LASSIE – modeLing treAtment proceSSes using Information Extraction

Modeling clinical guidelines and protocols in a computer-interpretable format is a challenging, but burdensome and time-consuming task. Existing methods and tools to support this task demand detailed medical knowledge, knowledge about the formal representations, and a manual modeling. Furthermore, formalized guideline documents mostly fall far short in terms of readability and understandability for the human domain modeler.

In this project we propose a methodology to support the human modeler by both automating parts of the modeling process and making the modeling process traceable and comprehensible.

Our methodology called LASSIE, represents a novel step-wise procedure that uses Information Extraction to semi-automatically model treatment processes (see Figure 1). We have developed several heuristics without the need to apply Natural Language Understanding. Finally, we integrated our heuristics in a form of a framework and applied them to several guidelines from the medical subject of otolaryngology. The framework has been applied to formalize the guidelines in the formal Asbru plan representation.

Figure 1: LASSIE methodology. Steps to semi-automatically transform clinical practice guidelines to a (semi-)formal representation (e.g., Asbru).

Findings of our evaluation indicate that using semi-automatic, step-wise Information Extraction methods are a valuable instrument to formalize clinical guidelines and protocols.



Publications: K. Kaiser, C. Akkaya, S. Miksch: How can Information Extraction ease formalizing treatment processes in clinical practice guidelines? A method and its evaluation,Artificial Intelligence in medicine, 2007.
  K. Kaiser, S. Miksch: Modeling Treatment Processes Using Information Extraction, In Lakhmi Jain (ed.) Computational Intelligence in Healthcare, Springer Verlag, 2006.
  K. Kaiser: LASSIE - Modeling Treatment Processes Using Information Extraction, PhD thesis, Institute of Software Technology & Interactive Systems, Vienna University of Technology, Nov. 2005.
  K. Kaiser, C. Akkaya, S. Miksch: Gaining Process Information from Clinical Practice Guidelines Using Information Extraction. In Proc. of the 10th Conference on Artificial Intelligende in Medicine (AIME 2005), Aberdeen, UK, 2005. 
  K. Kaiser: Semi-automatic Transformation of Structured Guideline Components into Formal Process Representations. In: 1st Doctoral Consortium at the Conference on Artificial Intelligence in Medicine (AIME 2005), Aberdeen, UK, 2005. 
  K. Kaiser: Knowledge-based Methods for Facilitating the Creation of Asbru Protocols. In J. Evermann, E. Söderström, J. Kotlarsky (eds.) Proc. of the 10th Doctoral Consortium on Advanced Information Systems Engineering (at CAiSE*03), University of Skövde, Sweden, pages 101 - 111, June 2003. 



This project has been supported by "Fonds zur Förderung der wissenschaftlichen Forschung FWF" (Austrian Science Fund), grant P15467-INF.