Towards Equitable ASD Diagnostics: A Comparative Study of Machine and Deep Learning Models Using Behavioral and Facial Data

TL;DR

This study compares machine learning and deep learning models for ASD diagnosis using behavioral and facial data, highlighting Random Forest's high accuracy and MobileNet's efficiency, with implications for equitable and accessible screening.

Contribution

It demonstrates the effectiveness of Random Forest and MobileNet models in ASD diagnosis, emphasizing their potential to improve accuracy and accessibility, especially for underdiagnosed groups.

Findings

Random Forest achieved 100% validation accuracy.

MobileNet outperformed baseline CNN with 87% accuracy.

Overfitting observed in facial analysis models, requiring further optimization.

Abstract

Autism Spectrum Disorder (ASD) is often underdiagnosed in females due to gender-specific symptom differences overlooked by conventional diagnostics. This study evaluates machine learning models, particularly Random Forest and convolutional neural networks, for enhancing ASD diagnosis through structured data and facial image analysis. Random Forest achieved 100% validation accuracy across datasets, highlighting its ability to manage complex relationships and reduce false negatives, which is crucial for early intervention and addressing gender biases. In image-based analysis, MobileNet outperformed the baseline CNN, achieving 87% accuracy, though a 30% validation loss suggests possible overfitting, requiring further optimization for robustness in clinical settings. Future work will emphasize hyperparameter tuning, regularization, and transfer learning. Integrating behavioral data with facial analysis could improve diagnosis for underdiagnosed groups. These findings suggest Random Forest's high accuracy and balanced precision-recall metrics could enhance clinical workflows. MobileNet's lightweight structure also shows promise for resource-limited environments, enabling accessible ASD screening. Addressing model explainability and clinician trust will be vital.