Evaluation of Strategies for Generalised Cases within a Case-Based Reasoning Antibiotics Therapy Advice System

Abstract

For an intensive care unit, we have developed an antibiotics therapy advice system, called ICONS. To speed-up the process of finding suitable therapy recommendations we have applied Case-based Reasoning techniques. As in a medical expert system all required information should always be up-to-date, a static case base is inappropriate. New cases should be incrementally incorporated into the case base and outdated ones should be updated or erased. For reasons of space limitations and of retrieval time an indefinite growth of the case base should be avoided. To fulfil these requirements we propose to generalise from single cases to prototypical cases and to erase redundant cases. In this paper, we mainly focus on results of extended experiments with generation strategies of generalised cases (prototypes). Additionally, we compare measured retrieval times for two indexing retrieval algorithms: For simple indexing and Tree-Hash retrieval.