WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography

Felix Oury; Harley Day; Karina Mayoral; Ville-Pekka Seppä; Sejal Saglani; Reiko J. Tanaka

cs.LGSep 30, 2026

WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography

Authors: Felix Oury, Harley Day, Karina Mayoral, Ville-Pekka Seppä, Sejal Saglani, Reiko J. Tanaka

Organizations: Department of Computing, Imperial College London, London, United Kingdom · Department of Bioengineering, Imperial College London, London, United Kingdom · National Heart and Lung Institute and Centre for Paediatrics and Child Health, Imperial College London, London, United Kingdom; Department of Respiratory Paediatrics, Royal Brompton Hospital, London, United Kingdom · Icare Finland Ltd, Vantaa, Finland

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.

Figures & tables

Figure 1: WIPSNet framework and architecture. (a) The IP signal is filtered, transformed into scalograms, grouped into 3D volumes, and passed through a 3D CNN; volume-level probabilities are aggregated into a night-level prediction. (b–d) Raw signal, processed signal, and 4-minute scalogram. (e) Volumetric input construction: $D$ consecutive scalograms stacked along the depth axis. (f) The bottleneck 3D ResNet backbone.

Model	Input & backbone	AUC	AUPRC
WIPSNet	CWT + 3D CNN	$\mathbf{.783{\scriptstyle\pm.026}}$	$\mathbf{.634{\scriptstyle\pm.047}}$
AttnSleep	Raw + MRCNN-attn	$.764{\scriptstyle\pm.030}$	$.603{\scriptstyle\pm.048}$
catch22+XGBoost	22 canonical TS features	$.704{\scriptstyle\pm.002}$	$.481{\scriptstyle\pm.002}$
Mamba	Raw + SSM	$.689{\scriptstyle\pm.047}$	$.509{\scriptstyle\pm.060}$
EVI †	Clinical scalar	$.633$	$.433$
SleePyCo	Raw + Pyramid-Transformer	$.577{\scriptstyle\pm.152}$	$.444{\scriptstyle\pm.101}$

Table 1 : Night-level wheeze classification results. Mean

\pm

std over 5 seeds, 15-fold patient-level LOOCV. AUPRC random baseline at our class prevalence is 0.35. Mamba and Mamba-Scalogram both use a 32-min window. † Deterministic; 57/60 valid nights.

Figure 2 : WIPSNet’s depth-scaling behaviour. Both AUC and AUPRC peak at $D{=}8$ (32 min of temporal context) and decline at longer windows, indicating an optimal macro-timescale rather than monotone improvement. Error bars: standard deviation over 5 seeds. Top axis: temporal context in minutes.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Parameter	Search Space	Selected Value
Scalogram window length	2–16 min	60,000 (4 min)
Volume depth $D$	1–10 scalograms	8
Stride (scalogram)	1– $D$ scalograms	8 ( $=D$ , non-overlapping)
Backbone	ResNet / EfficientNet	ResNet
Batch size	{8, 16, 32, 64}	32
Learning rate	$10^{-5}$ – $10^{-2}$	$3.00\times 10^{-4}$

Appendix

Table 2 : WIPSNet hyperparameter search space and selected values.

Parameter	Search Space	Selected Value
Context window $W$ (4-min segments)	{1, 2, 4, 8} sweep	8 ( $=32$ min)
Stride (segments)	$=W$ (non-overlapping)	8
Per-segment length	—	5,000 samples (4 min) 3 3 3 The raw 250 Hz IP signal is downsampled $12\times$ to $\approx$ 20.8 Hz before Mamba, so a 4-min segment is 5,000 samples and a 32-min window is $8\times 5{,}000=40{,}000$ samples. This keeps the SSM sequence length tractable; on the full-rate 480,000-sample window Mamba collapses to near-chance.
Sequence length	$W\times$ seg. length	40,000 samples (32 min)
$d_{\text{model}}$	16–192	32
$d_{\text{state}}$	8–48	32

Appendix

Table 3 : Mamba SSM hyperparameter search space and selected values. The context window

W

(number of consecutive 4-min segments) was swept separately, analogous to the WIPSNet volume depth

D

, while the architecture was tuned by Optuna.

Model	Input & backbone	AUC	AUPRC
WIPSNet-CWT ( $D{=}8$ )	CWT + 3D CNN	$\mathbf{.783\pm.026}$	$\mathbf{.634\pm.047}$
AttnSleep	Raw 1D + MRCNN + attention	$.764\pm.030$	$.603\pm.048$
WIPSNet-CWT ( $D{=}4$ )	CWT + 3D CNN	$.747\pm.032$	$.556\pm.035$
WIPSNet-CWT ( $D{=}1$ )	CWT + 3D CNN	$.744\pm.022$	$.527\pm.026$
WIPSNet-CWT ( $D{=}32$ )	CWT + 3D CNN	$.744\pm.042$	$.546\pm.049$
WIPSNet-CWT ( $D{=}2$ )	CWT + 3D CNN	$.742\pm.035$	$.558\pm.044$

Appendix

Table 4 : All models and ablations, sorted by AUC. Mean

\pm

std over 5 seeds for DL models. AUC is the primary ranking metric; AUPRC reflects performance on the minority (wheeze) class under class imbalance. Depth-sweep rows (

D{\neq}8

) and front-end rows share WIPSNet’s backbone; the headline model is WIPSNet-CWT (

D{=}8

Explore similar work

Deep learning-based detection of cessation of breathing in pre-term infants
Jun 22, 2026Dineo Serame, Lionel Tarassenko, Mauricio VillarroelRespiratory Motion Intensive Care Unit
Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, UK
Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm Reduction in the ICU
Sep 8, 2026Athanasios Papastathopoulos-Katsaros, Alexandra Stavrianidi, Zhandong LiuIntensive Care Unit Alarm Fatigue
Department of Pediatrics, Baylor College of Medicine, Houston, TX, USA · Jan and Dan Duncan Neurological Research Institute, Texas Children’s Hospital, Houston, TX, USA · Institute for Analysis and Numerics, University of Münster, Germany +1
AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts
Dec 16, 2025Niklas Grieger, Jannik Raskob, Siamak Mehrkanoon +1Sleep Electroencephalography
Department of Medical Engineering and Technomathematics, FH Aachen University of Applied Sciences, 52428 Jülich, Germany · Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands · Institute for Data-Driven Technologies, FH Aachen University of Applied Sciences, 52428 Jülich, Germany

Jun 22, 2026, cs.LGJ/K move · Enter open · S save

Deep learning-based detection of cessation of breathing in pre-term infants

Dineo Serame, Lionel Tarassenko, Mauricio Villarroel

Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, UK

Respiratory Motion Intensive Care Unit Remote Photoplethysmography Unsupervised Detection

Open paper AskPDF arXiv

Apnoea of prematurity is characterised by recurrent episodes of cessation of breathing and remains difficult to detect reliably using routinely monitored physiological signals in the Neonatal Intensive Care Unit (NICU). Existing bedside monitors rely primarily on respiratory rate and oxygen saturation thresholds, often generating high false-positive alarm rates and missing short or irregular events. Improving automated detection using routinely acquired clinical signals could enhance identification of clinically meaningful events without additional sensing hardware. We evaluated deep learning-based detection of apnoea-related Cessation Of BrEathing (COBE) events using impedance pneumography (IP), electrocardiography (ECG), and photoplethysmography (PPG) signals from approximately 430 hours of NICU recordings collected from 24 pre-term infants. Three independent reviewers annotated COBE events, producing a dataset of 346 COBE and 608 non-COBE events. We compared a shallow convolutional neural network (CNN), residual networks (ResNets), and a ConvNeXt architecture using an independent held-out test set. Across all architectures, detection performance was influenced more strongly by signal modality than by architectural complexity. Unimodal IP-based models achieved balanced accuracies of 86.8-88.0%, outperforming ECG-derived (62.6-69.7%) and PPG-derived (65.1-66.4%) respiratory surrogates. Multimodal fusion yielded modest improvements over IP alone. The best-performing model, a ConvNeXt architecture combining IP and PPG inputs, achieved 88.7% balanced accuracy and an F1 score of 0.75 on the independent test set. These findings demonstrate that deep learning models applied to routinely monitored NICU signals can reliably detect COBE events and highlight the importance of signal modality in data-constrained neonatal monitoring settings.

Abstract

Explore similar work

Deep learning-based detection of cessation of breathing in pre-term infants

Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm Reduction in the ICU

AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts