MedISys - Medical Information System

The Medical Information System (MedISys) is a fully automatic 24/7 public health surveillance system monitoring infectious diseases, bioterrorism, and chemical, biological, radiological and nuclear (CBRN) threats in open-source media. MedISys became online in August 2004 and has been continuously extended. At present, it processes approximately 90000 news articles from more than 2200 news sites in 50 languages per day (figures of July 2009). In this article, we give a broad overview of MedISys. On the one hand, we explain the technology behind MedISys, describing the processing chain from the definition of news sources, scraping and grabbing articles from the internet, text mining, event extraction with the Pattern-based Understanding and Learning System (PULS, developed by the University of Helsinki), clustering to the display of results. On the other hand, the web interface and service applications are shown from a user¿s perspective. Users can display world maps in which event locations are highlighted, statistics on reporting about diseases, countries and combinations thereof and can apply filters for language, disease or location or filters with orthogonal categories, e.g. outbreaks, via the user interface. Specific entities such as persons, organizations and geographical information are also identified automatically. The Rapid News Service (RNS) enables users to manually select and organize articles, add comments, create newsletters in various formats, and distribute these to user-defined groups. Thus, RNS allows human moderation facilitating the work of analyst teams. Finally, we briefly discuss our vision how open-source media monitoring will develop over the next few years.JRC.DG.G.2-Global security and crisis managemen