Published Paper Details:

Autism Spectrum Disorder (ASD) is a complex neurodevelopment condition characterized by challenges in social interaction, communication, and repetitive behaviors. Early and accurate diagnosis of ASD is crucial for effective intervention and treatment. Traditional diagnostic methods rely on behavioral assessments, which can be time-consuming and subjective. In recent years, machine learning (ML) techniques have emerged as powerful tools for automating and improving ASD detection by analyzing diverse data sources such as clinical reports, neuroimaging scans, genetic data, and behavioral patterns. This systematic review explores the latest advancements in ML-based ASD detection, highlighting various algorithms, feature selection methods, and performance metrics used in recent studies. We examine supervised, unsupervised, and deep learning approaches, emphasizing their strengths and limitations in ASD diagnosis. Additionally, we discuss the challenges associated with dataset availability, model interpretability, and generalization across diverse populations. The review aims to provide insights into the current trends and future directions of ML applications in ASD detection, ultimately contributing to the development of more efficient, accurate, and accessible diagnostic tools.