Research Article
Early Prediction of Autism Spectrum Disorder Using Machine Learning
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357839, author={P. Santhi and S. Sindhu Sevitha and M. Muth Tamil Pooja and C. Alamelu}, title={Early Prediction of Autism Spectrum Disorder Using Machine Learning}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part I}, publisher={EAI}, proceedings_a={ICITSM PART I}, year={2025}, month={10}, keywords={autism spectrum disorder (asd) early detection machine learning predictive modeling logistic regression gradient boosting decision tree}, doi={10.4108/eai.28-4-2025.2357839} }- P. Santhi
S. Sindhu Sevitha
M. Muth Tamil Pooja
C. Alamelu
Year: 2025
Early Prediction of Autism Spectrum Disorder Using Machine Learning
ICITSM PART I
EAI
DOI: 10.4108/eai.28-4-2025.2357839
Abstract
Autism spectrum disorder (ASD) describes neuro developmental conditions with different degrees of alterations in socialization communication and repetitive behavior. Early detection and intervention increase the chances of a better developmental outcome. The present study focuses on the development of a machine learning-based predictive model that could allow for the identification and diagnosis of infants at risk of ASD during 45 days crucial floor period. The heterogeneous dataset includes behavioral developmental and biological markers for understanding early signs of autism. It would develop an extremely reliable predictive model with emphasis on strong concepts in machine learning: characteristic engineering, modelling selection and hyperparameter tuning. Different classification algorithms such as Random Forests, K-Nearest Neighbors, Logistic Regression, Gradient Boosting, Decision Trees and Random Forest will therefore be used and assessed for predictive capability Effectiveness of the model is assessed by key metrics like sensitivity This research seeks to promote early diagnosis of ASD for those affected allowing timely intervention and better developmental outcomes.
