Extracting clinical cases from XML-based electronic patient records for use in web-based medical case based reasoning systems.

Development and usage of Case Based Reasoning (CBR) driven medical diagnostic system requires a large volume of clinical cases that depict the problem-solving methodology of medical experts. Successful usage of CBR based systems in healthcare is constrained by the need for a continuous supply of current and correct clinical cases (in an electronic medium) from medical experts. To address this constraint we present a strategy to pro-actively transform generic Electronic Patient Records (EPR) to Operable CBR-oriented Cases (OCC) that are compliant to specialised CBR-based medical systems. EPR-OCC transformation methodology is based on XML parse-trees, Unified Medical Language Source (UMLS) meta-thesauri and medical knowledge ontologies. The featured work involves the implementation of a Java-based computer system for the automatic transformation of XML-based EPR-originating from heterogeneous EPR repositories accessible over the Internet/WWW-to specialised OCC that can then be seamlessly incorporated within Intelligent CBR-based Medical Diagnostic Systems.