Using Legacy Polysomnography Data to Train a Radar System to Quantify Sleep in Older Adults and People living with Dementia

TL;DR

This study develops a deep transfer learning framework that leverages existing polysomnography data to train radar systems for accurate, unobtrusive sleep staging in older adults and individuals with dementia, addressing data scarcity and variability.

Contribution

The paper introduces a novel domain adaptation approach combining deep transfer learning and adversarial training to improve radar-based sleep staging accuracy across diverse cohorts.

Findings

Achieved 79.5% accuracy and 0.65 Kappa in sleep stage classification.

Significantly improved performance of radar sleep staging with transfer learning.

Validated effectiveness on a real-world dataset of older adults, including those with early Alzheimer’s.

Abstract

Objective: Ultra-wideband radar technology offers a promising solution for unobtrusive and cost-effective in-home sleep monitoring. However, the limited availability of radar sleep data poses challenges in building robust models that generalize across diverse cohorts and environments. This study proposes a novel deep transfer learning framework to enhance sleep stage classification using radar data. Methods: An end-to-end neural network was developed to classify sleep stages based on nocturnal respiratory and motion signals. The network was trained using a combination of large-scale polysomnography (PSG) datasets and radar data. A domain adaptation approach employing adversarial learning was utilized to bridge the knowledge gap between PSG and radar signals. Validation was performed on a radar dataset of 47 older adults (mean age: 71.2), including 18 participants with prodromal or mild Alzheimer disease. Results: The proposed network structure achieves an accuracy of 79.5% with a Kappa value of 0.65 when classifying wakefulness, rapid eye movement, light sleep and deep sleep. Experimental results confirm that our deep transfer learning approach significantly enhances automatic sleep staging performance in the target domain. Conclusion: This method effectively addresses challenges associated with data variability and limited sample size, substantially improving the reliability of automatic sleep staging models, especially in contexts where radar data is limited. Significance: The findings underscore the viability of UWB radar as a nonintrusive, forward-looking sleep assessment tool that could significantly benefit care for older people and people with neurodegenerative disorders.