Early Prediction of Autism Spectrum Disorder in Toddlers

Vaidya, Shivani Prakash (2024) Early Prediction of Autism Spectrum Disorder in Toddlers. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (967kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Autism spectrum disorder is one of the most complex neurological development disorders significantly affecting social and communication skills. In this research, deep learning and machine learning techniques are utilized for early prediction of autism spectrum disorder in toddlers, using the Autism Spectrum Quotient screening method for data gathering. The three deep-learning models and one machine-learning model are implemented, with the Multilayer Perceptron, Convolutional Neural Network, and Long Short-Term Memory model exhibiting superiority in terms of accuracy and performance parameters as compared to the machine-learning model, Random Forest. A novel feature of the study is the feature importance analysis carried out using the SHapley Additive exPlanations technique for calculating the individual contribution of certain demographic, genetic, and environmental factors such as ethnicity, gender, and jaundice, in the dataset. The findings of this research are beneficial for the healthcare sector as early and precise prediction can minimize long-term treatment costs and reduce mental stress among toddlers and their families.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Uncontrolled Keywords:	Autism spectrum disorder; Autism Spectrum Quotient screening method; Multilayer Perceptron model; Convolutional Neural Network model; Long Short-Term Memory model; Random Forest model; Feature important analysis; Shapley additive explanations technique
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HQ The family. Marriage. Woman > Children Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	26 Aug 2025 12:08
Last Modified:	26 Aug 2025 12:08
URI:	https://norma.ncirl.ie/id/eprint/8646

Actions (login required)

View Item