signals with high accuracy and low inference time suitable for edge devices.
Supports cuffless wearable BP monitoring on edge devices; leaves open prospective validation before clinical use.
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.
No takes yet. Share an insight, caveat, or question.
K et al. (2021) studied Blood pressure estimation (n=948). BP-Net (U-Net deep learning architecture) vs. Invasive Arterial Line measurements (ground truth) was evaluated on Mean Absolute Error (MAE) for Systolic Blood Pressure (SBP) and Diastolic Blood Pressure (DBP). BP-Net estimated continuous arterial blood pressure from photoplethysmogram signals with a Mean Absolute Error of 5.16 mmHg for systolic and 2.89 mmHg for diastolic blood pressure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: