A prediction model integrating synchronization biomarkers and clinical features to identify responders to vagus nerve stimulation among pediatric patients with drug‐resistant epilepsy

Abstract

Aims Vagus nerve stimulation (VNS) is a neuromodulation therapy for children with drug‐resistant epilepsy (DRE). The efficacy of VNS is heterogeneous. A prediction model is needed to predict the efficacy before implantation. Methods We collected data from children with DRE who underwent VNS implantation and received regular programming for at least 1 year. Preoperative clinical information and scalp video electroencephalography (EEG) were available in 88 children. Synchronization features, including phase lag index (PLI), weighted phase lag index (wPLI), and phase‐locking value (PLV), were compared between responders and non‐responders. We further adapted a support vector machine (SVM) classifier selected from 25 clinical and 18 synchronization features to build a prediction model for efficacy in a discovery cohort (n = 70) and was tested in an independent validation cohort (n = 18). Results In the discovery cohort, the average interictal awake PLI in the high beta band was significantly higher in responders than non‐responders (p < 0.05). The SVM classifier generated from integrating both clinical and synchronization features had the best prediction efficacy, demonstrating an accuracy of 75.7%, precision of 80.8% and area under the receiver operating characteristic (AUC) of 0.766 on 10‐fold cross‐validation. In the validation cohort, the prediction model demonstrated an accuracy of 61.1%. Conclusion This study established the first prediction model integrating clinical and baseline synchronization features for preoperative VNS responder screening among children with DRE. With further optimization of the model, we hope to provide an effective and convenient method for identifying responders before VNS implantation.

Characterization of Vagus Nerve Stimulation (VNS) Dose-Dependent Effects on EEG Power Spectrum and Synchronization

“…However, R shows a higher beta power in this region compared to NR. Similar results were reported by Yokoyama et al [ 32 ] and Ma et al [ 18 ], where higher beta oscillations were correlated with better responses for VNS. Using EEG data, Bodin et al investigated the impact of VNS on the synchronicity of interictal EEG rhythms in patients with refractory epilepsy.…”

“…Previous literature has shown that EEG synchronization using phase difference-based metrics, such as the weighted phase lag index (wPLI), is sensitive to the acute desynchronizing effects of VNS on EEG [ 18 , 25 , 26 ]. The wPLI accounts for the stability or consistency of phase differences across EEG epochs.…”

“…Many VNS studies have traditionally focused on the effects of clinically programmed VNS intensities [ 13 , 17 , 18 , 19 ]. They study the acute effects of VNS by comparing VNS ON and OFF states and classifying patients into ‘Responders’ and ‘Non-Responders’.…”

An objective model for diagnosing comorbid cognitive impairment in patients with epilepsy based on the clinical-EEG functional connectivity features

“…The phase locking value (PLV) is one of the quantitative indicators for functional connectivity ( Elahian et al, 2017 ; Duma et al, 2021 ). Furthermore, EEG-based functional connectivity is employed to predict vagus nerve stimulation (VNS) responsiveness in children with refractory epilepsies ( Ma et al, 2022 ), as well as to diagnose CI in patients comorbid with Parkinson’s disease (PD) ( Cai et al, 2021 ). However, this approach has not been applied to the diagnosis of cognitive dysfunctions in PWEs.…”

Brain functional connectivity‐based prediction of vagus nerve stimulation efficacy in pediatric pharmacoresistant epilepsy

“…First, this study is the first to investigate VNS response prediction using network features derived from EEG data acquired before VNS implantation. As children tend to move while being scanned, performing fMRI or MEG scans in children can be problematic 22,23 . Therefore, EEG is a more suitable technique than MEG and fMRI to detect brain functional activity in children.…”