A Patient-Independent Neonatal Seizure Prediction Model Using Reduced Montage EEG and ECG

2025-11-17

AI Summary

Neonatal seizures exhibit subtle clinical manifestations, leading to frequent misdiagnosis and secondary brain injury. To address the limitations of current continuous EEG (cEEG) monitoring—namely, heavy reliance on expert interpretation, high cost, and lack of real-time predictive capability—this study proposes a cross-subject generalizable, unsupervised seizure prediction framework. The method fuses multi-channel EEG and ECG signals, extracts Mel-frequency cepstral coefficients (MFCCs), and employs an attention-enhanced convolutional neural network (CNN), integrated with SHAP for model interpretability and scalp-level seizure focus localization. Crucially, the model requires no subject-specific hyperparameter tuning and enables efficient deployment in NICU settings. Evaluated on the Helsinki Neonatal EEG dataset via ten-fold cross-validation, it achieves 97.52% accuracy, 98.31% sensitivity, 96.39% specificity, and 97.95% F1-score, with seizure prediction up to 30 minutes in advance. Incorporating ECG and attention mechanisms improves the F1-score by 1.42% and 0.5%, respectively.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Neonates are highly susceptible to seizures, often leading to short or long-term neurological impairments. However, clinical manifestations of neonatal seizures are subtle and often lead to misdiagnoses. This increases the risk of prolonged, untreated seizure activity and subsequent brain injury. Continuous video electroencephalogram (cEEG) monitoring is the gold standard for seizure detection. However, this is an expensive evaluation that requires expertise and time. In this study, we propose a convolutional neural network-based model for early prediction of neonatal seizures by distinguishing between interictal and preictal states of the EEG. Our model is patient-independent, enabling generalization across multiple subjects, and utilizes mel-frequency cepstral coefficient matrices extracted from multichannel EEG and electrocardiogram (ECG) signals as input features. Trained and validated on the Helsinki neonatal EEG dataset with 10-fold cross-validation, the proposed model achieved an average accuracy of 97.52%, sensitivity of 98.31%, specificity of 96.39%, and F1-score of 97.95%, enabling accurate seizure prediction up to 30 minutes before onset. The inclusion of ECG alongside EEG improved the F1-score by 1.42%, while the incorporation of an attention mechanism yielded an additional 0.5% improvement. To enhance transparency, we incorporated SHapley Additive exPlanations (SHAP) as an explainable artificial intelligence method to interpret the model and provided localization of seizure focus using scalp plots. The overall results demonstrate the model's potential for minimally supervised deployment in neonatal intensive care units, enabling timely and reliable prediction of neonatal seizures, while demonstrating strong generalization capability across unseen subjects through transfer learning.

Problem

• Predicting neonatal seizures early using EEG and ECG signals
• Overcoming subtle clinical manifestations and misdiagnosis risks
• Providing accurate seizure prediction without patient-specific training

Innovation

• Patient-independent CNN model for seizure prediction
• Combines EEG and ECG signals with attention mechanism
• Uses SHAP explainable AI for model interpretation