Effects of Brain-Computer Interface-Based Training on Post-Stroke Lower Limb Rehabilitation: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.
Aug 2026· Journal of Stroke & Cerebrovascular Diseases· Vol 35, pp.
108711
· 0 citations· 51 references
Medicine
TL;DR
BCI-based training effectively improves lower-limb motor recovery after stroke, and subgroup analyses suggested that a moderate total dose combined with 20-40-minute sessions may represent a potentially optimal regimen, although these findings are based on limited RCTs and require confirmation in larger studies.
Abstract
Background
Lower-limb motor dysfunction after stroke severely compromises mobility and quality of life. Brain-computer interface (BCI) technology, which employs a "central-peripheral-central" closed-loop to promote neuroplasticity, offers a promising rehabilitation approach. However, its optimal dosing parameters remain unclear.
Objective
This study aimed to evaluate the efficacy of BCI-based training on lower-limb motor function, balance, walking capacity, and activities of daily living (ADL) after stroke, and to explore the impact of total training dose, session duration, and stroke phase.
Methods
We systematically searched major databases for randomized controlled trials (RCTs) published up to April 2026. All included studies were RCTs. Methodological quality was assessed using the PEDro scale. A meta-analysis was conducted using RevMan 5.4 to calculate mean differences (MD) and 95% confidence intervals (CI).
Results
Ten RCTs involving 366 participants were included. BCI training significantly improved lower-limb motor function (Fugl-Meyer Assessment for Lower Extremity: MD = 2.38, 95% CI 1.72 to 3.04, P < 0.00001). Although this mean difference is below the anchor-based Minimal Clinically Important Difference (MCID) of 6 points reported for chronic stroke populations, it represents a statistically robust and consistent improvement across RCTs, suggesting potential clinical relevance, particularly in subacute patients or specific intervention subgroups.
Conclusions
BCI-based training effectively improves lower-limb motor recovery after stroke. Subgroup analyses suggested that a moderate total dose (401-800 minutes) combined with 20-40-minute sessions may represent a potentially optimal regimen, although these findings are based on limited RCTs and require confirmation in larger studies.
Abstract Background 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. Objective 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. Methods 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. Results 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. Conclusions 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.
Jia-Bin Xu, Yitian Gao, Si-Qi Xie et al.· Journal of Medical Internet...· 0 citations
BACKGROUND
Stroke-related hemiplegia often results in significant lower limb dysfunction, severely affecting walking ability, balance, and daily activities. Although various non-pharmacological interventions have shown potential benefits, the optimal rehabilitation strategy remains unclear.
OBJECTIVE
To evaluate the efficacy and comparative ranking of non-pharmacological interventions in improving lower limb motor function, balance, walking ability, and activities of daily living in individuals with post-stroke hemiplegia.
METHODS
We conducted a search of PubMed, Embase, Cochrane Library, and Web of Science databases for randomized controlled trials (RCTs) published from January 2010 to August 2025. The Cochrane Risk of Bias Tool and Review Manager 5.4 were used to assess study quality, and evidence was graded with GRADEPro. Using R Studio software, a NMA was carried out to evaluate the clinical efficacy of various treatments in improving lower limb motor function in patients with post-stroke hemiplegia, ranked by the surface under the cumulative ranking curve (SUCRA). The study was officially registered in PROSPERO under the number CRD420251169037.
RESULTS
A total of 82 RCTs involving 3514 participants and 16 non-pharmacological interventions were included. The results indicated that repetitive transcranial magnetic stimulation (rTMS) showed favorable effects on lower limb motor function measured by FMA-LE (MD = 3.7, 95% CI 2.5 to 4.9; SUCRA = 88.13%). rTMS also demonstrated positive effects on balance (MD = 8.5, 95% CrI: 5.1 to 11; SUCRA = 98.41%) and activities of daily living (MD = 14, 95% CrI: 11 to 16; SUCRA = 94.68%). For walking independence assessed by FAC, transcranial direct current stimulation (tDCS) showed considerable effects (MD = 1.5, 95% CrI: 0.41 to 2.5; SUCRA = 87.60%). Furthermore, virtual reality combined with robotic rehabilitation showed a relatively marked effect in reducing TUG time (MD = - 6.6, 95% CrI: - 8.9 to - 4.3; SUCRA = 95.27%).
CONCLUSION
Different non-pharmacological interventions may provide distinct benefits for lower limb rehabilitation after stroke. rTMS appears favorable for improving motor function, balance, and daily living ability; tDCS may help enhance walking independence; and virtual reality combined with robotic rehabilitation may be beneficial for functional mobility. Further large-scale, multicenter, standardized RCTs with longer follow-up are needed to confirm these findings.
Di Zhang, Yating Yang, Guixing Xu et al.· Journal of NeuroEngineering...· 0 citations
Overall, the certainty of evidence was low to very low, downgraded primarily for these risk of bias concerns, severe imprecision (due to small sample sizes), and potential publication bias.
Yu Qin, Mei-xuan Li, Yan-fei Li et al.· Cochrane Database of Systema...· 0 citations
With respect to stroke staging, BCI-mediated rehabilitation interventions conferred superior efficacy for motor function recovery in patients with subacute stroke, a finding plausibly attributable to the temporal course of post-stroke neural remodeling.
Huanhuan Zhang, Runzhi Xian, Yuchi Zhang et al.· Journal of NeuroEngineering...· 0 citations
MI-BCI training can improve upper limb motor function, particularly for isolated movements and fine motor control, in stroke patients, but the current evidence does not support definitive conclusions regarding its superiority over standardised traditional rehabilitation.
Zhen Yang, Shan Zhang, Du Wang et al.· Brain Impairment· 0 citations
ABSTRACT
Background: Stroke is a leading cause of long-term disability, with upper limb motor deficits limiting functional independence and quality of life. Advances in artificial intelligence (AI) have enabled AI-assisted telerehabilitation platforms that deliver intensive, task-specific, individualized therapy remotely, yet their comparative effectiveness remains uncertain.
Methods: PubMed, Embase, Scopus, Cochrane CENTRAL, and Web of Science were searched to June 2025. Randomized controlled trials and quasi-experimental studies enrolling adults with stroke-related upper limb impairment were eligible. Studies compared AI-assisted telerehabilitation with conventional therapist-led or standard remote therapy and reported validated outcomes, including the Fugl-Meyer Assessment for Upper Extremity (FMA-UE) and Motor Activity Log (MAL). Risk of bias was assessed using the Cochrane tool, and pooled mean differences were calculated using random-effects models.
Result: Five studies including 339 participants met inclusion criteria. Meta-analysis demonstrated no statistically significant difference between AI-assisted telerehabilitation and conventional therapy. The pooled mean difference for FMA-UE was 0.55 (95% CI: -0.60 to 1.08; p=0.38; I²=89%), and for MAL was 0.36 (95% CI: -0.45 to 1.17; p=0.39). Both groups achieved clinically meaningful improvements, with no serious adverse events reported.
Conclusion: AI-assisted telerehabilitation is an alternative to conventional post-stroke upper limb rehabilitation.
Keywords: artificial intelligence, motor recovery, stroke, telerehabilitation, upper limb
ABSTRAK
Latar Belakang: Stroke merupakan salah satu penyebab disabilitas jangka panjang, dengan gangguan fungsi motorik ekstremitas atas membatasi kemandirian fungsional serta kualitas hidup. Telerehabilitasi berbasis AI sebagai alternatif layanan rehabilitasi memungkinkan pemberian terapi secara intensif, spesifik terhadap tugas, dan terindividualisasi dari rumah. Namun, bukti mengenai efektivitas telerehabilitasi berbasis AI masih terbatas.
Metode: Pencarian literatur dilakukan pada PubMed, Embase, Scopus, Cochrane CENTRAL, dan Web of Science hingga Juni 2025. Studi uji acak terkontrol dan kuasi-eksperimental yang melibatkan pasien dewasa pascastroke dengan gangguan ekstremitas atas disertakan. Studi membandingkan telerehabilitasi berbasis AI dengan terapi konvensional yang dipandu terapis atau terapi jarak jauh standar, disertai luaran tervalidasi seperti Fugl-Meyer Assessment untuk Ekstremitas Atas (FMA-UE) dan Motor Activity Log (MAL). Penilaian risiko bias dilakukan menggunakan alat Cochrane, dan analisis meta dilakukan dengan model efek acak.
Hasil: Lima studi dengan total 339 partisipan memenuhi kriteria inklusi. Hasil meta-analisis menunjukkan tidak terdapat perbedaan bermakna secara statistik antara kelompok telerehabilitasi berbasis AI dan terapi konvensional. Perbedaan rerata gabungan FMA-UE adalah 0.55 (95% CI: -0.60 to 1.08; p=0.38; I²=89%), sedangkan untuk MAL sebesar 0.36 (95% CI: -0.45 to 1.17; p=0.39). Kedua kelompok menunjukkan perbaikan klinis bermakna, tanpa kejadian efek samping serius.
Kesimpulan: Telerehabilitasi berbasis AI merupakan alternatif yang layak untuk pemulihan fungsi ekstremitas atas pascastroke.
Kata kunci: kecerdasan buatan, pemulihan motorik, stroke, telerehabilitasi, ekstremitas atas
Fianirazha Primesa Caesarani, Istinganah Noviana, Margareta Dewi Dwiwulandari· Indonesian Journal of Physic...· 0 citations