Enhancing evidence-based medicine with natural language argumentative analysis of clinical trials

作者：

Highlights：

• A dataset of clinical trials annotated with argument components and relations.

• An evaluation using ML methods to extract argument structures and classify outcomes.

• A characterisation of argumentative components using the effects on the outcomes.

摘要

•A dataset of clinical trials annotated with argument components and relations.•An evaluation using ML methods to extract argument structures and classify outcomes.•A characterisation of argumentative components using the effects on the outcomes.

论文关键词：Argument mining,Randomized controlled trials,Biomedical natural language processing,Information extraction,Clinical decision support systems,PICO analysis

论文评审过程：Received 23 October 2020, Revised 11 February 2021, Accepted 5 May 2021, Available online 7 May 2021, Version of Record 21 July 2021.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102098