Analyzing the Predictive Power of Machine Learning Models for Autism Detection

Abstract

This study delves into the application of machine learning models for the early detection of Autism Spectrum Disorder (ASD). Early diagnosis and intervention are critical for improving the lives of individuals with ASD and their families. This research compares various machine learning models, including Decision Tree, Random Forest, Support Vector Machine, k-Nearest Neighbors, and more, assessing their performance based on key metrics such as F1-Score, accuracy, precision, and recall. The study reveals the Multi-layer Perceptron (MLP) as the top-performing model with an impressive F1-Score of 79.35%, demonstrating its potential for accurate ASD detection. The feature importance analysis highlights the significant roles of gender, genetic predisposition, age at diagnosis, and ethnicity-related features in predicting ASD. This study underscores the promise of machine learning in ASD detection and emphasizes the importance of early intervention and personalized approaches to diagnosis.