• Tarani J
• V Vijayalakshmi
• Purushothaman V
• Rajath H Kurup
• Nilahilan R

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that manifests in early childhood, often impacting communication, social interaction, and behavior. Early detection of ASD is critical for enabling timely interventions that can significantly enhance developmental outcomes. However, traditional diagnostic methods are resource-intensive, time-consuming, and frequently lead to delays in identification, particularly in under-resourced settings. This paper proposes a machine learning-based framework for the early prediction of ASD, utilizing behavioral, developmental, and familial data collected through structured questionnaires. Various supervised learning algorithms, including Random Forest, Support Vector Machine, and Neural Networks, were trained and evaluated on a curated dataset of young children. The results demonstrate that the proposed system can accurately predict the risk of ASD, thereby supporting clinicians in prioritizing early intervention efforts. This approach highlights the potential of leveraging artificial intelligence to address gaps in traditional diagnostic pathways and improve access to early autism screening services.

"EARLY PREDICTION OF AUTISM DISORDER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.a414-a419, May-2025, Available :http://www.jetir.org/papers/JETIR2505043.pdf

"EARLY PREDICTION OF AUTISM DISORDER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppa414-a419, May-2025, Available at : http://www.jetir.org/papers/JETIR2505043.pdf