A Machine Learning Approach for Diagnosing Neurological Disorders using Longitudinal Resting-State fMRI

This paper focuses on developing a Machine Learning (ML) framework for classifying neurological disorders using longitudinal Resting State Functional Magnetic Resonance Imaging (rs-fMRI) samples. Neurological disorders considered in this study are Autism Spectrum disorder (ASD) and Alzheimer's Disease (AD). The proposed framework is applied on longitudinal rs-fMRI samples from ABIDE II dataset for the classification of ASD subjects from Typical Development (TD) subjects and rsfMRI samples from OASIS-3 longitudinal neuroimaging dataset for the classification of early Mild Cognitive Impairment (EMCI) subjects from Normal Control (NC) subjects. To our knowledge, this study is the first attempt to model a longitudinal ML framework on these two benchmarking datasets and hence serves as a baseline for future research.