Autism Screening in Toddlers and Adults Using Deep Learning and Fair AI Techniques

Abstract

Autism spectrum disorder (ASD) has been associated with conditions like depression, anxiety, epilepsy, etc., due to its impact on an individual’s educational, social, and employment. Since diagnosis is challenging and there is no cure, the goal is to maximize an individual’s ability by reducing the symptoms, and early diagnosis plays a role in improving behavior and language development. In this paper, an autism screening analysis for toddlers and adults has been performed using fair AI (feature engineering, SMOTE, optimizations, etc.) and deep learning methods. The analysis considers traditional deep learning methods like Multilayer Perceptron (MLP), Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM), and also proposes two hybrid deep learning models, i.e., CNN–LSTM with Particle Swarm Optimization (PSO), and a CNN model combined with Gated Recurrent Units (GRU–CNN). The models have been validated using multiple performance metrics, and the analysis confirms that the proposed models perform better than the traditional models.

Development of an eye-tracking system based on a deep learning model to assess executive function in patients with mental illnesses

“…Second, the small number of participants in the impaired group resulted in highly imbalanced datasets, which limits the validity and reliability of the assessment model in this study. To address this, the split dataset was strati ed to maintain class label proportions consistent with those of the original dataset, and synthetic minority oversampling technique (SMOTE) 31 data augmentation was implemented, as in previous studies dealing with similarly imbalanced datasets [32][33][34] . However, our results should be interpreted with caution due to the relatively small and imbalanced sample size of the original dataset.…”