Predictors of seizure reduction outcome after vagus nerve stimulation in drug-resistant epilepsy

Purpose: To evaluate the predictors of seizure reduction outcome after vagus nerve stimulation (VNS) in patients with drug-resistant epilepsy (DRE). Methods: A meta-analysis was performed using relevant research from databases such as PubMed, Embase, Cochrane Online Library, and Clinicaltrials.gov. Studies were selected according to predefined inclusion and exclusion criteria. The quality of studies was evaluated by using the Newcastle-Ottawa Scale (NOS) scale. All data was pooled by STATA 12.0 software for meta-analysis. Results: The review considered 1281 articles, and 16 articles with NOS score >= 6 were included in the analysis. The meta-analysis showed that at 6 m, 1, 2, 3, 4, 6 and 12 years after implantation, 33.99, 43.42, 46.50, 63.31, 52.71, 54.64, 70.37 and 82.90% of patients exhibited > 50% reduction of seizure frequency after VNS. The duration of epilepsy showed a significant difference between the good responders and poor responders (p = 0.038), whereas age at VNS implantation (p = 0.305), age at seizure onset (p = 0.530), seizure type (p = 0.11), etiology (p = 0.187), and history of previous epilepsy surgery (p = 0.075) were not predictors of seizure reduction outcome after VNS. Several features about the electroencephalogram (EEG) feature and heart rhythm complexity (HRV) have not been analyzed by a sufficient number of studies. Conclusions: DRE patients with shorter duration of epilepsy may be better candidates for VNS rather than those who are younger at onset and implantation. Several EEG or HRV features may have predictive value but more research is needed.