Deep learning for diagnosing autism spectrum disorder using EEG with upright and inverted face processing tasks

Key Points

• Deep learning models achieve high accuracy in diagnosing autism spectrum disorder using EEG data, particularly during face processing tasks.
• The analysis compares performance of upright and inverted face processing, highlighting distinct patterns associated with autism.
• Data was collected from EEG recordings during face processing tasks, revealing significant neural differences in individuals with autism.
• These findings suggest that deep learning techniques may enhance diagnostic accuracy for autism spectrum disorder, indicating future research directions.