QA-driven guidelines generation for bacteriotherapy

We propose a question-answering (QA) driven generation approach for automatic acquisition of structured rules that can be used in a knowledge authoring tool for antibiotic prescription guidelines management.

The rule generation is seen as a question-answering problem, where the parameters of the questions are known items of the rule (e.g. an infectious disease, caused by a given bacterium) and answers (e.g. some antibiotics) are obtained by a question-answering engine.

When looking for a drug given a pathogen and a disease, top-precision of 0.55 is obtained by the combination of the Boolean engine (PubMed) and the relevance-driven engine (easyIR), which means that for more than half of our evaluation benchmark at least one of the recommended antibiotics was automatically acquired by the rule generation method.

These results suggest that such an automatic text mining approach could provide a useful tool for guidelines management, by improving knowledge update and discovery.