{"slug": "wipsnet-deep-learning-for-paediatric-wheeze-detection-from-overnight-impedance", "title": "WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography", "summary": "WIPSNet, a 3D ResNet operating on stacked continuous wavelet transform scalograms of overnight impedance pneumography (IP) signals, achieved an AUC of 0.783 ± 0.026 for night-level paediatric wheeze classification, according to a new arXiv paper (arXiv:2610.00398v1). The model outperformed the current clinical readout, the Expiratory Variability Index (EVI), which scores an AUC of 0.633, as well as a state-space model (Mamba) and two modern sleep-staging architectures on a 15-patient cohort of 60 nights and 281 hours. Performance peaked at a volumetric depth corresponding to 32 minutes of temporal context, indicating that multi-scale temporal aggregation matters for modelling nocturnal respiratory dynamics.", "body_md": "arXiv:2610.00398v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/wipsnet-deep-learning-for-paediatric-wheeze-detection-from-overnight-impedance", "canonical_source": "https://www.machinebrief.com/news/wipsnet-deep-learning-for-paediatric-wheeze-detection-from-o-a0k5", "published_at": "2026-10-03 04:00:00+00:00", "updated_at": "2026-10-03 04:38:27.852371+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "neural-networks"], "entities": ["WIPSNet", "Expiratory Variability Index", "Mamba", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/wipsnet-deep-learning-for-paediatric-wheeze-detection-from-overnight-impedance", "markdown": "https://wpnews.pro/news/wipsnet-deep-learning-for-paediatric-wheeze-detection-from-overnight-impedance.md", "text": "https://wpnews.pro/news/wipsnet-deep-learning-for-paediatric-wheeze-detection-from-overnight-impedance.txt", "jsonld": "https://wpnews.pro/news/wipsnet-deep-learning-for-paediatric-wheeze-detection-from-overnight-impedance.jsonld"}}