Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning.
Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning.
复制标题
DOI：
10.2196/12159
复制
发表时间：
2018-11-26
影响因子：
3.2
通讯作者：
Yu H
中科院分区：
文献类型：
--
作者：
Li F;Liu W;Yu H
药物警戒和药物安全监测对于监测药物不良事件（ADE）至关重要，但美国食品和药物管理局不良事件报告系统等主要ADE报告系统面临漏报等挑战。因此，作为补充监测，通过自然语言处理（NLP）从电子健康记录（EHR）笔记中提取ADE数据。随着NLP的发展，许多最新的机器学习技术被引入该领域，如深度学习和多任务学习（MTL）。然而，只有少数研究集中在采用这种技术来提取ADE。我们的目标是设计一个深度学习模型，用于提取ADE和相关信息，如药物和适应症。由于提取ADE相关信息包括两个步骤-实体识别和关系提取-我们的第二个目标是在两个步骤之间使用多任务学习来改进深度学习模型。我们使用来自药物、适应症和药物不良事件（MADE）1.0挑战的数据集来训练和测试我们的模型。该数据集由1089个癌症患者的EHR笔记组成，包括药物、适应症和ADE等9种实体类型以及这些实体之间的7种关系。为了从数据集中提取信息，我们提出了一种深度学习模型，该模型使用双向长短期记忆（BiLSTM）条件随机场网络来识别实体，并使用BiLSTM-Attention网络来提取关系。为了进一步改进深度学习模型，我们采用了三种典型的MTL方法，即硬参数共享，参数正则化和任务关系学习，分别构建了三种MTL模型，分别称为HardMTL，RegMTL和LearnMTL。由于提取ADE相关信息是一项两步任务，因此第二步（即关系提取）的结果用于比较所有模型。我们使用微平均精度，召回率和F1作为评估指标。我们的深度学习模型取得了最先进的结果（F1=65.9%），显著高于MADE 1.0挑战中最好的系统（F1=61.7%）。HardMTL进一步将F1提高了0.8%，将F1提高到66.7%，而RegMTL和LearnMTL未能提高性能。深度学习模型可以显著提高ADE相关信息提取的性能。MTL对于命名实体识别和关系抽取可能是有效的，但它依赖于方法、数据和其他因素。我们的研究结果可以促进ADE检测，NLP和机器学习的研究。
Pharmacovigilance and drug-safety surveillance are crucial for monitoring adverse drug events (ADEs), but the main ADE-reporting systems such as Food and Drug Administration Adverse Event Reporting System face challenges such as underreporting. Therefore, as complementary surveillance, data on ADEs are extracted from electronic health record (EHR) notes via natural language processing (NLP). As NLP develops, many up-to-date machine-learning techniques are introduced in this field, such as deep learning and multi-task learning (MTL). However, only a few studies have focused on employing such techniques to extract ADEs. We aimed to design a deep learning model for extracting ADEs and related information such as medications and indications. Since extraction of ADE-related information includes two steps—named entity recognition and relation extraction—our second objective was to improve the deep learning model using multi-task learning between the two steps. We employed the dataset from the Medication, Indication and Adverse Drug Events (MADE) 1.0 challenge to train and test our models. This dataset consists of 1089 EHR notes of cancer patients and includes 9 entity types such as Medication, Indication, and ADE and 7 types of relations between these entities. To extract information from the dataset, we proposed a deep-learning model that uses a bidirectional long short-term memory (BiLSTM) conditional random field network to recognize entities and a BiLSTM-Attention network to extract relations. To further improve the deep-learning model, we employed three typical MTL methods, namely, hard parameter sharing, parameter regularization, and task relation learning, to build three MTL models, called HardMTL, RegMTL, and LearnMTL, respectively. Since extraction of ADE-related information is a two-step task, the result of the second step (ie, relation extraction) was used to compare all models. We used microaveraged precision, recall, and F1 as evaluation metrics. Our deep learning model achieved state-of-the-art results (F1=65.9%), which is significantly higher than that (F1=61.7%) of the best system in the MADE1.0 challenge. HardMTL further improved the F1 by 0.8%, boosting the F1 to 66.7%, whereas RegMTL and LearnMTL failed to boost the performance. Deep learning models can significantly improve the performance of ADE-related information extraction. MTL may be effective for named entity recognition and relation extraction, but it depends on the methods, data, and other factors. Our results can facilitate research on ADE detection, NLP, and machine learning.
登录
查看更多内容
影响因子：
2.6
作者：
Haas, Jennifer S.;Iyer, Aarthi;Bates, David W.
通讯作者：
Bates, David W.
通过评估跨核心学习，全路径图核用于蛋白质 - 蛋白质相互作用提取。
影响因子：
3
作者：
Airola, Antti;Pyysalo, Sampo;Bjoerne, Jari;Pahikkala, Tapio;Ginter, Filip;Salakoski, Tapio
通讯作者：
Salakoski, Tapio
影响因子：
3.4
作者：
Fattinger, K;Roos, M;Meier, PJ
通讯作者：
Meier, PJ
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：
4.5
作者：
Dogan, Rezarta Islamaj;Leaman, Robert;Lu, Zhiyong
通讯作者：
Lu, Zhiyong