Improving Early ASD Diagnosis in Pediatric Populations Using Ensemble Learning Approaches

DOI

10.2991/978-94-6463-704-5_13How to use a DOI?

Keywords

Autism Spectrum Disorder; Ensembling; Boosting

Abstract

Autism spectrum disorder (ASD) is a neurological condition defined by repetitive mannerisms, communication impairments, and social interaction issues. For treatments to be effective and for children to lead easy lives, early sickness detection is crucial. Because symptoms can manifest in a variety of ways, traditional diagnostic techniques are frequently time-consuming, subjective, and limiting. This research leverages machine learning and ensemble methods to improve the early detection of autism in pediatric populations. During our work flow, a dataset including behavioral, demographic and clinical parameters was analyzed using models like Logistic Regression, Decision Tree and Naïve Bayes, achieving baseline accuracies upto 91.41%. A Voting Classifier ensemble, combining these models with hyperparameter tuning, improved accuracy to 95.95%. Advanced ensemble methods such as AdaBoost, CatBoost, XGBoost and Random Forest were further evaluated, with CatBoost and XGBoost demonstrating superior precision, recall and overall performance. These results underscore the ability of ensembling techniques in addressing the limitations of traditional ASD diagnostics, offering a scalable, accurate and efficient approach for early intervention of autism focusing on children.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Priyanshi Mulwani
AU  - Manisha Bhende
AU  - Swati Sharma
PY  - 2025
DA  - 2025/04/30
TI  - Improving Early ASD Diagnosis in Pediatric Populations Using Ensemble Learning Approaches
BT  - Proceedings of the International Conference on Smart Health and Intelligent Technologies (ICSHit-2024)
PB  - Atlantis Press
SP  - 155
EP  - 170
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-704-5_13
DO  - 10.2991/978-94-6463-704-5_13
ID  - Mulwani2025
ER  -