Physiology as Language: Translating Respiration to Sleep EEG

TL;DR

This paper presents a novel method to generate sleep EEG signals from respiration data using a waveform-conditional generative model, enabling accurate sleep analysis and remote neurological assessment.

Contribution

Introduces a cross-physiology translation framework that synthesizes EEG from respiration signals, supporting multiple sleep-related tasks and enabling contactless sleep monitoring.

Findings

Achieves 7% MAE in EEG spectrogram reconstruction.

Supports age, sex, and sleep staging with performance close to real EEG.

Generalizes to wireless RF signals for contactless sleep EEG synthesis.

Abstract

This paper introduces a novel cross-physiology translation task: synthesizing sleep electroencephalography (EEG) from respiration signals. To address the significant complexity gap between the two modalities, we propose a waveform-conditional generative framework that preserves fine-grained respiratory dynamics while constraining the EEG target space through discrete tokenization. Trained on over 28,000 individuals, our model achieves a 7% Mean Absolute Error in EEG spectrogram reconstruction. Beyond reconstruction, the synthesized EEG supports downstream tasks with performance comparable to ground truth EEG on age estimation (MAE 5.0 vs. 5.1 years), sex detection (AUROC 0.81 vs. 0.82), and sleep staging (Accuracy 0.84 vs. 0.88), significantly outperforming baselines trained directly on breathing. Finally, we demonstrate that the framework generalizes to contactless sensing by synthesizing EEG from wireless radio-frequency reflections, highlighting the feasibility of remote, non-contact neurological assessment during sleep.