top of page

WORK PACKAGE 4 - Text Mining of Unstructured Healthcare Data

PARTNERS

  • The Institute of Health Information and Statistics of the Czech Republic

  • Charles University

  • Technological University Dublin

  • Ontotext

  • University Murcia

  • Vall D'Hebron Research Institute

  • Institute of Psychiatry and Neurology

  • University Hospital Bucharest

  • University Multi-Profile Hospital for Active Treatment "St. Naum“

  • Health Management Institute

  • University of Glasgow

  • International Clinical Research Institute

1.png

OBJECTIVES

2.png

  • Develop a software application for automation of the entire process that will be supported by an automatic NLP pipeline for information extraction followed by manual validation of the extracted information before it is inserted into RES-Q.  English and at least two other EU languages will be supported natively, additional languages will be supported by machine translation of the source documents into English and application of the English extraction pipeline.

bottom of page