|
|
Methods and tools for the development of computer-interpretable guidelines |
|
Stepper |
|
Mark-up tool for narrative guidelines |
|
| keywords |
Knowledge representation, clinical practice guideline document model, clinical practice guidelines, XML, computer interpretable guidelines, markup
introduced in 2003 |
developed by |
EuroMISE centrum – Kardio, University of Economics, Prague, Czech Republic |
| introduced |
Development started in 2001; first beta version
released in 2003.
|
| status |
Development on hold (2006) |
| support |
Ministry of Education of the Czech Republic |
| in use |
Evaluation activities have taken place in
hypertension. |
| tools |
|
|
| description |
The Stepper project has two main goals:
- To develop a stepwise method for formalization (in this context, XML transformation) of text documents of clinical guidelines
- To develop the Stepper tool, an XML editor enhanced with features to support the above method
Some guideline formalisation methods favour a one-step, top-down approach using a a pre-defined model and the involvement of a domain expert and knowledge engineer. This process that can suffer from a lack of transparency (as shown, for example, in the difficulty of tracing back the exact source of every piece of knowledge in a resulting guideline application.
Stepper, on the other hand, has been designed as a document-centric tool which takes a guideline text as its starting point, and splits the fomalisation process into multiple user-definable steps, each of which corresponds to an interactive XML transformation. The result of each step is an increasingly formalized version of the source document.
[Click for full size image]

Stepper Screen - click for full size image
Stepper contains an embedded XSLT processor which carries out non-interactive transformation. Mark-up and interative transformation are carried out by by rules expressed in a new transformation language based on XML called XKBT (XML Knowledge Block Transformation).
The Stepper method and tool have been tested in the formalization of WHO/ISH (International
Society of Hypertension) hypertension guidelines and in guidelines for breast cancer care.
Evaluation has shown that using step-by-step approach makes it possible to transform medical
guidelines into fragments of operational code (e.g. Java) or into an instance of medical ontology (such as Asbru).
Rules for transforming guidelines into the Asbru language have been implemented.
Although Stepper has been designed to support a bottom-up, stepwise approach to guideline formalisation, the tool is not yet designed to support the development of a complete decision support application. A series of XML transformations cannot produce a standalone, exectuable application.
|
| benefits |
A main advantage of Stepper lies in the clarity of the step-by-step approach it fosters. All user activities (all single transformations) are documented in
XML files so another user can easily review the whole transformation process.
Stepper provides an interface showing the interconnection between the source text and the model.
The document-centric approach supported by the Stepper tool ensures that
all additions of "external knowledge" (knowledge not contained in textual
guidelines) are kept track of in the guideline model.
The approach can also help highlight knowledge missing from a
source guideline.
|
|
| references |
Ruzicka M, Svatek V.
Mark-up based analysis of narrative guidelines with the Stepper tool.
Stud Health Technol Inform. 2004;101:132-6.
[PubMed]
[University of Economics, Prague]
|
"
The Stepper tool was developed to assist a knowledge engineer in developing a computable version of narrative guidelines.
The system is document-centric: it formalises the initial text in multiple user-definable steps corresponding to interactive XML transformations. In this paper, we report on experience obtained by applying the tool on a narrative guideline document addressing unstable angina pectoris. Possible role of the tool and associated methodology in developing a guideline-based application is also discussed.
"
|
|
Svátek V, Ružicka M. Step-by-step mark-up of medical guideline documents.
Int J Med Inform. 2003 Jul;70(2-3):329-35.
[PubMed]
[ScienceDirect]
|
"
Approaches to formalization of medical guidelines can be divided into model-centric and document-centric. While model-centric approaches dominate in the development of clinical decision support applications, document-centric, mark-up-based formalization is suitable for application tasks requiring the 'literal' content of the document to be transferred into the formal model. Examples of such tasks are logical verification of the document or compliance analysis of health records. The quality and efficiency of document-centric formalization can be improved using a decomposition of the whole process into several explicit steps. We present a methodology and software tool supporting the step-by-step formalization process. The knowledge elements can be marked up in the source text, refined to a tree structure with increasing level of detail, rearranged into an XML knowledge base, and, finally, exported into the operational representation. User-definable transformation rules enable to automate a large part of the process. The approach is being tested in the domain of cardiology. For parts of the WHO/ISH Guidelines for Hypertension, the process has been carried out through all the stages, to the form of executable application, generated automatically from the XML knowledge base.
" |
|
Ružicka M., Svátek V. An interactive approach to rule–based transformation of XML documents, In: Lubos Popelínský (ed.), Datakon 2003, Proceedings of the Annual Database Conference, p. 277–288.
[]
[University of Economics, Prague]
|
"
The quality of document–centric formalisation of medical guidelines can be improved using a decomposition of the whole process into several explicit steps. We present a methodology and a software tool supporting the step–by–step formalisation process. The knowledge elements can be marked up in the text with increasing level of detail, rearranged into an XML knowledge base and exported into the operational representation. Semi–automated transitions can be specified by means of rules. The approach has been tested in a hypertension application.
" |
|
|
| contact |
Marek Ružicka or
Vojtech Svátek University of Economics Prague
Nam.W.Churchilla 4 13067 Praha 3 Czech Republic
T: +420 224095462
W: Vojtech Svátek home page
|
| links |
|
|
| acknowledgements |
| Marek Ružicka, Vojtech Svátek, University of Economics, Prague |
| page history |
Entry on OpenClinical: 01 October 2004
Last main updates: 20 October 2004; (06 April 2005) 14 March 2006
Design - template v0.3: 25 June 2005. |
|
|
|
|