Clinical Information Retrieval using Document and PICO Structure

In evidence-based medicine, clinical questions involve four aspects: Patient/Problem (P), Intervention (I), Comparison (C) and Outcome (O), known as PICO elements. In this paper we present a method that extends the language modeling approach to incorporate both document structure and PICO query formulation. We present an analysis of the distribution of PICO elements in medical abstracts that motivates the use of a location-based weighting strategy. In experiments carried out on a collection of 1.5 million abstracts, the method was found to lead to an improvement of roughly 60% in MAP and 70% in P@10 as compared to state-of-the-art methods.