@inproceedings{ZubkeKatzensteinerBott2020,
  author    = {Maximilian Zubke and Matthias Katzensteiner and Oliver J. Bott},
  title     = {Integration of Unstructured Data into a Clinical Data Warehouse for Kidney Transplant Screening – Challenges \& Solutions},
  series = {Digital Personalized Health and Medicine : Proceedings of MIE 2020 (Studies in Health Technology and Informatics ; 270)},
  isbn      = {978-1-64368-083-5},
  issn      = {1879-8365},
  doi       = {10.25968/opus-3060},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:960-opus4-30605},
  pages     = {272 -- 276},
  year      = {2020},
  abstract  = {After kidney transplantation graft rejection must be prevented. Therefore, a multitude of parameters of the patient is observed pre- and postoperatively. To support this process, the Screen Reject research project is developing a data warehouse optimized for kidney rejection diagnostics. In the course of this project it was discovered that important information are only available in form of free texts instead of structured data and can therefore not be processed by standard ETL tools, which is necessary to establish a digital expert system for rejection diagnostics. Due to this reason, data integration has been improved by a combination of methods from natural language processing and methods from image processing. Based on state-of-the-art data warehousing technologies (Microsoft SSIS), a generic data integration tool has been developed. The tool was evaluated by extracting Banff-classification from 218 pathology reports and extracting HLA mismatches from about 1700 PDF files, both written in german language.},
  language  = {en}
}