Using Eye-Tracking to Assess Dyslexia: A Systematic Review of Emerging Evidence

Abstract

Reading is a complex skill that requires accurate word recognition, fluent decoding, and effective comprehension. Children with dyslexia often face challenges in these areas, resulting in ongoing reading difficulties. This study systematically reviews the use of eye-tracking technology to assess dyslexia, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. The review identifies the specific types of eye-tracking technologies used, examines the cognitive and behavioral abilities assessed (such as reading fluency and attention), and evaluates the primary purposes of these evaluations—screening, assessment, and diagnosis. This study explores key questions, including how eye-tracking outcomes guide intervention strategies and influence educational practices, and assesses the practicality and time efficiency of these evaluations in real-world settings. Furthermore, it considers whether eye-tracking provides a holistic developmental profile or a targeted analysis of specific skills and evaluates the generalizability of eye-tracking results across diverse populations. Gaps in the literature are highlighted, with recommendations proposed to improve eye-tracking’s precision and applicability for early dyslexia intervention. The findings underscore the potential of eye-tracking to enhance diagnostic accuracy through metrics such as fixation counts, saccadic patterns, and processing speed, key indicators that distinguish dyslexic from typical reading behaviors. Additionally, studies show that integrating machine learning with eye-tracking data can enhance classification accuracy, suggesting promising applications for scalable, early dyslexia screening in educational settings. This review provides new insights into the value of eye-tracking technology in identifying dyslexia, emphasizing the need for further research to refine these methods and support their adoption in classrooms and clinics.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 29 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.