Objective Large databases of published medical research can support clinical decision making by providing physicians with the best available evidence. The time required to obtain optimal results from these databases using traditional systems often makes accessing the databases impractical for clinicians. This paper explores whether a hybrid approach of augmenting traditional information retrieval with knowledge-based methods facilitates finding practical clinical advice in the research literature.

Design Three experimental systems were evaluated for their ability to find MEDLINE^TM citations providing answers to clinical questions of different complexity. The systems (SemRep, Essie, and CQA-1.0), which rely on domain knowledge and semantic processing to a varying extent, were evaluated separately and in combination. Fifteen therapy and prevention questions in three categories (general questions, intermediate, and specific) were searched. The first ten citations retrieved by each system were randomized, anonymized, and evaluated on a three-point scale. The reasons for ratings were documented.

Measurements Metrics evaluating the overall performance of a system (Mean Average Precision - MAP, Binary Preference - Bpref) and metrics evaluating the number of relevant documents in the first several presented to a physician were used.

Results Scores (MAP=0.57, Bpref=0.71) for fusion of the retrieval results of the three systems are significantly (p < 0.01) better than those for any individual system. All three systems present three to four relevant citations in the first five for any question type.

Conclusion The improvements in finding relevant MEDLINE citations due to knowledge-based processing show promise in assisting physicians answer questions in clinical practice.