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

2026-05-04

AI Summary

This study addresses the limited generalizability of existing automated sleep staging models, which often overlook demographic heterogeneity such as sex, age, and severity of obstructive sleep apnea (OSA). To bridge this gap, the authors propose a demographic-stratified transfer learning framework: a convolutional recurrent neural network is first pretrained on multi-channel polysomnography (PSG) data from a diverse population, then fine-tuned separately on subgroups stratified by sex, age, and apnea–hypopnea index (AHI) levels. Evaluated across 37 configurations, the proposed approach outperforms baseline models in 35 cases, achieving Cohen’s kappa improvements ranging from 0.9% to 12.9%. These results demonstrate a significant enhancement in personalized sleep staging accuracy, effectively integrating clinical standards with deep learning methodologies.

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.

Problem

• sleep stage classification
• demographic variation
• polysomnography
• obstructive sleep apnea
• personalized sleep assessment

Innovation

• demographic-aware
• transfer learning
• sleep stage classification
• stratified fine-tuning
• clinical polysomnography