VFF: Text-based disease classification of medical literature

In a recent collaboration with researchers from Indiana University, I have begun exploring ways to use natural language terms and phrases to detect broad disease categories in the titles of articles from the PubMed database. An early attempt classifies four million papers written in five different languages over the last 50 years into nine broad disease categories, visualizing the results as flows and streams to explore the changing focus of medical research over time. This early project was submitted as an entry to the ACM Web Science 2014 Conference, where it received an award as a top student submission. Future work includes refining disease detection with more sophisticated text and data mining, as well as developing new visual interfaces to the results.