Transformer-Based Sleep Stage Classification Enhanced by Clinical Information

TL;DR

This paper introduces a Transformer-based sleep staging model that incorporates clinical metadata and expert annotations, significantly improving accuracy and interpretability over PSG-only methods.

Contribution

It presents a novel two-stage architecture that fuses clinical and event-based context with deep learning for enhanced sleep stage classification.

Findings

Contextual fusion improves macro-F1 from 0.7745 to 0.8031

Event annotations contribute the largest accuracy gains

Feature fusion outperforms multi-task learning approaches

Abstract

Manual sleep staging from polysomnography (PSG) is labor-intensive and prone to inter-scorer variability. While recent deep learning models have advanced automated staging, most rely solely on raw PSG signals and neglect contextual cues used by human experts. We propose a two-stage architecture that combines a Transformer-based per-epoch encoder with a 1D CNN aggregator, and systematically investigates the effect of incorporating explicit context: subject-level clinical metadata (age, sex, BMI) and per-epoch expert event annotations (apneas, desaturations, arousals, periodic breathing). Using the Sleep Heart Health Study (SHHS) cohort (n=8,357), we demonstrate that contextual fusion substantially improves staging accuracy. Compared to a PSG-only baseline (macro-F1 0.7745, micro-F1 0.8774), our final model achieves macro-F1 0.8031 and micro-F1 0.9051, with event annotations contributing the largest gains. Notably, feature fusion outperforms multi-task alternatives that predict the same auxiliary labels. These results highlight that augmenting learned representations with clinically meaningful features enhances both performance and interpretability, without modifying the PSG montage or requiring additional sensors. Our findings support a practical and scalable path toward context-aware, expert-aligned sleep staging systems.