The Effectiveness of Artificial Intelligence-Based Interventions for Students with Learning Disabilities: A Systematic Review

Background/Objectives: While artificial intelligence (AI) is rapidly transforming education, its specific effectiveness for students with learning disabilities (LD) requires rigorous evaluation. This systematic review aims to assess the efficacy of AI-based educational interventions for students with LD, with a specific focus on the methodological quality and risk of bias of the available evidence. Methods: A systematic search was conducted across seven major databases (Google Scholar, ScienceDirect, APA PsycInfo, ERIC, Scopus, PubMed) for experimental studies published between 2022 and 2025. This review followed PRISMA guidelines, using the PICOS framework for inclusion criteria. A formal risk of bias assessment was performed using the ROBINS-I and JBI critical appraisal tools. Results: Eleven studies (representing 10 independent experiments), encompassing 3033 participants, met the inclusion criteria. The most studied disabilities were dyslexia (six studies) and other specific learning disorders (three studies). Personalized/adaptive learning systems and game-based learning were the most common AI interventions. All 11 studies reported positive outcomes. However, the risk of bias assessment revealed significant methodological limitations: no studies were rated as having a low risk of bias, with most presenting a moderate (70%) to high/serious (30%) risk. Despite these limitations, quantitative results from the stronger studies showed large effect sizes, such as in arithmetic fluency (d = 1.63) and reading comprehension (d = −1.66). Conclusions: AI-based interventions demonstrate significant potential for supporting students with learning disabilities, with unanimously positive reported outcomes. However, this conclusion must be tempered by the considerable risk of bias and methodological weaknesses prevalent in the current literature. The limited and potentially biased evidence base warrants cautious interpretation. Future research must prioritize high-quality randomized controlled trials (RCTs) and longitudinal assessments to establish a definitive evidence base and investigate long-term effects, including the risk of cognitive offloading.