Autism Spectrum Disorder Prediction: A Machine Learning Approach

Autism Spectrum Disorders (ASD) represent a group of intricate neurological developmental disabilities characterized by multifaceted behavioral impairments. The early identification of potential autistic traits is crucial for effective intervention and support. In response to this imperative, we explored the application of various supervised machine learning (ML) models, including XGBoost (XGB), AdaBoost (AdaB), Decision Tree (DT), LightGBM, Random Forest (RF), and Logistic Regression (LR) for ASD detection. The findings spotlight XGB, AdaB, and LightGBM algorithms as the standout models, distinguished by their remarkable predictive accuracy. Additionally, LR emerges as a noteworthy performer, boasting the highest Area Under the Curve (AUC) value. This research contributes to the advancement of ASD detection methodologies, offering valuable insights for future researchers and practitioners in the field.