BiRD: A Strategy to Autonomously Supplement Clinical Practice Guidelines with Related Clinical Studies

摘要

In this paper we introduce a framework to supplement and tag computerized CPG with related best-evidence automatically sourced from on-line medical literature repositories. The idea is to provide CPG users with additional published evidence pertaining to the different sections of a CPG of their interest. We present a web-enabled Best-evidence Retrieval and Delivery (BiRD) system that autonomously retrieves pertinent medical literature with respect to user-specified content from a GEM-encoded CPG. This is achieved via a multi-level literature search strategy that uses the actual CPG content to autonomously generate a search query. The featured search strategy firstly categorizes the search query towards a priori defined clinical query subjects and secondly filters out insignificant medical terms from the search query. The technical architecture comprises existing medical language processing tools and vocabularies, together with newly developed tools to automatically (a) generate optimum search queries; (b) retrieve medical articles from MEDLINE; and (c) embed the retrieved medical articles within XML-based CPG encoded according to the GEM formalism.