arXiv cs.AI· Riku Huttunen, Samu Kainulainen, Matias Rusanen, Sami Myllymaa, Juha T\"oyr\"as, Timo Lepp\"anen, Henri Korkalainen·· 1 小时前AI 评分38
PSG-GAN 学会睡眠呼吸暂停信号动态,用合成 PSG 数据支持 AI 训练
From real to synthetic: PSG-GAN learns sleep apnea signal dynamics for AI training
AI 导读
研究者开发了生成对抗网络 PSG-GAN,可共同合成多通道 PSG 信号的长片段,涵盖阻塞性睡眠呼吸暂停(OSA)的复杂特征。合成信号在脑电、眼电频段功率分布上与真实数据一致,并能复现呼吸阻塞期间光电容积脉搏波心率的互动变化。
正文 · 原文
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 this https URL.
| Comments: | 23 pages, 9 figures |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Medical Physics (physics.med-ph) |
| Cite as: | arXiv:2611.24436 [cs.AI] |
| (or arXiv:2611.24436v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24436 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Riku Huttunen [view email]
[v1]
Wed, 18 Nov 2026 13:53:05 UTC (705 KB)
来源:arXiv cs.AI · arxiv.org