Multiple sclerosis (MS) is an inflammatory, demyelinating and neurodegenerative disease of the central nervous system (CNS). Despite progress in understanding immunogenetic aspects of this disease, the mechanisms involved in lesion formation are unknown. To gain new insights into the neuropathology of MS, we used an innovative integration of Fourier transform infrared (FT-IR) microspectroscopy, bioinformatics, and a synchrotron light source to analyze macromolecular changes in the CNS during the course and prevention of experimental autoimmune encephalomyelitis (EAE), an animal model for MS. We report that subtle chemical and structural changes not observed by conventional histology were detected before the onset of clinical signs of EAE. Moreover, trained artificial neural networks (ANNs) could discriminate, with excellent sensitivity and specificity, pathology from surrounding tissues and the early stage of the disease progression. Notably, we show that this novel measurement platform can detect characteristic differences in biochemical composition of lesion pathology in animals partially protected against EAE by vaccination with Nogo-A, an inhibitor of neural outgrowth, demonstrating the potential for automated screening and evaluation of new therapeutic agents.