BP-DeepONet: A new method for cuffless blood pressure estimation using the physcis-informed DeepONet

TL;DR

This paper introduces BP-DeepONet, a physics-informed neural network framework that predicts continuous arterial blood pressure waveforms by satisfying Navier-Stokes equations and boundary conditions, using meta-learning to optimize parameters.

Contribution

It is the first to predict continuous ABP waveforms with spatial and temporal resolution, incorporating physics-based constraints and meta-learning for parameter estimation.

Findings

Accurately predicts ABP waveforms satisfying physical laws.

Generates realistic reflection waves resembling real measurements.

Handles varying periodic conditions effectively.

Abstract

Cardiovascular diseases (CVDs) are the leading cause of death worldwide, with blood pressure serving as a crucial indicator. Arterial blood pressure (ABP) waveforms provide continuous pressure measurements throughout the cardiac cycle and offer valuable diagnostic insights. Consequently, there is a significant demand for non-invasive and cuff-less methods to measure ABP waveforms continuously. Accurate prediction of ABP waveforms can also improve the estimation of mean blood pressure, an essential cardiovascular health characteristic. This study proposes a novel framework based on the physics-informed DeepONet approach to predict ABP waveforms. Unlike previous methods, our approach requires the predicted ABP waveforms to satisfy the Navier-Stokes equation with a time-periodic condition and a Windkessel boundary condition. Notably, our framework is the first to predict ABP waveforms continuously, both with location and time, within the part of the artery that is being simulated. Furthermore, our method only requires ground truth data at the outlet boundary and can handle periodic conditions with varying periods. Incorporating the Windkessel boundary condition in our solution allows for generating natural physical reflection waves, which closely resemble measurements observed in real-world cases. Moreover, accurately estimating the hyper-parameters in the Navier-Stokes equation for our simulations poses a significant challenge. To overcome this obstacle, we introduce the concept of meta-learning, enabling the neural networks to learn these parameters during the training process.