There are over 34 million citations for biomedical literature on PubMed, which is great for the spread of scientific information, but it makes it difficult to keep pace with new ideas and research occurring in a field. Here we develop an unsupervised contextual-based Natural Language Processing and Topic Modeling Network knowledge map visualization pipeline named ‘Topic Space’ to efficiently analyze large amounts of contextual data. Topic Space was used to analyze Global Health Disparities and Biomedical Technologies abstracts. Both fields have extensive, specialized research being performed and key topics and key words were highlighted. Despite potential overlapping subject matter, there is a disconnect between Biomedical researchers and Global Health researchers. Topic Space is used to build network visualization maps for Health Disparities and Biomedical Technologies to related topics in both fields and potentially bridge the gap between these two fields.
