< Back to previous page

Project

Machine Reading of Patient Records

Documents written in natural language in the records of patients contain information valuable for the management of patient data. However, the information needs to be unlocked from the natural language texts. In this project we want to focus on the extraction of entities, relations and attributes that characterize the patient history, anamnesis and descriptions of clinical examinations. The scientific challenges are mastering the domain-specific (sometimes physician-specific) terminology and linking it to a terminological standard, analyzing a language which is not well formed, and extracting the information with a limited amount of training data. The text mining needs to be performed in a legal framework that respects the privacy of the patients.
Date:1 Oct 2015 →  30 Sep 2017
Keywords:Patient Records
Disciplines:Applied mathematics in specific fields, Computer architecture and networks, Distributed computing, Information sciences, Information systems, Programming languages, Scientific computing, Theoretical computer science, Visual computing, Other information and computing sciences