Comparative Effectiveness of AI-Assisted Telerehabilitation Versus Conventional Rehabilitation for Upper Limb Recovery After Stroke: A Systematic Review and Meta-Analysis
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