Implications and Identification of Specific Learning Disability Using Weighted Ensemble Learning Model

Area of Science:

• Neurodevelopmental Disorders
• Artificial Intelligence in Education
• Machine Learning for Diagnostics

Background:

• Specific learning disabilities (SLDs), including dyslexia and dysgraphia, significantly impact children's cognitive development and academic success.
• Early identification of SLDs is critical for providing timely support and interventions.
• Neurodevelopmental disorders require tailored approaches for effective management.

Purpose of the Study:

• To develop and validate an AI-powered model for the accurate identification of children with specific learning disabilities.
• To create a diagnostic tool that offers personalized recommendations for instructional strategies.
• To improve the assessment process for dyslexia and dysgraphia.

Main Methods:

• Utilized a weighted ensemble learning (WEL) variation of the XGBoost (XGB) algorithm for SLD detection.
• Developed a system for personalized exams and tasks to gather student performance data.
• Employed AI to analyze performance scores and completion times, even with imbalanced datasets.

Main Results:

• The WEL-XGB model achieved high accuracy rates: 98.7% for dyslexia and 99.08% for dysgraphia.
• The model was integrated into a user-friendly application for assessing reading and writing impairments.
• Demonstrated superior performance compared to other machine learning and deep learning models.

Conclusions:

• The WEL-XGB model is a highly effective tool for identifying learning disabilities in children.
• The model provides valuable diagnostic insights and supports the development of tailored instructional strategies.
• This AI approach has the potential to significantly enhance the assessment and intervention process for SLDs.