Sleep apnea detection in pediatric LT-NIV via a hybrid LSTM-machine learning framework
5 affiliations
- 1Mathematics Area, mathLab, SISSA, Via Bonomea, 265, Trieste, 34136, Friuli-Venezia Giulia, Italy; Corresponding author.
- 2Institute for Maternal and Child Health-IRCCS “Burlo Garofolo”, Via dell’Istria, 65, Trieste, 34137, Italy
- 3Department of spinal surgery and Pain managment Krankenhaus Neuwer, Dünner Str. 214-216, Mönchengladbach, 41066, Germany
- 4Institute for Maternal and Child Health-IRCCS “Burlo Garofolo”, Via dell’Istria, 65, Trieste, 34137, Italy; Department of Medical, Surgical and Health Sciences, University of Trieste, Strada di Fiume, 447, 34129, Trieste, 34129, Italy
- 5Mathematics Area, mathLab, SISSA, Via Bonomea, 265, Trieste, 34136, Friuli-Venezia Giulia, Italy
Abstract
For pediatric patients with respiratory insufficiency, long-term non-invasive ventilation (LT-NIV) represents an essential treatment. Despite significant technological progress, the commercial built-in ventilator software has structural limitations: its automatic scoring algorithms are typically calibrated for adult respiratory patterns, failing to detect the high respiratory rate variability inherent to children. As a result, clinicians must perform a manual data review to identify episodes of obstructive sleep apnea. While Machine Learning (ML) has demonstrated significant potential in identifying these events, most studies focus on adults and employ multi-channel polysomnography data. Addressing this, we investigated automated methods for sleep apnea detection using only a single-channel respiratory signal from built-in ventilator software. Therefore, we propose a novel hybrid approach combining a Bidirectional Long Short-Term Memory (BiLSTM) network with a Feature Engineering-based ML ensemble. Experimental results, validated through a Leave-One-Out strategy, demonstrate that the hybrid model can identify sleep apnea events despite the high variability in pediatric respiratory rates and the significant class imbalance within the dataset. The findings provide encouraging evidence for the potential use of the proposed approach as a decision-support tool for automated analysis of respiratory signals in pediatric LT-NIV. However, prospective validation on larger and more diverse pediatric cohorts will be necessary before clinical deployment.
Related
- Machine Learning-Based Fatigue Detection from EEG Signals: A Methodological Pilot Framework with Potential for Nursing Applications
- Hybrid quantum-classical machine learning for industrial multi-anomaly detection via single acoustic sensor
- Predicting atropine treatment response heterogeneity in pediatric myopia using explainable machine learning: an on-treatment longitudinal monitoring framework
- Hybrid machine learning driven optimization of multilayer SPR sensor for high sensitivity milk fat detection
- An EfficientNet hybrid deep learning detection framework of network intrusion with an optimized mixture-of-experts architecture
BibTeX
@article{meneghetti2026sleep,
title = {{Sleep apnea detection in pediatric LT-NIV via a hybrid LSTM-machine learning framework}},
author = {Laura Meneghetti and Sergio Ghirardo and Alberto Favero and Francesca Policastro and Alessandro Amaddeo and Gianluigi Rozza},
journal = {Computer Methods and Programs in Biomedicine Update},
year = {2026},
month = oct,
doi = {10.1016/j.cmpbup.2026.100273},
url = {https://doi.org/10.1016/j.cmpbup.2026.100273},
note = {CC BY},
}
RIS
TY - JOUR
TI - Sleep apnea detection in pediatric LT-NIV via a hybrid LSTM-machine learning framework
AU - Laura Meneghetti
AU - Sergio Ghirardo
AU - Alberto Favero
AU - Francesca Policastro
AU - Alessandro Amaddeo
AU - Gianluigi Rozza
PY - 2026
DA - 2026/10/30
JO - Computer Methods and Programs in Biomedicine Update
DO - 10.1016/j.cmpbup.2026.100273
UR - https://doi.org/10.1016/j.cmpbup.2026.100273
AB - For pediatric patients with respiratory insufficiency, long-term non-invasive ventilation (LT-NIV) represents an essential treatment. Despite significant technological progress, the commercial built-in ventilator software has structural limitations: its automatic scoring algorithms are typically calibrated for adult respiratory patterns, failing to detect the high respiratory rate variability inherent to children. As a result, clinicians must perform a manual data review to identify episodes of obstructive sleep apnea. While Machine Learning (ML) has demonstrated significant potential in identifying these events, most studies focus on adults and employ multi-channel polysomnography data. Addressing this, we investigated automated methods for sleep apnea detection using only a single-channel respiratory signal from built-in ventilator software. Therefore, we propose a novel hybrid approach combining a Bidirectional Long Short-Term Memory (BiLSTM) network with a Feature Engineering-based ML ensemble. Experimental results, validated through a Leave-One-Out strategy, demonstrate that the hybrid model can identify sleep apnea events despite the high variability in pediatric respiratory rates and the significant class imbalance within the dataset. The findings provide encouraging evidence for the potential use of the proposed approach as a decision-support tool for automated analysis of respiratory signals in pediatric LT-NIV. However, prospective validation on larger and more diverse pediatric cohorts will be necessary before clinical deployment.
SN - 2666-9900
ER -