Abstract
Following the Evidence Based Medicine (EBM) practice, practitioners make use of the existing evidence to make therapeutic decisions. This evidence, in the form of scientific statements, is usually found in scholarly publications such as randomised control trials and systematic reviews. However, finding such information in the overwhelming amount of published material is particularly challenging. Approaches have been proposed to automatically extract scientific artefacts in EBM using standardised schemas. Our work takes this stream a step forward and looks into consolidating extracted artefacts—i.e., quantifying their degree of similarity based on the assumption that they carry the same rhetorical role. By semantically connecting key statements in the literature of EBM, practitioners are not only able to find available evidence more easily, but also can track the effects of different treatments/outcomes in a number of related studies. We devise a regression model based on a varied set of features and evaluate it both on a general English corpus (the SICK corpus), as well as on an EBM corpus (the NICTA-PIBOSO corpus). Experimental results show that our approach performs on par with the state of the art on the general English and achieves encouraging results on the biomedical text when compared against human judgement.
Highlights
Evidence Based Medicine (EBM) is a prescribing scenario that employs available medical research outcomes in the treatment process
We proposed a supervised approach for quantifying semantic similarity of full sentences
We described a series of measures that model the similarity of a pair of sentences from diverse perspectives, including syntactic, structural, and semantic
Summary
Evidence Based Medicine (EBM) is a prescribing scenario that employs available medical research outcomes in the treatment process. Selecting the most relevant publications, among often thousands from the search results, is a time consuming task for experts. The key statements externalized by the resulting set (e.g. Outcome or Intervention) need to be collated in order to provide a comprehensive, succinct and balanced overview of the domain. Number of pairs of sentences roles, we adapted the guidelines to include detailed examples on different types of pairs of scientific artefacts and the effective factors in identifying and assessing their similarity, e.g., the quantitative elements in Population pairs, the dimension of the study in Study Design pairs, etc. Class-based sub-corpora of pairs Intervention Outcome Population
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have