An Enhanced Intelligenomics-Based Framework for Profiling Personalised Childhood Learning and Development

Document Type

Article

Publication Date

1-1-2026

Abstract

Malaysia acknowledges the importance of childhood learning and development to ensure that future generations are prepared and get the best education possible. However, providing educational support for children with diverse developmental needs remains a significant challenge for educators and caregivers. Traditional approaches in Early Childhood Care & Education (ECCE) rely heavily on manual observations, which may overlook underlying genetic influences. Advances in genomics, particularly the use of Polygenic Risk Scores (PRS), present new opportunities to integrate genetic and phenotypic data for more personalized learning profiles. This study proposes an intelligenomics-based framework that integrates genomic datasets processed into PRS with observation-based phenotypic data to create personalized Child Learning & Development (CLD) profiles. The methodology involves data preprocessing, missing value imputation, PRS computation, and the application of machine learning algorithms, such as Naïve Bayes, k-Nearest Neighbors (kNN), and a hybrid Random Forest with entropy-based splitting. This study identifies that Random Forest achieved the most balanced and accurate predictions of CITA scores, outperforming other models in terms of generalization and consistency. This study also contributes an integrated PRS–phenotype (CITA) dataset from Malaysia and provides a semi-automated profiling process for educational and clinical applications. The proposed framework has the potential to guide more effective intervention strategies, enabling schools to design personalized learning plans that better support children’s development.

Keywords

Child learning development, machine learning, phenotypic profiling, polygenic risk score, random forest

Publication Title

International Journal on Informatics Visualization

DOI

10.62527/joiv.10.1.5123

Volume

10

Issue

1

First Page

384

Last Page

389

Share

COinS