DFKI-LT - mEx - An Information Extraction Platform for German Medical Text
mEx - An Information Extraction Platform for German Medical Text
4 Proceedings of the 11th International Conference on Semantic Web Applications and Tools for Healthcare and Life Sciences (SWAT4HCLS'2018), Antwerp, Belgium, o.A., 12/2018
In recent years, clinical text processing gained a lot of attention. Easing the access to information for medical personnel, combined with the ability to track and forecast a patients development, makes structured information extraction from medical text sources a crucial component. Due to a specialized domain language, existing tools trained on different domains might not yield the desired performance. Clinical data is highly sensitive and therefore a scarce resource. When focusing on non-English languages, the situation is even worse. Besides the limited language resources, hardly any tools are freely available to process clinical text. To address this limitation we present mEx, an Information Extraction system for German medical text. While specialized on the nephrology domain, mEx is powered by generic components that can be adopted to any medical domain. We provide mEx as an online tool that demonstrates various functionalities to process medical text. It can be tested via web front-end or accessed via REST API.