sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals

TL;DR

sleep2vec is a foundation model that learns a unified, robust representation of heterogeneous nocturnal biosignals through cross-modal alignment, improving sleep staging and clinical assessments despite sensor heterogeneity and dropout.

Contribution

It introduces sleep2vec, a contrastively pre-trained model that aligns multiple biosignal modalities using metadata-aware objectives, advancing unified modeling of nocturnal biosignals.

Findings

Outperforms strong baselines in sleep staging and clinical outcome tasks.

Remains robust with any subset of available modalities and sensor dropout.

Characterizes scaling laws for nocturnal biosignals with respect to modality diversity and model capacity.

Abstract

Tasks ranging from sleep staging to clinical diagnosis traditionally rely on standard polysomnography (PSG) devices, bedside monitors and wearable devices, which capture diverse nocturnal biosignals (e.g., EEG, EOG, ECG, SpO$_2$). However, heterogeneity across devices and frequent sensor dropout pose significant challenges for unified modelling of these multimodal signals. We present \texttt{sleep2vec}, a foundation model for diverse and incomplete nocturnal biosignals that learns a shared representation via cross-modal alignment. \texttt{sleep2vec} is contrastively pre-trained on 42,249 overnight recordings spanning nine modalities using a \textit{Demography, Age, Site \& History-aware InfoNCE} objective that incorporates physiological and acquisition metadata (\textit{e.g.}, age, gender, recording site) to dynamically weight negatives and mitigate cohort-specific shortcuts. On downstream sleep staging and clinical outcome assessment, \texttt{sleep2vec} consistently outperforms strong baselines and remains robust to any subset of available modalities and sensor dropout. We further characterize, to our knowledge for the first time, scaling laws for nocturnal biosignals with respect to modality diversity and model capacity. Together, these results show that unified cross-modal alignment, coupled with principled scaling, enables label-efficient, general-purpose modelling of real-world nocturnal biosignals.