Leveraging a common representation for personalized search and summarization in a medical digital library

Abstract

Despite the large amount of online medical literature, it can be difficult for clinicians to find relevant information at the point of patient care. We present techniques to personalize the results of search, making use of the online patient record as a sophisticated, preexisting user model. Our work in PERSIVAL, a medical digital library, includes methods for reranking the results of search to prioritize those that better match the patient record. It also generates summaries of the reranked results, which highlight information that is relevant to the patient under the physician's care. We focus on the use of a common representation for the articles returned by search and the patient record, which facilitates both the reranking and the summarization tasks. This common approach to both tasks has a strong positive effect on the ability to personalize information.