Feature engineering combined with machine learning and rule-based methods for structured information extraction from narrative clinical discharge summaries
Feature engineering combined with machine learning and rule-based methods for structured information extraction from narrative clinical discharge summaries
复制标题
特征工程与机器学习和基于规则的方法相结合，用于从叙述性临床出院摘要中提取结构化信息
DOI：
10.1136/amiajnl-2011-000776
复制
发表时间：
2012-09-01
影响因子：
6.4
通讯作者：
Chang, Eric I-Chao
中科院分区：
文献类型：
--
作者：
Xu, Yan;Hong, Kai;Chang, Eric I-Chao
目的建立一种将医学领域的叙事文本转化为结构化表征的系统。该系统执行三个子任务：概念提取、断言分类和关系识别。整个系统包括五个步骤：(1)预处理句子；(2)标记名词短语（NPs）和形容词短语（APs）；(3)使用剂量单位字典提取概念，基于条件随机场（CRF）动态切换两个模型；(4)基于五个分类器的投票对断言进行分类；(5)使用一组有效的判别特征使用规范化句子识别关系。采用宏观平均精密度、微观平均精密度、召回率和f值对结果进行评价。结果该系统在概念提取、断言分类和关系识别方面的微平均f值分别为0.8489、0.9392和0.7326。该系统利用了一系列共同的特点，达到了最先进的性能。谨慎的特征工程为我们的系统奠定了基础。在概念提取中，我们证明了切换模型，其中一个是专门为电报句子设计的，显著提高了处理概念的提取。在断言分类中，从基于规则的分类器派生的一组特征被证明对条件类和可能类是有效的。在传统的机器学习方法中，这些类会受到数据缺乏的困扰。在关系识别中，我们使用两阶段体系结构，其中第二阶段将成对分类器应用于可能的候选类。这种体系结构显著提高了性能。
Objective A system that translates narrative text in the medical domain into structured representation is in great demand. The system performs three sub-tasks: concept extraction, assertion classification, and relation identification.Design The overall system consists of five steps: (1) pre-processing sentences, (2) marking noun phrases (NPs) and adjective phrases (APs), (3) extracting concepts that use a dosage-unit dictionary to dynamically switch two models based on Conditional Random Fields (CRF), (4) classifying assertions based on voting of five classifiers, and (5) identifying relations using normalized sentences with a set of effective discriminating features.Measurements Macro-averaged and micro-averaged precision, recall and F-measure were used to evaluate results.Results The performance is competitive with the state-of-the-art systems with micro-averaged F-measure of 0.8489 for concept extraction, 0.9392 for assertion classification and 0.7326 for relation identification.Conclusions The system exploits an array of common features and achieves state-of-the-art performance. Prudent feature engineering sets the foundation of our systems. In concept extraction, we demonstrated that switching models, one of which is especially designed for telegraphic sentences, improved extraction of the treatment concept significantly. In assertion classification, a set of features derived from a rule-based classifier were proven to be effective for the classes such as conditional and possible. These classes would suffer from data scarcity in conventional machine-learning methods. In relation identification, we use two-staged architecture, the second of which applies pairwise classifiers to possible candidate classes. This architecture significantly improves performance.