Department of Computer Science, University College London, Gower Street, London, WC1E 6BT, UK.
Artif Intell Med. 2023 Oct;144:102661. doi: 10.1016/j.artmed.2023.102661. Epub 2023 Sep 7.
Evidence-based medicine, the practice in which healthcare professionals refer to the best available evidence when making decisions, forms the foundation of modern healthcare. However, it relies on labour-intensive systematic reviews, where domain specialists must aggregate and extract information from thousands of publications, primarily of randomised controlled trial (RCT) results, into evidence tables. This paper investigates automating evidence table generation by decomposing the problem across two language processing tasks: named entity recognition, which identifies key entities within text, such as drug names, and relation extraction, which maps their relationships for separating them into ordered tuples. We focus on the automatic tabulation of sentences from published RCT abstracts that report the results of the study outcomes. Two deep neural net models were developed as part of a joint extraction pipeline, using the principles of transfer learning and transformer-based language representations. To train and test these models, a new gold-standard corpus was developed, comprising over 550 result sentences from six disease areas. This approach demonstrated significant advantages, with our system performing well across multiple natural language processing tasks and disease areas, as well as in generalising to disease domains unseen during training. Furthermore, we show these results were achievable through training our models on as few as 170 example sentences. The final system is a proof of concept that the generation of evidence tables can be semi-automated, representing a step towards fully automating systematic reviews.
循证医学是一种医疗实践，医生在做决策时会参考最佳现有证据。它是现代医疗保健的基础。然而，它依赖于劳动密集型的系统评价，领域专家必须从成千上万的出版物中（主要是随机对照试验 RCT 的结果）汇总和提取信息到证据表中。本文通过将问题分解为两个语言处理任务来研究自动生成证据表的问题：命名实体识别，它识别文本中的关键实体，如药物名称；关系提取，它将它们的关系映射出来，将它们分离成有序元组。我们专注于从报告研究结果的已发表 RCT 摘要中自动编制句子。两个深度神经网络模型是作为联合提取管道的一部分开发的，使用了迁移学习和基于转换器的语言表示的原理。为了训练和测试这些模型，开发了一个新的黄金标准语料库，其中包含来自六个疾病领域的 550 多个结果句子。这种方法表现出了显著的优势，我们的系统在多个自然语言处理任务和疾病领域表现良好，并且可以泛化到训练中未见过的疾病领域。此外，我们证明通过在 170 个示例句子上训练我们的模型就可以实现这些结果。最终系统是一个概念验证，表明证据表的生成可以半自动完成，这是朝着完全自动化系统评价迈出的一步。
