Prediction Of Autism Spectrum Disorder Using Machine Learning

This is to investigate the predictive potential of electroencephalogram (EEG) signals extracted from children diagnosed with autism spectrum disorder (ASD). The objective is to utilize machine learning techniques, specifically logistic regression, to discern patterns within EEG data that could aid in the early prediction of ASD. EEG signals collected from autism-affected children are analyzed and processed to extract relevant features. Subsequently, these features are used as inputs to train a logistic regression model. Thestudy evaluates the model's performance in distinguishing between ASD and typically developing individuals, aiming to provide a reliable predictive toolfor identifying ASD based on EEG signals. Results suggest promising prospects for leveraging EEG data and machine learning methods in the early detection and potential prediction of autism spectrum disorder in children.