# Cross-Modality Transfer Learning from PSG to FMCW Radar for Event-Level Apnea–Hypopnea Segmentation

## TL;DR

This paper introduces a deep learning method to detect sleep apnea using radar, reducing reliance on costly sleep studies.

## Contribution

A novel cross-modality transfer learning framework for apnea detection using FMCW radar, pre-trained on PSG data.

## Key findings

- The model achieved an F1-score of 0.8167±0.0052 for apnea–hypopnea event detection using FMCW radar.
- PSG-to-radar transfer learning enabled accurate and scalable sleep apnea screening in home settings.
- Temporal post-processing improved event-level detection and AHI estimation from radar data.

## Abstract

Sleep apnea–hypopnea syndrome (SAHS) is a common sleep-related breathing disorder associated with substantial cardiovascular and neurocognitive risks. Although polysomnography (PSG) remains the clinical gold standard for diagnosis, its cost, operational burden, and limited accessibility hinder scalable and longitudinal home monitoring. Frequency-modulated continuous-wave (FMCW) radar provides unobtrusive, non-contact respiration sensing, yet radar-based event detection is often constrained by scarce annotations and pronounced domain shifts relative to PSG signals. In this work, we propose a deep learning framework for apnea–hypopnea event detection from FMCW radar that combines a 1D U-Net segmentation backbone with multi-head self-attention (MHSA) and cross-modality transfer learning. The model was first pre-trained on a large public PSG dataset to learn transferable respiratory-event representations and then fine-tuned on a smaller clinically annotated radar respiration dataset using synchronized PSG labels. It produced per-sample event probabilities, which were further refined via temporal post-processing to generate event-level detections and apnea–hypopnea index (AHI) estimates. Experimental results demonstrate strong performance in the radar domain, achieving precision of 0.8137±0.0332, recall of 0.8369±0.0470, and an F1-score of 0.8167±0.0052. Overall, these results indicate that PSG-to-radar transfer learning enables accurate, low-cost, and non-contact sleep apnea screening, supporting scalable longitudinal monitoring in home-like settings.