Access to clinical evidence is a critical component of the practice of evidence-based medicine. Advanced retrieval systems can supplement precompiled secondary sources to assist physicians in making sound clinical decisions. This study explores one particular issue related to the design of such retrieval systems: the effective organization of search results to facilitate rapid understanding and synthesis of potentially relevant information. We hypothesize that grouping retrieved MEDLINE citations into semantically-coherent clusters, based on automatically-extracted interventions from the abstract text, represents an effective strategy for presenting results, compared to a traditional ranked list. Experiments with our implemented system appear to support this claim.