English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Evidence-based medicine, the practice in which healthcare professionals referto the best available evidence when making decisions, forms the foundation ofmodern healthcare. However, it relies on labour-intensive systematic reviews,where domain specialists must aggregate and extract information from thousandsof publications, primarily of randomised controlled trial (RCT) results, intoevidence tables. This paper investigates automating evidence table generationby decomposing the problem across two language processing tasks: \textit{namedentity recognition}, which identifies key entities within text, such as drugnames, and \textit{relation extraction}, which maps their relationships forseparating them into ordered tuples. We focus on the automatic tabulation ofsentences from published RCT abstracts that report the results of the studyoutcomes. Two deep neural net models were developed as part of a jointextraction pipeline, using the principles of transfer learning andtransformer-based language representations. To train and test these models, anew gold-standard corpus was developed, comprising almost 600 result sentencesfrom six disease areas. This approach demonstrated significant advantages, withour system performing well across multiple natural language processing tasksand disease areas, as well as in generalising to disease domains unseen duringtraining. Furthermore, we show these results were achievable through trainingour models on as few as 200 example sentences. The final system is a proof ofconcept that the generation of evidence tables can be semi-automated,representing a step towards fully automating systematic reviews.

Automated tabulation of clinical trial results: A joint entity and relation extraction approach with transformer-based language representations