PSG-GAN generates synthetic sleep apnea signals for training diagnostic models
Researchers developed PSG-GAN, a generative adversarial network that co-synthesizes longer segments of multiple polysomnography signals with characteristics of obstructive sleep apnea. The synthetic signals appeared realistic, preserved sleep-stage band-power distributions, and mirrored interactions such as heart-rate changes around breathing obstructions. A scoring model trained only on automatically scored synthetic signals reached Cohen's kappa of 0.71 and 0.63 for sleep staging and 0.57 and 0.60 for respiratory event segmentation on test sets of healthy volunteers and OSA patients. The source code is publicly available.
It shows a concrete generative-AI approach for producing multi-signal synthetic clinical data that can train sleep-diagnostic models without relying solely on sensitive real recordings.
Comments & Questions (0)
No comments yet
Be the first to comment!