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.