The Efficacy and Predictors of Using GPi-DBS to Treat Early-Onset Dystonia: An Individual Patient Analysis

Objective. To compare the efficacy in patients with different genotypes, identify the potential predictive factors, and summarize the complications of globus pallidus deep brain stimulation (GPi-DBS) treating early-onset dystonia. Methods. Three electronic databases (PubMed, Embase, and Cochrane databases) were searched with no publication data restriction. The primary outcomes were the improvements in Burke-Fahn-Marsden Dystonia Rating Scale motor (BFMDRS-M) and disability (BFMDRS-D) score. Pearson's correlation coefficients and a metaregression analysis were used to identify the potential predictive factors. This article was registered in Prospero (CRD42020188527). Results. Fifty-four studies (231 patients) were included. Patients showed significant improvement rate in BFMDRS-M (60.6%, p < 0.001) and BFMDRS-D (57.5%, p < 0.001) scores after treatment with GPi-DBS. BFMDRS-M score improved greater in the DYT-1-positive (p = 0.001) and DYT-11-positive (p = 0.008) patients compared to DYT-6-positive patients. BFMDRS-D score improved greater in the DYT-11 (+) compared to DYT-6 (+) patients (p = 0.010). The relative change of BFMDRS-M (p = 0.002) and BFMDRS-D (p = 0.010) scores was negatively correlated with preoperative BFMDRS-M score. In the metaregression analysis, the best predictive model showed that preoperative BFMDRS-M, disease duration (p = 0.047), and the age at symptom onset (p = 0.027) were important. Conclusion. Patients with early-onset dystonia have a significant effect after GPi-DBS treatment, and DYT-1 (+) and DYT-11 (+) patients are better candidates for GPi-DBS. Lower preoperative score, later age of onset, and an earlier age at surgery probably predict better clinical outcomes.