RespDiff: An End-to-End Multi-scale RNN Diffusion Model for Respiratory Waveform Estimation from PPG Signals

TL;DR

RespDiff is an innovative end-to-end multi-scale RNN diffusion model that accurately estimates respiratory rate from PPG signals without requiring handcrafted features, demonstrating superior performance on real-world datasets.

Contribution

The paper introduces RespDiff, a novel multi-scale RNN diffusion model that effectively estimates respiratory waveform from PPG signals without manual feature extraction or segment exclusion.

Findings

Achieves a mean absolute error of 1.18 bpm on BIDMC dataset.

Outperforms previous methods with MAE ranging from 1.66 to 2.15 bpm.

Demonstrates robustness in real-world scenarios.

Abstract

Respiratory rate (RR) is a critical health indicator often monitored under inconvenient scenarios, limiting its practicality for continuous monitoring. Photoplethysmography (PPG) sensors, increasingly integrated into wearable devices, offer a chance to continuously estimate RR in a portable manner. In this paper, we propose RespDiff, an end-to-end multi-scale RNN diffusion model for respiratory waveform estimation from PPG signals. RespDiff does not require hand-crafted features or the exclusion of low-quality signal segments, making it suitable for real-world scenarios. The model employs multi-scale encoders, to extract features at different resolutions, and a bidirectional RNN to process PPG signals and extract respiratory waveform. Additionally, a spectral loss term is introduced to optimize the model further. Experiments conducted on the BIDMC dataset demonstrate that RespDiff outperforms notable previous works, achieving a mean absolute error (MAE) of 1.18 bpm for RR estimation while others range from 1.66 to 2.15 bpm, showing its potential for robust and accurate respiratory monitoring in real-world applications.