PROCEEDINGS ANNUAL MEETING 2009

Purpose: Our objective is to propose a question-answering-driven generation approach for automatic acquisition of structured rules that can be used in decision support sys-tems for antibiotic prescription. Methods: We apply a question-answering engine to an-swer specific information requests. The rule generation is seen as an equation problem, where the factors are known items of the rule (e.g. an infectious disease, caused by a given bacterium) and solutions are answered by the engine (e.g. some antibiotics). Results: A top precision of 0.64 is reported, which means, for about two thirds of the benchmark knowledge rules, that one of the recommended antibiotics was automati-cally acquired by the rule generation method. Conclusion: These results suggest that a significant frac-tion of medical knowledge can be obtained by an auto-matic text mining approach of this kind