Short-horizon neonatal seizure prediction using EEG-based deep learning

Jonathan Kim, Edilberto Amorim, Vikram R Rao, Hannah C Glass and Danilo Bernardo

PLOS Digital Health, 2025, vol. 4, issue 7, 1-16

Abstract: Strategies to predict neonatal seizure risk have typically focused on long-term static predictions with prediction horizons spanning days during the acute postnatal period. Higher temporal resolution or short-horizon neonatal seizure prediction, on the time-frame of minutes, remains unexplored. Here, we investigated quantitative electroencephalography (QEEG) based deep learning (DL) for short-horizon seizure prediction. We used two publicly available EEG seizure datasets with a total of 132 neonates containing a total of 281 hours of EEG data. We benchmarked current state-of-the-art time-series DL methods for seizure prediction, identifying convolutional LSTM (ConvLSTM) as having the strongest performance at preictal state classification. We assessed ConvLSTM performance in a seizure alarm system over varying short-range (1–7 minutes) seizure prediction horizons (SPH) and seizure occurrence periods (SOP) and identified optimal performance at SPH 3 min and SOP 7 min, with AUROC 0.8. At 80% sensitivity, false detection rate was 0.68 events/hour with time-in-warning of 0.36. Model calibration was moderate, with an expected calibration error of 0.106. These findings establish the feasibility of short-horizon neonatal seizure prediction and warrant the need for further validation.Author summary: Neonatal seizures are associated with substantial long-term morbidity and mortality. A promising strategy to improve neonatal clinical outcomes has focused on developing EEG-based machine learning models to identify seizure-prone neonates to reduce the time to seizure diagnosis and treatment. Such work has typically focused on identifying neonates at risk of seizure, providing static predictions, rather than dynamic predictions containing information of when the seizure may occur. Here, we focus on short-term seizure prediction to advance the temporal resolution of neonatal seizure prediction. We present a deep learning approach that leverages quantitative EEG to predict seizures on the order of minutes. We demonstrate that short-term seizure prediction—down to a 7-minute horizon—is accurate. Our results suggest that precise real-time estimation of dynamic seizure risk is feasible, potentially enabling improved triage of resources to neonates at higher risk for seizures and earlier clinical intervention for neonatal seizures. However, further development and external validation are warranted.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000890 (text/html)
https://journals.plos.org/digitalhealth/article/fi ... 00890&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pdig00:0000890

DOI: 10.1371/journal.pdig.0000890

Access Statistics for this article

More articles in PLOS Digital Health from Public Library of Science
Bibliographic data for series maintained by digitalhealth ().