EviX – Facilitating Evidence-based Decision Support Using Information Extraction and Clinical Guidelines


This project has been supported by "Fonds zur Förderung der wissenschaftlichen Forschung FWF" (Austrian Science Fund), grant L290-N04.


The goal of the proposed project is the experimental application and further development of promising approaches in the area of semi-automatic creation of computer-interpretable clinical guidelines and the execution of evidence-based recommendations. We expect contributions to ease the creation of computer-interpretable guidelines and support of the medical staff in their daily routine and decision-making.

Computer-interpretable guidelines ought to support the medical staff in treatment planning and execution and promulgate the most effective and efficient care. Due to the complexity of most of the guideline representation languages the transformation into these languages is a very complex and cumbersome task. In the same way, embedding of evidence-based treatment recommendations is important, but such concepts are inadequately incorporated in currently existing representation languages. Consequently, these aspects are not considered during the execution and decision-making process.

In previous projects we developed a set of methods and programs for creating and executing treatment plans as well as to visualize them. In the proposed project we will use these methods to point out, improve, and augment methods to solve the problems mentioned above. Within this interdisciplinary project we build upon extensive existing contacts to developers of clinical guidelines as well as to developers of computer-interpretable guideline representation languages (e.g., PROforma).

Both the medical discipline and the computer science discipline will be enriched by this project. On the one hand, the developed methods and applications will influence the development of guidelines and probably will contribute to the development of repositories for computer-interpretable guideline representation languages as well as to better support the decision making process in treatment planning. On the other hand, methods of Information Extraction and Integration are extended and evaluated.