Proximity-aware Clinical Passage Retrieval Framework by Exploiting Knowledge Structure

Clinicians have minimal time to search for and absorb the information needed while performing duties of their medical practice. Their time-pressured situations requires relevant in be retrieved presented a more succinct form, such as short passage, rather than whole page or document. In this context, clinical decision support (CDS) searches are beneficial when used retrieve critical passages that can assist practice experts by offering appropriate case at hand. We present novel CDS framework designed passage retrieval order decision-making using laboratory test results incorporating proximity information. To do so, we use knowledge structure graphically visualizes key concepts corresponding relationships specific domain where nodes denote with associative relationships. Furthermore, unlike previous studies exploit structures during re-ranking step, only dealing initially highly passages, utilize purpose query expansion. By doing our approach unveil not initial process including latent terms list. compared two models with/without edge pruning capture relationship between terms. Our experiment showed embedded-based outperformed building approaches other proximity-aware state-of-the-art models.