Contactless Oxygen Monitoring with Gated Transformer

TL;DR

This paper introduces a contactless method for monitoring blood oxygen levels at home by analyzing room radio signals with a novel neural network, enabling accurate, wearable-free health assessment.

Contribution

The paper presents Gated BERT-UNet, a neural network that adapts to individual physiological indices to accurately estimate oxygen levels from radio signals.

Findings

Achieves high accuracy on medical and radio datasets

Effectively extracts respiration signals from radio bounce data

Adapts to patient-specific indices for improved predictions

Abstract

With the increasing popularity of telehealth, it becomes critical to ensure that basic physiological signals can be monitored accurately at home, with minimal patient overhead. In this paper, we propose a contactless approach for monitoring patients' blood oxygen at home, simply by analyzing the radio signals in the room, without any wearable devices. We extract the patients' respiration from the radio signals that bounce off their bodies and devise a novel neural network that infers a patient's oxygen estimates from their breathing signal. Our model, called \emph{Gated BERT-UNet}, is designed to adapt to the patient's medical indices (e.g., gender, sleep stages). It has multiple predictive heads and selects the most suitable head via a gate controlled by the person's physiological indices. Extensive empirical results show that our model achieves high accuracy on both medical and radio datasets.