Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation

TL;DR

This paper introduces a source-free unsupervised domain adaptation framework for personalized sleep staging, enabling models to adapt to new individuals without source data, improving generalization across diverse subjects.

Contribution

The proposed SF-UIDA framework is the first to enable source-free, unsupervised adaptation for personalized sleep staging, enhancing model applicability in clinical settings.

Findings

Achieved state-of-the-art performance on three public datasets.

Effectively adapts models to new individuals without source data.

Improves generalization of sleep staging models across subjects.

Abstract

Sleep staging is crucial for assessing sleep quality and diagnosing related disorders. Recent deep learning models for automatic sleep staging using polysomnography often suffer from poor generalization to new subjects because they are trained and tested on the same labeled datasets, overlooking individual differences. To tackle this issue, we propose a novel Source-Free Unsupervised Individual Domain Adaptation (SF-UIDA) framework. This two-step adaptation scheme allows the model to effectively adjust to new unlabeled individuals without needing source data, facilitating personalized customization in clinical settings. Our framework has been applied to three established sleep staging models and tested on three public datasets, achieving state-of-the-art performance.