论文信息 - The Stockholm EPR Corpus – Characteristics and Some Initial Findings

The Stockholm EPR Corpus – Characteristics and Some Initial Findings

This paper describes the characteristics of the Stockholm Electronic Patient Record Corpus (the SEPR Corpus), an important resource for performing research on clinical data. The whole SEPR corpus contains over one million patient records from over 2 000 clinics. We compare parts of the SEPR corpus with the Swedish PAROLE Corpus and describe the differences and similarities. We also describe a set of experiments we have initiated on the SEPR corpus, experiments whose outcome we believe will, in the long run, contribute to the medical research as well as the daily life of the clinician. Moreover, this corpus contains characteristics that are very interesting from a linguistic point of view, such as domain specific compounds and abbreviations, and various narratives.

H. Dalianis | Martin Hassel | S. Velupillai

[1] Martin Gellerstam,et al. The Bank of Swedish , 2000, LREC.

[2] Antoine Geissbühler,et al. Using lexical disambiguation and named-entity recognition to improve spelling correction in the electronic patient record , 2003, Artif. Intell. Medicine.

[3] A. Bourke,et al. Feasibility study and methodology to create a quality-evaluated database of primary care data. , 2004, Informatics in primary care.

[4] Christopher G. Chute,et al. Domain-specific language models and lexicons for tagging , 2005, J. Biomed. Informatics.

[5] Martin Hassel. Resource Lean and Portable Automatic Text Summarization , 2007 .

[6] K. Bretonnel Cohen,et al. A shared task involving multi-label classification of clinical free text , 2007, BioNLP@ACL.

[7] Dimitrios Kokkinakis,et al. Identification of Entity References in Hospital Discharge Letters , 2007, NODALIDA.

[8] Sumithra Velupillai,et al. Revealing Relations between Open and Closed Answers in Questionnaires through Text Clustering Evaluation , 2008, LREC.

[9] János Csirik,et al. The BioScope corpus: biomedical texts annotated for uncertainty, negation and their scopes , 2008, BMC Bioinformatics.

[10] Peter Szolovits,et al. A de-identifier for medical discharge summaries , 2008, Artif. Intell. Medicine.

[11] John F. Hurdle,et al. Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research , 2008, Yearbook of Medical Informatics.