Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{205497,
        author = {Zahara Mirza and Md. Ateeq Ur Rahman and Subramanian K.M.},
        title = {A MACHINE LEARNING FRAMEWORK FOR EARLY – STAGE DETECTION OF AUTISM SPECTRUM DISORDERS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {6718-6726},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205497},
        abstract = {autism spectrum disorder (ASD) is a neurodevelopmental condition that affects communication, social interaction, and behavior. Early detection of ASD is essential because timely intervention can significantly improve cognitive, social, and emotional development in children. Traditional diagnostic methods often rely on clinical observations and expert assessments, which may be time-consuming, subjective, and inaccessible in resource-limited settings. A Machine Learning Framework for Early-Stage Detection of Autism Disorders provides an intelligent and data-driven approach to assist healthcare professionals in identifying potential ASD cases at an early stage. The framework collects and processes behavioral, demographic, and developmental data, followed by data preprocessing, feature selection, and model training using machine learning algorithms such as Decision Trees, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Gradient Boosting. The trained model analyzes patterns within the data and predicts the likelihood of autism with high accuracy. Performance evaluation metrics including accuracy, precision, recall, F1-score, and ROC-AUC are used to compare models and identify the most effective classifier. The proposed framework aims to reduce diagnostic delays, minimize human bias, and support clinicians with reliable decision-making tools. Additionally, it can be integrated into web or mobile healthcare applications to enable accessible screening in schools, hospitals, and remote areas. By leveraging machine learning techniques, the system offers a scalable, cost-effective, and efficient solution for early autism detection, ultimately contributing to improved treatment planning and better quality of life for affected individuals and their families.},
        keywords = {Machine Learning, Autism Spectrum Disorder (ASD), Early Detection, Classification Models, Predictive Analytics, Healthcare Analytics, Feature Selection, Behavioral Analysis, Decision Support System, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Intelligence, Medical Diagnosis, Data Mining.},
        month = {June},
        }