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.
Vagus nerve stimulation (VNS) is an effective treatment for drug-resistant epilepsy (DRE). The present study evaluated the efficacy of VNS in pediatric patients with DRE of monogenic etiology. A total of 20 patients who received VNS treatment at our center were followed up every 3 months through outpatient visits or a remote programming platform. The median follow-up time was 1.4 years (range: 1.0–2.9). The rate of response to VNS at 12 months of follow-up was 55.0% (11/20) and the seizure-free rate was 10.0% (2/20). We found that 75.0% (3/4) of patients with an SCN1A variant had a >50% reduction in seizure frequency. Patients with pathogenic mutations in the SLC35A2, CIC, DNM1, MBD5, TUBGCP6, EEF1A2, and CHD2 genes or duplication of X q28 (MECP2 gene) had a >50% reduction in seizure frequency. Compared with the preoperative electroencephalography (EEG), at 6, 12, 18, and 24 months after stimulator implantation, the percentage of the patients whose background frequency increased >1.5 Hz was respectively, 15.0% (3/20), 50.0% (10/20), 58.3% (7/12) and 62.5% (5/8); the percentage of the patients whose interictal EEG showed a >50% decrease in spike number was respectively 10% (2/20), 40.0% (8/20), 41.6% (5/12) and 50.0% (4/8). In the 9 patients with no response to VNS treatment, there was no difference in terms of spike number and background frequency between preoperative and postoperative EEG. Five of the 20 children (25.0%) reached new developmental milestones or acquired new skills after VNS compared to the preoperative evaluation. The efficacy of VNS in pediatric patients with DRE of monogenic etiology is consistent with that in the overall population of pediatric DRE patients. Patients with Dravet syndrome (DS), tuberous sclerosis complex (TSC), or Rett syndrome/MECP2 duplication syndrome may have a satisfactory response to VNS, but it is unclear whether patients with rare variants of epilepsy-related genes can benefit from the treatment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.