Subtypes of Relapsing-Remitting Multiple Sclerosis Identified by Network Analysis

ABSTRACT The objective of this study was to use network analysis to identify subtypes of relapsing-remitting multiple sclerosis subjects based on their cumulative signs and symptoms. We reviewed the electronic medical records of 120 subjects with relapsing-remitting multiple sclerosis and recorded signs and symptoms. Signs and symptoms were mapped to a neuroontology and then collapsed into 16 superclasses by subsumption and normalized. Bipartite (subject-feature) and unipartite (subject-subject) network graphs were created using Gephi. Degree and weighted degree were calculated for each node. Graphs were partitioned into communities using the modularity score. Feature maps were used to visualize differences in features by the community. Network analysis of the unipartite graph yielded a higher modularity score (0.49) than the bipartite graph (0.247). Network analysis can partition multiple sclerosis subjects into communities based on signs and symptoms. Communities of subjects with predominant motor, sensory, pain, fatigue, cognitive, behavior, and fatigue features were found. Larger datasets and additional partitioning algorithms are needed to confirm these results and elucidate their clinical significance.