Back to AI News
arxiv

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.

AI Brief

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.

arXiv:2611.24436v1 Announce Type: new Abstract: Synthetic polysomnography (PSG) data has great potential in healthcare applications, for example in substituting real data that is sensitive and challenging to collect. Previous research on synthetic PSG data has been largely focused on short segments of individual signals, overlooking the inter-signal dynamics related to sleep disorders. In this study, we developed a generative adversarial network (PSG-GAN) for co-synthesizing longer segments of multiple PSG signals with diverse and complex characteristics typical of obstructive sleep apnea (OSA). The synthetic signals appeared realistic, and the electroencephalography and electrooculography band powers were similarly distributed across sleep stages. Moreover, the PSG-GAN learned to mirror signal interactions such as changes in photoplethysmography-based heart rate during and after breathing obstructions. An automatic scoring model trained solely with automatically scored synthetic signals reached good performance on sleep staging (\k{appa}=0.71 and 0.63) and respiratory event segmentation (\k{appa}=0.57 and 0.60), on two test sets consisting of healthy volunteers and OSA patients, respectively. This demonstrates the potential of synthetic data in supporting algorithm development for sleep diagnostics. The source code is available at https://github.com/rikuhuttunen/psg-gan.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!