Architecture of a decision support system to improve clinicians' interpretation of abnormal liver function tests

The objective of this work was to create a self-working computerized clinical decision support system (CDSS) able to analyze liver function tests (LFTs) in order to provide diagnostic suggestions and helpful care support to clinicians. We developed an expert system that processes exclusively para-clinical information to provide diagnostic propositions. Drugs are a major issue in dealing with abnormal LFTs, therefore we created a drug-disease causality assessment tool to include drugs in the differential diagnosis. Along with the results, the CDSS will guide clinicians in the care process offering them case-specific support in the form of guidelines, order sets and references to recent articles. The CDSS will be implemented in Geneva University Hospitals clinical information system (CIS) during year 2011. For the time being, preliminary tests have been conducted on case reports chosen randomly on Pubmed. Considered as medical challenges, case reports were nevertheless processed correctly by the program to the extent that 18 cases out of 20 were diagnosed accurately.