Contactless Oxygen Monitoring with Gated Transformer
This enables non-invasive telehealth monitoring for patients, reducing the need for wearables, but it is incremental as it builds on existing radio signal analysis methods.
The paper tackles the problem of contactless blood oxygen monitoring at home by analyzing radio signals to extract respiration and infer oxygen levels, achieving high accuracy on medical and radio datasets.
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.