Seyfang, Vienna University of Technology, Institute of Software Technology
and Interactive System, Vienna, Austria
Previous experience showed that it is very difficult to create Asbru plans based on the original guideline (formulated in English or any other natural language) in a single step. An intermediate representation is needed to divide the abstraction step from nearly unformatted free text to a precise notation such as Asbru.
In the framework of the Protocure II project we developed MHB (the Many-Headed Bridge to guideline formalization). Its syntax is based on XML and allows enough freedom to model vague concepts from the original guideline text while organizing the information in a structured way and with defined semantics.
The guideline is dissected into chunks of information. The aspects of each chunk are described along eight different, independent dimensions. These are: control flow, data flow, temporal aspects, evidence, background information, patient-related aspects, resources, and document structure.
Using the DELT/A, the links between the original guideline text, its representation in MHB, and its representation in Asbru are easily maintained. This ensures easy tracking of misunderstandings, modeling flaws, and abnormalities in the original guideline text.
An additional advantage of MHB is its independence from Asbru. Therefore,
the knowledge engineer using MHB does not need to know Asbru and an MHB model
of a guideline can be used as a basis to model the guideline in other representations
such as GLIF, too.
|Papers||Deliverable 2.2a of EU project Protocure|
|Seyfang, A.; Miksch, S.; Polo Conde, C.; Wittenberg, J.; Marcos, M.; Rosenbrand K.: MHB - A Many-Headed Bridge between Informal and Formal Guideline Representations In S. Miksch, J. Hunter, and E. Keravnou (eds.) Artificial Intelligence in Medicine. Proceedings of the 10th Conference on Artificial Intelligence in Medicine (AIME 2005), Aberdeen, UK; Springer, pp. 146-150, 2005.|
|Polo-Conde, C.; Marcos, M.; Seyfang, A.; Wittenberg, J.; Miksch, S.; Rosenbrand, K.: Assessment of MHB: an Intermediate Language for the Representation of Medical Guidelines. In Marin, R.; Onaindia, E.; Bugarin, A.; Santos, J. (eds.) Proceedings of the 10th Conference of the Spanish Association for Artificial Intelligence (CAEPIA-05), University of Corunna, Corunna, pp. I-19 - I-28, 2005.|
|Seyfang, A.; Miksch, S.; Marcos, M.; Wittenberg, J.; Polo-Conde, C.; Rosenbrand, K.: Bridging the Gap between Informal and Formal Guideline Representations In G. Brewka, S. Coradeschi, A. Perini, and P. Traverso (ed.), European Conference on Artificial Intelligence (ECAI-2006), IOS Press, 447-451, 2006.|
|Seyfang, A.; Martinez-Salvador, B.; Serban, R.; Wittenberg, J.; Miksch, S.; Marcos, M.; ten Teije, A.; Rosenbrand, K.: Maintaining Formal Models of Living Guidelines Efficiently In Artificial Intelligence in Medicine. Proceedings of the 11th Conference on Artificial Intelligence in Medicine (AIME 2007), LNAI 4594, Amsterdam, The Netherlands, 441-445, 2007.|
|Seyfang, A.; Kaiser, K.; Miksch, S.: Modelling Clinical Guidelines and Protocols for the Prevention of Risks Against Patient Safety. In Proc. of the 22nd International Congress of the European Federation for Medical Informatics (MIE 2009), Sarajevo, Bosnia-Herzegovina, 2009, accepted.|
|Kaiser, K.; Seyfang, A.: Modelling Clinical Guidelines and Protocols in MHB. A Tutorial, Technical Report Asgaard-TR-2010-1, Vienna University of Technology, Institute of Software Technology and Interactive Systems, March 2010.|
Guideline modeling languages at OpenClinical
» Asbru at the Asgaard website
» Other publications from the Protocure project
|Funding||This work is part of the EU STREP project Protocure II