https://jjcit.org/paper/245 10.5455/jjcit.71-1712193259 Lilian Lee Yen Wei,Ag Asri Ag Ibrahim,Rayner Alfred Detection,Prediction,Classification,Deep learning,Machine learning,Mental health,Neurodevelopment disorders 5 3052 732 15-Jul.-2024 18-Sep.-2024 2-Oct.-2024 This paper presents a comprehensive literature review focusing on the utilization of machine-learning (ML) and deep-learning (DL) methods for predicting and detecting Neurodevelopmental Disorders (NDDs), such as Intellectual Disability (ID), Autism Spectrum Disorder (ASD), Attention Deficit Hyperactivity Disorder (ADHD), Dyslexia, among others. While existing reviews often lack detailed discussions on the specific ML algorithms, datasets and performance metrics employed in NDD prediction and detection, this study aims to address this gap by examining two primary aspects: prediction and detection. Objective: The objective of this study is to investigate the current state-of-the-art methodologies, challenges and future directions in leveraging ML and DL techniques for the prediction and detection of NDDs. It aims to categorize the literature based on these two major aspects and provide insights into the various approaches, datasets, parameters and performance measures used in previous research. Methodology: This review encompasses articles published in journals and conference proceedings indexed in Scopus from 2013 to 2023. The search employed terms such as "Predicting Neurodevelopmental Disorder" and/or "Detection of Disorder Using Machine Learning." The analysis focuses on identifying common ML and DL approaches, ensemble models, types of datasets utilized, as well as the parameters and performance metrics employed in NDD-prediction and detection studies. Results: The findings of this review shed light on prevalent ML and DL methodologies, the challenges encountered and potential avenues for future research aimed at enhancing services for the NDD community through improved prediction and detection techniques.