Combining rules and machine learning for extraction of temporal expressions and events from clinical narratives
Combining rules and machine learning for extraction of temporal expressions and events from clinical narratives
复制标题
DOI：
10.1136/amiajnl-2013-001625
复制
发表时间：
2013-09-01
影响因子：
6.4
通讯作者：
Nenadic, Goran
中科院分区：
文献类型：
--
作者：
Kovacevic, Aleksandar;Dehghan, Azad;Nenadic, Goran
临床事件（例如，问题，测试，治疗）和相关的时间表达（例如，日期和时间）的识别是从电子健康记录中提取和管理数据的关键任务。作为i2 b2 2012临床数据自然语言处理挑战赛的一部分，我们开发并评估了一个从临床叙述中自动提取时间表达和事件的系统。所提取的时间表达式另外规范化分配类型，值，和modifier.Materials和methodsThe系统结合了基于规则和机器学习的方法，依赖于形态，词汇，句法，语义和特定领域的功能。基于规则的组件被设计来处理识别和规范化的时间表达式，而条件随机场模型进行训练的事件和时间recognization.ResultsThe系统实现了微F分数为90%的时间表达式的提取和87%的临床事件提取。时态表达式的规范化组件实现了84.73%（表达式类型），70.44%（值）和82.75%（修饰符）的准确率。讨论与人类注释者之间的初始一致率（87-89%）相比，该系统为事件和时态表达式挖掘提供了相当的性能。虽然（宽松）识别这样的提及是可以实现的，找到确切的边界证明challenging.ConclusionsThe系统提供了一个国家的最先进的方法，可用于支持自动识别的临床事件和时间表达的叙述中提到的支持手动审查过程或作为一个大规模的电子健康数据库处理的一部分。
ObjectiveIdentification of clinical events (eg, problems, tests, treatments) and associated temporal expressions (eg, dates and times) are key tasks in extracting and managing data from electronic health records. As part of the i2b2 2012 Natural Language Processing for Clinical Data challenge, we developed and evaluated a system to automatically extract temporal expressions and events from clinical narratives. The extracted temporal expressions were additionally normalized by assigning type, value, and modifier.Materials and methodsThe system combines rule-based and machine learning approaches that rely on morphological, lexical, syntactic, semantic, and domain-specific features. Rule-based components were designed to handle the recognition and normalization of temporal expressions, while conditional random fields models were trained for event and temporal recognition.ResultsThe system achieved micro F scores of 90% for the extraction of temporal expressions and 87% for clinical event extraction. The normalization component for temporal expressions achieved accuracies of 84.73% (expression's type), 70.44% (value), and 82.75% (modifier).DiscussionCompared to the initial agreement between human annotators (87-89%), the system provided comparable performance for both event and temporal expression mining. While (lenient) identification of such mentions is achievable, finding the exact boundaries proved challenging.ConclusionsThe system provides a state-of-the-art method that can be used to support automated identification of mentions of clinical events and temporal expressions in narratives either to support the manual review process or as a part of a large-scale processing of electronic health databases.