Exploiting LLMs for Supporting Conformance Checking on Medical Processes

Clinical guidelines, which serve as the normative process models in medicine, are generally presented in an unstructured, textual format. This poses a challenge for applying traditional conformance checking algorithms, as they require a formalized, machine-readable description of the process. In this paper, we propose a solution to this issue by utilizing a Large Language Model (LLM) to extract normative rules from textual guidelines. These extracted rules can then be used to check the conformance of patient event logs. We present some first results, obtained on a real world stroke management dataset.