gms | German Medical Science

36. Jahrestagung der Deutschsprachigen Arbeitsgemeinschaft für Verbrennungsbehandlung (DAV 2018)

10.01. - 13. 01.2018, Garmisch-Partenkirchen

Domain-Expert-Driven Knowledge Discovery from Medical Databases

Meeting Abstract

Search Medline for

  • presenting/speaker Michael Giretzlehner - Johannes Kepler University, RISC Software GmbH, Forschungsabteilung Medizin-Informatik, Hagenberg, Österreich

Deutschsprachige Arbeitsgemeinschaft für Verbrennungsbehandlung. 36. Jahrestagung der Deutschsprachigen Arbeitsgemeinschaft für Verbrennungsbehandlung (DAV 2018). Garmisch-Partenkirchen, 10.-13.01.2018. Düsseldorf: German Medical Science GMS Publishing House; 2018. DocV 55

doi: 10.3205/18dav66, urn:nbn:de:0183-18dav667

Published: January 9, 2018

© 2018 Giretzlehner.
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 License. See license information at



Structured collections of medical data such as clinical information systems, disease registries, or study databases build the base for new insights in complex medical issues. However, this complexity of the medical domains requires an experienced medical expert to interpret the data and extract new knowledge. On the other hand, it is well known that the technical complexity of handling large database systems and the application of advanced datamining algorithms is an enormous technical and psychological burden for researching domain experts – especially without explicit IT support. This often leads to the situation that general purpose office applications (e.g. MS Excel) are used for data-storage, -management and -processing. Moreover, data exploration and analysis are often limited to descriptive statistics or simple statistical tests. Experience in both worlds is needed – the medical domain and the IT domain, including databases and algorithms – to perform data-based research on a high level.

We present a domain-independent research data-platform which actively supports the medical research in these complex IT tasks such as data-acquisition, data-processing and -plausibilization, data exploration and analysis. Our ontology-based research platform adapts itself to the requirements of the current research project and allows the user to work with his complex data and to find new correlations and complex patterns. Moreover, we question the established process models of knowledge discovery, which traditionally see the domain expert in a customer-like, supervising role. The focus on the researching domain experts allows these researchers to overtake a central role in their own research projects and take advantage of complex data analysis algorithms to gain new insights, derive new research hypothesises and extract knowledge from their data.