Diagnostic Classification of Autism Spectrum Disorder Using SD Maps of fMRI Data and Machine Learning

Purpose: Autism spectrum disorder (ASD) is a neurodevelopmental condition characterised by social, behavioural and communication traits. The diagnosis of ASD is challenging, particularly due to the heterogeneity of symptoms, overlapping clinical features with other neurodevelopmental conditions and the current reliance on subjective behavioural assessments. Our study investigates the effectiveness of features computed from standard deviation (SD) maps of resting-state functional magnetic resonance imaging (rs-fMRI) in discriminating between ASD and typical development (TD). Methods: The rs-fMRI data of TD and ASD considered in this study were obtained from the ABIDE-I and ABIDE-II databases. Initially, the images were pre-processed using a standard pipeline. Further, 3D SD maps were generated, and 110 features were computed from the maps. We fed the features to four machine learning models, such as logistic regression (LR), ridge classifier, gradient boosting, and extreme gradient boosting. We performed the grid search to optimize the parameters and evaluated the models with 5-fold nested cross-validation. Results: We achieved an average 5-fold classification accuracy of 70.71% using LR. Our results revealed that the 3D shape and global statistical features contributed well to the model. Conclusion: The findings demonstrate that features extracted from 3D SD maps provide a robust and clinically meaningful framework for diagnosing ASD.