Demographic-Aware Transfer Learning for Sleep Stage Classification in Clinical Polysomnography

TL;DR

This study introduces a demographic-aware transfer learning approach for sleep stage classification, significantly improving accuracy by tailoring models to specific patient groups based on gender, age, and OSA severity.

Contribution

The paper presents a novel two-stage training strategy that combines demographic stratification with transfer learning, enhancing sleep staging performance over generic models.

Findings

35 out of 37 fine-tuned models outperform the baseline.

Cohen's kappa improvements ranged from 0.9 to 12.9%.

Demographic-specific models provide more accurate sleep staging.

Abstract

Automated sleep stage classification typically employs a single population-agnostic model, disregarding established demographic variations in sleep architecture. Sleep patterns, however, differ substantially across gender, age, and obstructive sleep apnea (OSA) severity, indicating that a onesize-fits all approach may be suboptimal for diverse clinical populations. In this paper, we propose a two stage training strategy based on demographic stratification and transfer learning framework. We first pretrains a convolutional recurrent model on the full population and then fine tunes it independently for demographic subgroups defined by gender, age, and Apnea-Hypopnea Index (AHI) severity according to the AASM clinical standard. Using the DREAMT dataset comprising 100 clinical subjects and 7 PSG channels, we evaluate 37 fine-tuned configurations across single-axis and two-way demographic combinations. Results demonstrate that 35 of the 37 fine-tuned models outperform the baseline, with Cohen's kappa improvements ranging from 0.9 to 12.9%. These findings indicate that stratified fine tuning tailored to specific patient demographics yields substantially more accurate sleep staging than a single generalized model, offering a practical and clinically grounded paradigm for personalized sleep assessment.