Exploiting Thesauri Knowledge in Medical Guideline Formalization

Summary

Objectives: As in software product lifecycle, the effort spent in maintaining medical knowl edge in guidelines can be reduced, if modularization, formalization and tracking of domain knowledge are employed across the guideline development phases.

Methods: We propose to exploit and combine knowledge templates with medical background knowledge from existing thesauri in order to produce reusable building blocks used in guideline development. These templates enable easier guideline formalization, by describing how chunks of medical knowledge can be combined into more complex ones and how they are linked to a textual representation.

Results: By linking our ontology used in guideline formalization with existing thesauri, we can use compilations of thesauri knowledge as building blocks for modeling and maintaining the content of a medical guideline.

Conclusions: Our paper investigates whether medical knowledge acquired from several medical thesauri can be molded on a guideline pattern, such that it supports building of executable models of guidelines.

Keywords

Linguistic and control patterns - guideline modeling and formalization

• References

• 1 MeSH (Medical Subject Headings) (Internet home-page, cited June 15, 2008). Available from: http://www.nlm.nih.gov/mesh/meshhome.html.
• 2 National Cancer Institute (NCI) Ontology (Internet homepage, cited June 15, 2008). Available from: http://www.mindswap.org/2003/CancerOntology/.
• 3 Unified medical language system (Internet home-page, cited June 15, 2008). Available from: http://www.nlm.nih.gov/research/umls.
• 4 Shahar Y, Young O, Shalom E, Mayaffit A, Moskovitch R, Hessing A, Galperin M. DEGEL: A hybrid, multiple-ontology framework for specification and retrieval of clinical guidelines. In: Proc 9th Conference on Artificial Intelligence in Medicine – Europe (AIME 2003). Protaras, Cyprus: 2003. pp 122-131.
• 5 Aronson AR. Effective mapping of biomedical text to the UMLS metathesaurus: the MetaMap program. In: Proc of American Medical Informatics Association (AMIA) Symposium, National Library of Medicine. 2001. pp 17-21. PMID: 11825149.
• 6 Bodenreider O, Rindflesch TC, Burgun A. Unsupervised, corpus-based method for extending a biomedical terminology. In: Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain. Phildadelphia, Pennsylvania: July 11-11 2002. Vol 03 pp 53-60. Association for Computational Linguistics, Morristown, NJ, 53-60. DOI = http://dx.doi.org/10.3115/1118149.1118157.
• 7 Dutch Institute for Healthcare Improvement (CBO).. Guideline for the Treatment of Breast Carcinoma.,. 2002 PMID: 12474555.
• 8 Cimiano P, Volker J. Text2onto: A framework for ontology learning and data-driven change discovery. In: Metais E, Montoyo A, Munoz R. editors. NLP and Information Systems. 10th International Conference on Applications of Natural Language to Information Systems, NLDB 2005, Alicante, Spain, June 15-17, 2005. Springer; 2005. pp 227-238. LNCS Vol. 3513.
• 9 De Coronado S, Haber MW, Sioutos N, Tuttle MS, Wright LW. NCI Thesaurus: using science-based terminology to integrate cancer research results. Stud Health Technol Inform 2004; 107 Pt (01) 33-37.
• 10 Do Amaral MB, Roberts A, Rector AL. NLP techniques associated with the OpenGALEN ontology for semi-automatic textual extraction of medical knowledge: abstracting and mapping equivalent linguistic and logical constructs. In: Overhage JM. editor. Proceedings of the 2000 American Medical Informatics Association Annual Symposium (AMIA 2000). Los Angeles: 2000. pp 76-80.
• 11 Ten Teije A, Balser M, Coltell O, van Croonenborg J, Duelli C, van Harmelen F. et al. Protocure: Supporting the development of medical protocols through formal methods. In: Proc of the Symposium on Computerized Guidelines and Protocols (CGP-04). Prague: April 2004. IOS Press; pp 103-107.
• 12 Johnson P, Miksch S, Shahar Y. ASBRU: A task-specific, intention-based, and time-oriented language for representing skeletal plans. In: PierretGolbreich C, Filby I, Wijngaards N, Motta E, van Harmelen F. editors. Proceedings of the 7th Workshop on Knowledge Engineering: Methods and Languages (KEML-97). Open University UK: 1997. pp 9-21.
• 13 Scottish Intercollegiate Guidelines Network.. Breast Cancer in Women, SIGN#29. SIGN, 1998
• 14 Royal College of Radiologists.. Guidelines on the non-surgical management of lung cancer. Springer-Verlag; 2001
• 15 Rindflesch TC, Aronson AR. Semantic processing for enhanced access to biomedical knowledge. In: Real World Semantic Web Applications. IOS Press; 2001. pp 157-172.
• 16 Boxwala AA, Peleg M, Tu S, Ogunyemi O, Zeng QT, Wang D, Patel VL, Greenes RA, Shortliffe EH. GLIF3: a representation format for sharable computer-interpretable clinical practice guidelines. J of Biomedical Informatics 2004; 37 (03) 147-161. PMID: 15196480.
• 17 Van der Maas A, ter Hofstede A, ten Hoopen AJ. Requirements for medical modeling languages. JAMIA 2001; 8 (02) 146-162. PMID: 11230383.
• 18 Serban R, Ten Teije A, Van Harmelen F, Marcos M, Polo-Conde C. Ontology-driven extraction of linguistic patterns for modelling clinical guidelines. In: Miksch S. et al., editors. Proceedings 10th Conference on AI in Medicine (AIME 05), LNAI 3581, Aberdeen, Scotland. Springer; 2005. pp 191-203. DOI: 10.1007/11527770_28.