U-NeXt: General-purpose event detection for neonatal EEG
Abstract
We developed U-NeXt, a general framework for neonatal electroencephalography (EEG) event detection based on semantic segmentation. Its convolutional encoder-decoder directly segments individual channels using long input segments to preserve temporal context. A shared architecture and training framework were developed using low-voltage interval, artefact, and seizure datasets containing 51, 98, and 278 neonates, respectively, comprising over 11,000 hours of EEG and 82,000 annotated events. Performance was compared with task-specific ConvNeXt classifiers. For seizure detection, we also evaluated U-NeXt+, trained on an expanded dataset. Both U-NeXt variants and the ConvNeXt baseline were evaluated on two independent held-out seizure datasets, Helsinki and Cork, comprising 130 neonates, with recordings annotated by three experts. U-NeXt improved detection across all three event types, with particular gains in sensitivity for short events. U-NeXt+ achieved Matthews correlation coefficients of 0.862 and 0.891 on Helsinki and Cork, respectively, and improved hourly seizure burden correlations by 30-40% relative to ConvNeXt. U-NeXt+ met the criterion for expert-level performance on both datasets (p < 0.001). In separate computational benchmarks, U-NeXt reduced batch inference time relative to ConvNeXt by 254-fold on a central processing unit and 200-fold on a graphics processing unit. A common segmentation framework improves detection across diverse neonatal EEG event types while substantially reducing inference time. Accurate seizure burden estimates and performance comparable to expert reviewers support its potential use in continuous monitoring and clinical decision support.
Related
- GMAP: A General Purpose Hamiltonian Mapping Program for Computational Spectroscopy
- vibe‐qc: An Open‐Source, General‐Purpose Electronic‐Structure Code for Molecules and Solids Developed With Generative AI
- Assessing the Transferability of General-Purpose MachineLearning Interatomic Potentials for Heterogeneous Catalysis with HetCat26
- General-purpose equations of state for hadron-quark matter: first application to accretion-induced phase transitions in neutron stars
- QMClaw: A Scalable General-purpose Framework for Quantum Measurement and Control
BibTeX
@misc{hogan2026unext,
title = {{U-NeXt: General-purpose event detection for neonatal EEG}},
author = {Robert Hogan and Sean R. Mathieson and Aurel Luca and Soraia Ventura and Sean Griffin and Geraldine B. Boylan and John M. O'Toole},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32811},
eprint = {2610.32811},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32811},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - U-NeXt: General-purpose event detection for neonatal EEG
AU - Robert Hogan
AU - Sean R. Mathieson
AU - Aurel Luca
AU - Soraia Ventura
AU - Sean Griffin
AU - Geraldine B. Boylan
AU - John M. O'Toole
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32811
UR - https://arxiv.org/abs/2610.32811
AB - We developed U-NeXt, a general framework for neonatal electroencephalography (EEG) event detection based on semantic segmentation. Its convolutional encoder-decoder directly segments individual channels using long input segments to preserve temporal context. A shared architecture and training framework were developed using low-voltage interval, artefact, and seizure datasets containing 51, 98, and 278 neonates, respectively, comprising over 11,000 hours of EEG and 82,000 annotated events. Performance was compared with task-specific ConvNeXt classifiers. For seizure detection, we also evaluated U-NeXt+, trained on an expanded dataset. Both U-NeXt variants and the ConvNeXt baseline were evaluated on two independent held-out seizure datasets, Helsinki and Cork, comprising 130 neonates, with recordings annotated by three experts. U-NeXt improved detection across all three event types, with particular gains in sensitivity for short events. U-NeXt+ achieved Matthews correlation coefficients of 0.862 and 0.891 on Helsinki and Cork, respectively, and improved hourly seizure burden correlations by 30-40% relative to ConvNeXt. U-NeXt+ met the criterion for expert-level performance on both datasets (p < 0.001). In separate computational benchmarks, U-NeXt reduced batch inference time relative to ConvNeXt by 254-fold on a central processing unit and 200-fold on a graphics processing unit. A common segmentation framework improves detection across diverse neonatal EEG event types while substantially reducing inference time. Accurate seizure burden estimates and performance comparable to expert reviewers support its potential use in continuous monitoring and clinical decision support.
ER -