arXiv：cs.LG· Felix Oury, Harley Day, Karina Mayoral, Ville-Pekka Sepp\"a, Sejal Saglani, Reiko J. Tanaka·· 2 天前AI 评分33
WIPSNet：基于整夜阻抗体积描记的小儿喘息检测深度学习模型
WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography
AI 导读
WIPSNet 是一种基于 3D ResNet 的模型，对整夜阻抗体积描记（IP）信号堆叠连续小波变换尺度图进行小儿喘息检测，在 15 名患者、60 夜、281 小时队列上取得 AUC 0.783±0.026，优于临床指标 EVI（AUC 0.633）、状态空间模型 Mamba 及两种现代睡眠分期架构。
正文
Abstract:Overnight impedance pneumography (IP) is used to monitor paediatric respiratory health. Its current clinical readout, the Expiratory Variability Index (EVI), compresses each IP recording into a single scalar and achieves an AUC of 0.633 for night-level wheeze classification. We introduce Wheeze Impedance Pneumography Scalogram Network (WIPSNet), a 3D ResNet operating on stacked continuous wavelet transform scalograms of overnight IP signals. On a 15-patient cohort (60 nights, 281 hours), WIPSNet achieves an AUC of $0.783 \pm 0.026$, outperforming EVI, a state-space model (Mamba), and two modern sleep-staging architectures. Performance peaks at a volumetric depth corresponding to 32 minutes of temporal context, suggesting that multi-scale temporal aggregation is important for modelling nocturnal respiratory dynamics. Overall, these results indicate that structured time-frequency representations combined with 3D convolutional architectures provide an effective approach for learning from long, irregular physiological time series.
| Comments: | Accepted at the Workshop on Structured Data for Health, ICML 2026. Code: this https URL |
| Subjects: | Machine Learning (cs.LG); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.00398 [cs.LG] |
| (or arXiv:2610.00398v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00398 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Felix Oury [view email]
[v1]
Wed, 30 Sep 2026 11:58:27 UTC (1,185 KB)
来源：arXiv：cs.LG · arxiv.org