Diseases across the Top Five Languages of the PubMed Database: 1961-2012

Collaborators: Inna Kouper, Trevor Edelblute

January 2014 to June 2014

A team submission to the Data Visualization Challenge for WebSci’14. Original dataset of historical MEDLINE/PubMed article titles was enhanced with additional metadata and parsed for references to diseases. Visualization received the Best Student Award.

Responsibilities:

• Developed python scripts to locate disease phrases in article titles
• Developed exploratory visualizations in a variety of tools to help the team narrow down to a particular narrative approach
• With continued feedback from team members, designed the submitted visualization using Raw Graphs, Wordle, and Adobe Illustrator.

Project Outputs:

Awards/Honors

• Zoss, Angela M., Edelblute, Trevor and Kouper, Inna. (2014). Diseases across the Top Five Languages in PubMed. Visualization submitted to Data Challenge at ACM Web Science 2014 Conference. Bloomington, IN. Won Student Best Entry.

Presentations at Conferences, Professional Gatherings

• Zoss, Angela M. (February 11, 2015). Text-based disease classification of medical literature. Presentation at the Duke Center for Health Informatics Informatics Research Seminar Series, Durham, NC.