Summary of the paper
| Title | Influence of Module Order on Rule-Based De-identification of Personal Names in Electronic Patient Records Written in Swedish |
|---|---|
| Authors | Elin Carlsson and Hercules Dalianis |
| Abstract | Electronic patient records (EPRs) are a valuable resource for research but forconfidentiality reasons they cannot be used freely. In order to make EPRsavailable to a wider group of researchers, sensitive information such aspersonal names has to be removed. De-identification is a process that makesthis possible. Both rule-based as well as statistical and machine learningbased methods exist to perform de-identification, but the second methodrequires annotated training material which exists only very sparsely forpatient names. It is therefore necessary to use rule-based methods forde-identification of EPRs. Not much is known, however, about the order in whichthe various rules should be applied and how the different rules influenceprecision and recall. This paper aims to answer this research question byimplementing and evaluating four common rules for de-identification of personalnames in EPRs written in Swedish: (1) dictionary name matching, (2) titlematching, (3) common words filtering and (4) learning from previous modules.The results show that to obtain the highest recall and precision, the rulesshould be applied in the following order: title matching, common wordsfiltering and dictionary name matching. |
| Language | Evaluation methodologies |
| Topics | Named Entity recognition, Person Identification, Evaluation methodologies |
Full paper  |
Influence of Module Order on Rule-Based De-identification of Personal Names in Electronic Patient Records Written in Swedish |
| Bibtex | @InProceedings{CARLSSON10.46, author = {Elin Carlsson and Hercules Dalianis}, title = {Influence of Module Order on Rule-Based De-identification of Personal Names in Electronic Patient Records Written in Swedish}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |