Creative Commons source reading · Epilepsy and seizure classification
A prediction model integrating synchronization biomarkers and clinical features to identify responders to vagus nerve stimulation among pediatric patients with drug-resistant epilepsy.
Jiayi Ma; Zhiyan Wang; Tungyang Cheng; Yingbing Hu; Xiaoya Qin; Wen Wang; Guojing Yu; Qingzhu Liu; Taoyun Ji; Han Xie; Daqi Zha; Shuang Wang; Zhixian Yang; Xiaoyan Liu; Lixin Cai; Yuwu Jiang; Hongwei Hao; Jing Wang; Luming Li; Ye Wu
Originally published in CNS neuroscience & therapeutics · 2022-07-27
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
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).
DISCUSSION
To the best of our knowledge, this study is the first to establish a model integrating baseline clinical and synchronization features before implantation through SVM machine learning to predict the efficacy of VNS in children with DRE.
CONCLUSION
This study established the first prediction model integrating both clinical and synchronization features from baseline scalp EEG for screening VNS responders. With further optimization of the model in the future, we hope to provide an effective, convenient, and individualized method that could be used in clinical practice to identify potential responders before VNS implantation.
Editorial reading guide
- Which patient population and reference standard did the authors use?
- Was the finding validated in a separate cohort, and how might patient selection affect it?
