EUVIMEDEUVIMED entdecken
Crossref

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

Sultan Alzahrani, Faris Algahtani iD

Child: Care, Health and Development · 2025-01 · 51 (1)

DOI: 10.1111/cch.70026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Child: Care, Health and Development, online erschienen am 23.12.2024. Verfasst von Sultan Alzahrani und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Special Education, University of Jeddah, Jeddah, Saudi Arabia. Hauptthemen laut MEDLINE: Learning Disabilities, Dyslexia. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 32 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Learning disabilities, categorized as neurodevelopmental disorders, profoundly impact the cognitive development of young children. These disabilities affect text comprehension, reading, writing and problem‐solving abilities. Specific learning disabilities (SLDs), most notably dyslexia and dysgraphia, can significantly hinder students' academic achievement. The timely identification of such students is crucial in providing them with essential assistance and facilitating the development of skills required to overcome their limitations.

Methods

The proposed model, which utilizes artificial intelligence (AI), plays a crucial role in identifying and diagnosing SLDs. This system allows students suspected of having SLD to engage in personalized exams and unique tasks tailored to their SLDs. The data generated from these activities, including performance scores and completion times, are fed into the proposed weighted ensemble learning (WEL) variation of the XGBoost (XGB) algorithm. The WEL‐XGB model is designed to detect learning challenges by analysing these datasets, even when dealing with imbalanced data.

Results

The WEL‐XGB model has been successfully integrated into a user‐friendly application for assessing reading and writing impairments. The proposed model not only identifies SLD but also offers tailored recommendations for effective instructional strategies for parents and educators. Comparative analyses with other machine learning (ML) and deep learning (DL) models demonstrate the superiority of the WEL‐XGB model, which achieved an accuracy rate of 98.7% for dyslexia datasets and 99.08% for dysgraphia datasets.

Conclusion

The proposed WEL‐XGB model effectively identifies learning disabilities in children, offering a powerful tool for both diagnosis and instructional support. Its high accuracy rates underscore its potential to revolutionize the assessment and intervention process for dyslexia and dysgraphia, benefiting students, parents and educators alike.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Learning DisabilitiesDyslexiaHumansChildArtificial IntelligenceAgraphiaMaleFemaleMachine LearningAlgorithms

Stichwörter der Autor:innen

cognitive impairmentsdyscalculiadysgraphiadyslexianeurological disorders

Autor:innen und Institutionen

  • Department of Special Education, University of Jeddah, Jeddah, Saudi Arabia.

ORCID-Profile: Faris Algahtani

Zitieren

APA

Alzahrani, S., & Algahtani, F. (2025). Implications and Identification of Specific Learning Disability Using Weighted Ensemble Learning Model. Child: Care, Health and Development, 51(1). https://doi.org/10.1111/cch.70026

Vancouver

Alzahrani S, Algahtani F. Implications and Identification of Specific Learning Disability Using Weighted Ensemble Learning Model. Child: Care, Health and Development. 2025;51(1). doi:10.1111/cch.70026

BibTeX
@article{Alzahrani2025,
  author = {Alzahrani, Sultan and Algahtani, Faris},
  title = {Implications and Identification of Specific Learning Disability Using Weighted Ensemble Learning Model},
  journal = {Child: Care, Health and Development},
  year = {2025},
  volume = {51},
  number = {1},
  doi = {10.1111/cch.70026}
}
Kostenlos starten →