[论文解读] Extraction of evidence tables from abstracts of randomized clinical trials using a maximum entropy classifier and global constraints

Antonio Trenta, Anthony Hunter+1 more|arXiv (Cornell University)|Sep 17, 2015

Advanced Text Analysis Techniques参考文献 18被引用 14

一句话总结

本文提出了一种机器学习系统，通过结合最大熵分类器与整数线性规划（ILP），从随机对照试验（RCT）摘要中提取结构化的证据表数据，以强制执行全局约束。该方法通过建模PICO元素（人群、干预、对照、结局）之间的依赖关系，提高了准确性和一致性，在基于证据的医学自动化证据表编制中显著优于基线方法。

ABSTRACT

Systematic use of the published results of randomized clinical trials is increasingly important in evidence-based medicine. In order to collate and analyze the results from potentially numerous trials, evidence tables are used to represent trials concerning a set of interventions of interest. An evidence table has columns for the patient group, for each of the interventions being compared, for the criterion for the comparison (e.g. proportion who survived after 5 years from treatment), and for each of the results. Currently, it is a labour-intensive activity to read each published paper and extract the information for each field in an evidence table. There have been some NLP studies investigating how some of the features from papers can be extracted, or at least the relevant sentences identified. However, there is a lack of an NLP system for the systematic extraction of each item of information required for an evidence table. We address this need by a combination of a maximum entropy classifier, and integer linear programming. We use the later to handle constraints on what is an acceptable classification of the features to be extracted. With experimental results, we demonstrate substantial advantages in using global constraints (such as the features describing the patient group, and the interventions, must occur before the features describing the results of the comparison).

研究动机与目标

• 为解决在基于证据的医学中手动从RCT摘要填充证据表的劳动密集型挑战。
• 开发一种自动化、可扩展的方法，从临床试验摘要中提取结构化信息（PICO元素）。
• 通过使用全局约束建模信息项之间的依赖关系，提高提取准确性。
• 通过实现机器对临床证据的读取，减少对专家标注的依赖。
• 为系统综述员和决策者提供可计算、标准化的证据摘要。

提出的方法

• 训练最大熵分类器以识别RCT摘要中与PICO相关的短语的句法核心词。
• 系统使用依存句法分析在识别出句法核心词后提取完整短语。
• 将全局约束（如文本中PICO元素的顺序）编码为整数线性规划（ILP）约束。
• ILP阶段通过确保患者群体和干预描述在结果之前出现，来强制实现逻辑一致性。
• 约束基于随机对照试验报告惯例（如CONSORT指南）手工构建。
• 最终输出为填充了提取的PICO元素的结构化证据表。

实验结果

研究问题

• RQ1 统计NLP方法能否以高精确率和高召回率有效从RCT摘要中提取PICO元素？
• RQ2 对PICO元素相对顺序的全局约束在多大程度上提升了提取性能？
• RQ3 信息项之间的依赖关系在多大程度上增强了自动化提取的鲁棒性和一致性？
• RQ4 领域特定模型在不重构核心架构的情况下，能否适应其他医学领域？
• RQ5 将ILP与最大熵分类结合的方法与基于规则或独立的统计方法相比，表现如何？

主要发现

• 通过整数线性规划集成全局约束，显著提高了信息提取的一致性和可靠性。
• 与不建模项间依赖关系的基线模型相比，该系统实现了显著的性能提升。
• 使用最大熵分类使系统能够从标注训练数据中稳健地学习特征。
• 该方法在从RCT摘要自动化生成证据表方面具有可行性，显著减少了人工工作量。
• 该系统的架构具有跨领域可扩展性，因为模型结构不依赖于领域特定特征。
• 结果表明，建模结构和语言约束可同时提升临床文本挖掘中NLP系统的准确性和可解释性。