Related Experiment Video
Updated: Sep 10, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
The Effectiveness of Artificial Intelligence-Based Interventions for Students with Learning Disabilities: A
Andrea Paglialunga1, Sergio Melogno1
1Department of Economic, Psychological, Communication, Education and Motor Sciences, Università Degli Studi Niccolò Cusano, 00166 Rome, Italy.
Artificial intelligence (AI) shows promise for students with learning disabilities (LD), but current research has significant methodological flaws. More high-quality studies are needed to confirm AI
Area of Science:
- Educational Technology
- Artificial Intelligence in Education
- Special Education
Background:
- Artificial intelligence (AI) is increasingly used in education, but its effectiveness for students with learning disabilities (LD) needs thorough evaluation.
- Existing research on AI interventions for LD lacks rigorous methodological quality and carries a significant risk of bias.
- This review focuses on assessing the efficacy and methodological rigor of AI-based educational tools for students with LD.
Purpose of the Study:
- To systematically review the efficacy of AI-based educational interventions for students with learning disabilities (LD).
- To critically evaluate the methodological quality and risk of bias in studies examining AI interventions for LD.
- To identify the types of AI interventions and learning disabilities most frequently studied.
Main Methods:
- Systematic literature search across seven databases (2022-2025) following PRISMA guidelines.
- Inclusion criteria based on the PICOS framework for experimental studies.
- Risk of bias assessment using ROBINS-I and JBI critical appraisal tools.
Main Results:
- Eleven studies (3033 participants) met inclusion criteria, primarily focusing on dyslexia and specific learning disorders.
- Personalized/adaptive learning systems and game-based learning were common AI interventions, all reporting positive outcomes.
- Significant methodological limitations were identified, with most studies having moderate to high risk of bias; however, large effect sizes were noted in arithmetic fluency and reading comprehension.
Conclusions:
- AI-based interventions show potential for supporting students with LD, with consistently positive reported outcomes.
- The current evidence base is limited and potentially biased, necessitating cautious interpretation of findings.
- Future research should prioritize high-quality randomized controlled trials and longitudinal studies to establish definitive evidence and explore long-term effects.
More Related Videos
10:26Problem-Solving Before Instruction PS-I: A Protocol for Assessment and Intervention in Students with Different Abilities
Published on: September 11, 2021
12:55Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
Published on: September 27, 2020