Key result
Explainable deep learning using a reduced EEG montage improves neonatal seizure detection recall by ~43%.
Why the study?
Gold-standard continuous video-EEG for neonatal seizure detection requires clinical expertise and resource-rich settings, highlighting a need for cost-effective automated techniques with reduced montages.
Does an explainable deep learning model with reduced EEG montage improve neonatal seizure detection performance?
Does an explainable deep learning model with reduced EEG montage improve neonatal seizure detection performance?
Effect estimate: Absolute improvement of 8.31% in AUC and 42.86% in recall
A novel explainable deep learning model using a reduced EEG montage significantly improves AUC and recall for real-time neonatal seizure detection.
May support reduced-montage EEG for neonatal seizure detection; leaves open prospective validation before clinical adoption.
The neonatal period is the most vulnerable time for the development of seizures. Seizures in the immature brain lead to detrimental consequences, therefore require early diagnosis. The gold -standard for neonatal seizure detection currently relies on continuous video-EEG monitoring; which involves recording multi-channel electroencephalogram (EEG) alongside real-time video monitoring within a neonatal intensive care unit (NICU). However, video-EEG monitoring technology requires clinical expertise and is often limited to technologically advanced and resourceful settings. Cost-effective new techniques could help the medical fraternity make an accurate diagnosis and advocate treatment without delay. In this work, a novel explainable deep learning model to automate the neonatal seizure detection process with a reduced EEG montage is proposed, which employs convolutional nets, graph attention layers, and fully connected layers. Beyond its ability to detect seizures in real time with a reduced montage, this model offers the unique advantage of real-time interpretability. By evaluating the performance on the Zenodo dataset with 10-fold cross-validation, the presented model achieves an absolute improvement of 8.31% and 42.86% in area under curve (AUC) and recall, respectively.
No takes yet. Share an insight, caveat, or question.
Udayantha et al. (2024) studied Neonatal Seizures. Explainable deep learning model with reduced EEG montage was evaluated on Area under curve (AUC) and recall for seizure detection (Absolute improvement of 8.31% in AUC and 42.86% in recall). An explainable deep learning model using a reduced EEG montage achieved an absolute improvement of 8.31% in AUC and 42.86% in recall for neonatal seizure detection.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: