A pipeline for tabular dataset formation from unstructured data provided by ACR Appropriateness Criteria guidelines

Abstract

Among the current data-centric technologies, clinical decision support systems (CDSS) figure out as one of the most promising for healthcare. Despite the technological advances facilitating its implementation, the maintenance of knowledge base for CDSS remains open to improvements. Here, we argue that the Appropriateness Criteria provided by ACR guidelines can be used as an open data-source that, combined with appropriate algorithms, can push forward basic research and technological developments regarding knowledge bases for CDSS. Therefore, we developed a pipeline capable of forming tabular datasets from ACR guidelines, stored in a web site in textual PDF files. We also experimentally demonstrate that the proposed pipeline successfully recovers the interested contents, and the best composition, in terms of its component algorithms, is discussed. Future research focused on algorithms flexibility in the face of PDF template updates could improve our work.