Journal Article

A predictive model combining connectomics and entropy biomarkers to discriminate long‐term vagus nerve stimulation efficacy for pediatric patients with drug‐resistant epilepsy

Li, Luming, Ma, Jiayi, Zha, Daqi, Liu, Qingzhu, Wu, Ye, Hu, Yingbing, Cheng, Tung‐yang, Xie, Han, Hao, Hongwei, Ji, Taoyun, Wang, Zhiyan, Qin, Xiaoya

2024

Overview

Aims To predict the vagus nerve stimulation (VNS) efficacy for pediatric drug‐resistant epilepsy (DRE) patients, we aim to identify preimplantation biomarkers through clinical features and electroencephalogram (EEG) signals and thus establish a predictive model from a multi‐modal feature set with high prediction accuracy. Methods Sixty‐five pediatric DRE patients implanted with VNS were included and followed up. We explored the topological network and entropy features of preimplantation EEG signals to identify the biomarkers for VNS efficacy. A Support Vector Machine (SVM) integrated these biomarkers to distinguish the efficacy groups. Results The proportion of VNS responders was 58.5% (38/65) at the last follow‐up. In the analysis of parieto‐occipital α band activity, higher synchronization level and nodal efficiency were found in responders. The central‐frontal θ band activity showed significantly lower entropy in responders. The prediction model reached an accuracy of 81.5%, a precision of 80.1%, and an AUC (area under the receiver operating characteristic curve) of 0.838. Conclusion Our results revealed that, compared to nonresponders, VNS responders had a more efficient α band brain network, especially in the parieto‐occipital region, and less spectral complexity of θ brain activities in the central‐frontal region. We established a predictive model integrating both preimplantation clinical and EEG features and exhibited great potential for discriminating the VNS responders. This study contributed to the understanding of the VNS mechanism and improved the performance of the current predictive model. The long‐term efficacy of VNS was assessed among 65 pediatric patients. Presurgical EEG analysis shows that VNS responders exhibit higher nodal efficiency in parietal‐occipital EEG α activity and lower entropy in central‐frontal EEG θ activity. The SVM model with clinical and EEG features for VNS efficacy shows high accuracy.

• Publisher: John Wiley & Sons, Inc,John Wiley and Sons Inc
• Subject: Adolescent / Biomarkers / Child / Child, Preschool / Connectome - methods / Convulsions & seizures / Drug resistance / Drug Resistant Epilepsy - physiopathology / Drug Resistant Epilepsy - therapy / drug‐resistant epilepsy / EEG / Electroencephalography / Electroencephalography - methods / Entropy / Epilepsy / Female / Follow-Up Studies / functional connectivity / Hilbert‐Huang spectral entropy / Humans / Magnetic resonance imaging / Male / Original / Patients / Pediatrics / Prediction models / Support Vector Machine / Surgery / Synchronization / Treatment Outcome / Vagus nerve / Vagus nerve stimulation / Vagus Nerve Stimulation - methods