Mapping of Clinical Documentation to Ontology

• Edson José Pacheco UTFPR
• Percy Nohama UTFPR
• Stefan Schulz University Medical Center

Abstract

Clinical documentation requires the representation of fine-grained descriptions of patients' history, evolution, and treatment. These descriptions are materialized in findings reports, medical orders, as well as in evolution and discharge summaries. In most clinical environments natural language is the main carrier of documentation. Written clinical jargon is commonly characterized by idiosyncratic terminology, a high frequency of highly context-dependent ambiguous expressions (especially acronyms and abbreviations). Violations of spelling and grammar rules are common. The purpose of this work is to map free text from clinical narratives to a domain ontology. To this end, natural language processing (NLP) tools will be combined with a heuristic of semantic mapping.

References

D. Cohn et al., Active learning with statistical models, Journal of Artificial Intelligence Research, 1996:4, 129–145.

E. Agirre and P. Edmonds (eds.) 2007. Word Sense Disambiguation: Algorithms and Applications. Text, Speech and Language Technology, Springer, Heidelberg, Germany, 2007.

IHTSDO (International Health Terminology Standards Development Organisation). Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT), 2008. Available from: [link]. Last accessed: 20 March 2009.

K. Markó, Foundation, Implementation and Evaluation of the MorphoSaurus System, Doctoral Dissertation, Freiburg, Germany, 2008.

K. Tomanek et al., Approximating learning curves for active-learning-driven annotation, In Proceedings of the Language Resources and Evaluation (LREC 2008), Marrakesh, Morocco, 2008.

MITA (Medical Imaging and Technology Alliance). Digital Imaging and Communication in Medicine (DICOM), 2008. Available from: [link]. Last accessed: 20 March 2009.

NCI (National Cancer Institute). NCI Enterprise Vocabulary Services (EVS), 2008. Available from: [link]. Last accessed: 20 March 2009.

NHS (World Health Organization). Dictionary of Medicines and Devices (dm+d), 2008. Available from: [link]. Last accessed: 20 March 2009.

NLM (United States National Library of Medicine). Medical Subject Headings (MeSH), 2008. Available from: [link]. Last accessed: 20 March 2009.

NLMa (United States National Library of Medicine). RxNorm, 2008. Available from: [link]. Last accessed: 20 March 2009.

OpenNLP, [link]. Last accessed: 20 March 2009.

R. Mihalcea. Graph-based ranking algorithms for sentence extraction, applied to text summarization, In Proceedings of the 42nd Annual Meeting of the Association for Computational Lingusitics (ACL 2004), Barcelona, Spain, 2004.

REGENSTRIEF INSTITUTE. Logical Observation Identifiers Names and Codes (LOINC), 2008. Available from: [link]. Last accessed: 20 March 2009.

UMC (Uppsala Centre for International Drug Monitoring). WHO Drug Dictionary Enhanced, 2008. Available from: [link]. Last accessed: 20 March 2009.

WHO (World Health Organization). International Classification of Diseases (ICD), 2008. Available from: [link]. Last accessed: 20 March 2009.

WHOCC (WHO Collaborating Centre for Drug Statistics Methodology). Anatomical Therapeutic Chemical Classification System (ATC), 2008. Available from: [link]. Last accessed: 20 March 2009.