GOALS: Modeling Clinical Guidelines Based on TimeML Concepts

R. Wenzina, K. Kaiser:
"GOALS: Modeling Clinical Guidelines Based on TimeML Concepts";
Vortrag: 5th International Conference on Digital Health 2015 (DH'15), Florenz, Italien; 18.05.2015 - 22.05.2015; in:"DH '15 Proceedings of the 5th International Conference on Digital Health 2015", ACM, New York, New York, NY (2015), ISBN: 978-1-4503-3492-1; S. 121 - 128.

[ Publication Database ]

Abstract:


Clinical practice guidelines aim at raising the quality of healthcare. They are written in a narrative style and have to be translated into a computer-interpretable guideline (CIG) to be usable in a clinical software application. In this project we present the GOALS methodology which defines a stepwise approach to support this modeling process. The methodology is specified independently from the target CIG language and uses a guideline's text annotated with temporal concepts provided by TimeML as a starting point. It describes step-by-step how parts of the guideline's model can be generated and finally assessed by means of an evaluation scheme. By means of a scenario-based evaluation we show the applicability of GOALS by translating temporally-related sentences of a clinical protocol into its semi-formal model. Thus, we conclude that this methodology indeed supports the translation process.