Clinical Relation Extraction Toward Drug Safety Surveillance Using Electronic Health Record Narratives: Classical Learning Versus Deep Learning.
Clinical Relation Extraction Toward Drug Safety Surveillance Using Electronic Health Record Narratives: Classical Learning Versus Deep Learning.
复制标题
DOI：
10.2196/publichealth.9361
复制
发表时间：
2018-04-25
影响因子：
8.5
通讯作者：
Yu H
中科院分区：
文献类型：
--
作者：
Munkhdalai T;Liu F;Yu H
从电子健康记录（EHR）中提取的药物和药物不良事件（ADE）信息可以成为药物安全监测的丰富资源。现有的观察性研究主要依靠结构化的电子病历数据来获取ADE信息；然而，ADEs通常隐藏在EHR叙述中，而不是记录在结构化数据中。为了从电子病历叙述中解锁ade相关信息，需要提取相关实体并识别它们之间的关系。在本研究中，我们主要关注关系识别。本研究旨在评估药物安全监测背景下使用专家注释医学实体和关系的自然语言处理和机器学习方法，并研究不同学习方法在不同配置下的表现。我们手工注释了791份EHR记录，其中包含9个命名实体（如药物、适应症、严重程度和ade）和7种不同类型的关系（如药物-剂量、药物- ade和严重程度- ade）。然后，我们探索了3种用于关系识别的监督机器学习系统：(1)支持向量机（SVM）系统，(2)端到端深度神经网络系统，以及(3)监督描述性规则归纳基线系统。对于神经网络系统，我们利用了最先进的循环神经网络（RNN）和注意力模型。我们通过关系类型的宏观平均精度、召回率和f1分数来报告性能。我们的研究结果表明，SVM模型在测试数据上的平均f1得分为89.1%，达到了最佳水平，大大优于具有注意力的长短期记忆（LSTM）模型（f1得分为65.72%）和规则诱导基线系统（f1得分为7.47%）。在不同的RNN模型中，带注意的双向LSTM模型的性能最好。通过在LSTM模型中加入额外的特征，其性能可以提高到平均f1分数77.35%。这表明经典学习模型（SVM）在临床关系识别方面仍然优于深度学习模型（RNN变体），特别是在长距离间歇关系识别方面。然而，如果有更多的训练数据可用，rnn显示出显著改进的巨大潜力。我们的工作是挖掘电子病历以提高药物安全监测有效性的重要一步。最重要的是，本研究使用的带注释的数据将向公众开放，这将进一步促进社区的药物安全研究。
Medication and adverse drug event (ADE) information extracted from electronic health record (EHR) notes can be a rich resource for drug safety surveillance. Existing observational studies have mainly relied on structured EHR data to obtain ADE information; however, ADEs are often buried in the EHR narratives and not recorded in structured data. To unlock ADE-related information from EHR narratives, there is a need to extract relevant entities and identify relations among them. In this study, we focus on relation identification. This study aimed to evaluate natural language processing and machine learning approaches using the expert-annotated medical entities and relations in the context of drug safety surveillance, and investigate how different learning approaches perform under different configurations. We have manually annotated 791 EHR notes with 9 named entities (eg, medication, indication, severity, and ADEs) and 7 different types of relations (eg, medication-dosage, medication-ADE, and severity-ADE). Then, we explored 3 supervised machine learning systems for relation identification: (1) a support vector machines (SVM) system, (2) an end-to-end deep neural network system, and (3) a supervised descriptive rule induction baseline system. For the neural network system, we exploited the state-of-the-art recurrent neural network (RNN) and attention models. We report the performance by macro-averaged precision, recall, and F1-score across the relation types. Our results show that the SVM model achieved the best average F1-score of 89.1% on test data, outperforming the long short-term memory (LSTM) model with attention (F1-score of 65.72%) as well as the rule induction baseline system (F1-score of 7.47%) by a large margin. The bidirectional LSTM model with attention achieved the best performance among different RNN models. With the inclusion of additional features in the LSTM model, its performance can be boosted to an average F1-score of 77.35%. It shows that classical learning models (SVM) remains advantageous over deep learning models (RNN variants) for clinical relation identification, especially for long-distance intersentential relations. However, RNNs demonstrate a great potential of significant improvement if more training data become available. Our work is an important step toward mining EHRs to improve the efficacy of drug safety surveillance. Most importantly, the annotated data used in this study will be made publicly available, which will further promote drug safety research in the community.
登录
查看更多内容
影响因子：
2.6
作者：
Brown, Jeffrey S.;Kulldorff, Martin;Platt, Richard
通讯作者：
Platt, Richard
影响因子：
4.2
作者：
Butt, Tehreem F.;Cox, Anthony R.;Ferner, Robin E.
通讯作者：
Ferner, Robin E.
DOI：
10.1111/j.1365-2125.1994.tb04373.x
发表时间：
1994-11-01
影响因子：
3.4
作者：
BEGAUD, B;MORIDE, Y;HARAMBURU, F
通讯作者：
HARAMBURU, F
影响因子：
--
作者：
BENGIO, Y;SIMARD, P;FRASCONI, P
通讯作者：
FRASCONI, P
影响因子：
9.8
作者：
Banda JM;Evans L;Vanguri RS;Tatonetti NP;Ryan PB;Shah NH
通讯作者：
Shah NH