Comparative Effectiveness of Noninvasive Brain-Computer Interface-Based Interventions for Upper Limb Rehabilitation in Poststroke Hemiplegia: Systematic Review and Network Meta-Analysis of Randomized Controlled Trials.

Abstract

Noninvasive brain-computer interface (BCI)-based interventions show promise for poststroke motor recovery. However, the intrinsic complexity of BCI-based interventions limits the determination of their comparative efficacy. Guided by the International Classification of Functioning, Disability and Health framework, this review evaluated the effectiveness of BCI-based interventions in poststroke upper limb rehabilitation and identify the optimal intervention. We searched PubMed, Cochrane Library, EBSCOhost, Web of Science, Embase, Wiley Online Library,CNKI, Wanfang, VIP, and SinoMed through July 2026. Randomized controlled trials (RCTs) assessing BCI-based interventions for poststroke upper limb rehabilitation were included. Outcomes were body functions and structures (Fugl-Meyer Assessment of Upper Extremity [FMA-UE]) and activities and participation (Action Research Arm Test [ARAT], Wolf Motor Function Test [WMFT], and Modified Barthel Index [MBI]). Risk of bias was assessed using Cochrane RoB 2, and evidence quality was graded using the Grading of Recommendations, Assessment, Development, and Evaluation framework. We used pairwise meta-analyses to evaluate the overall effectiveness of BCI-based interventions vs controls and network meta-analysis to compare the interventions. Seventy-two RCTs involving 2906 patients with stroke were included, evaluating 12 BCI-based interventions. Pairwise meta-analyses demonstrated that, compared with control groups, BCI-based interventions improved FMA-UE (mean difference [MD] 5.33, 95% CI 4.28 to 6.38; 95% prediction interval [PI] -1.76 to 12.43), ARAT (MD 5.26, 95% CI 3.90 to 6.62; 95% PI 0.41 to 10.11), WMFT (MD 7.25, 95% CI 5.06 to 9.44; 95% PI 0.71 to 13.79), and MBI (MD 8.18, 95% CI 6.04 to 10.32; 95% PI -1.87 to 18.23). Network meta-analysis revealed that BCI-motor imagery-transcutaneous electrical acupoint stimulation (BCI-MI-TEAS) achieved the highest surface under the cumulative ranking curve (SUCRA; 95.5%) in improving FMA-UE. For ARAT, BCI-MI-end-effector robots and transcranial direct current stimulation (tDCS; 86.3%) alongside BCI-MI-TEAS (86.3%) yielded the highest SUCRA. BCI-MI-exoskeleton robot showed the highest SUCRA for WMFT (92.7%), whereas BCI-MI-TEAS (85.3%) and BCI-MI-exoskeleton robot (81.7%) ranked highest for MBI. The evidence quality ranged from very low to high across these interventions. This study represents the first network meta-analysis comparing the efficacy of different BCI-based interventions. Unlike previous reviews, interventions were categorized by experimental paradigms, external feedback devices, and adjunctive noninvasive brain stimulation, to enable clinically meaningful comparisons. Overall, BCI-based interventions significantly improved poststroke upper limb rehabilitation. Among evaluated interventions, BCI-MI-TEAS demonstrated the most performance across body functions, structures, and activities and participation, whereas BCI-MI-end-effector robot + tDCS showed advantages for fine motor dexterity and BCI-MI-exoskeleton robot improved activities of daily living.Given low to moderate evidence certainty and substantial heterogeneity, these findings remain exploratory. High-quality trials are needed to establish the clinical utility of these interventions.