https://scholars.lib.ntu.edu.tw/handle/123456789/520456
標題: | Adverse drug event and medication extraction in electronic health records via a cascading architecture with different sequence labeling models and word embeddings | 作者: | Dai H.-J. Su C.-H. CHI-SHIN WU |
關鍵字: | adverse drug event; electronic health record; information extraction; named entity recognition; word embedding | 公開日期: | 2020 | 卷: | 27 | 期: | 1 | 起(迄)頁: | 47-55 | 來源出版物: | Journal of the American Medical Informatics Association | 摘要: | Objective: An adverse drug event (ADE) refers to an injury resulting from medical intervention related to a drug including harm caused by drugs or from the usage of drugs. Extracting ADEs from clinical records can help physicians associate adverse events to targeted drugs. Materials and Methods: We proposed a cascading architecture to recognize medical concepts including ADEs, drug names, and entities related to drugs. The architecture includes a preprocessing method and an ensemble of conditional random fields (CRFs) and neural network-based models to respectively address the challenges of surrogate string and overlapping annotation boundaries observed in the employed ADEs and medication extraction (ADME) corpus. The effectiveness of applying different pretrained and postprocessed word embeddings for the ADME task was also studied. Results: The empirical results showed that both CRFs and neural network-based models provide promising solution for the ADME task. The neural network-based models particularly outperformed CRFs in concept types involving narrative descriptions. Our best run achieved an overall micro F-score of 0.919 on the employed corpus. Our results also suggested that the Global Vectors for word representation embedding in general domain provides a very strong baseline, which can be further improved by applying the principal component analysis to generate more isotropic vectors. Conclusions: We have demonstrated that the proposed cascading architecture can handle the problem of overlapped annotations and further improve the overall recall and F-scores because the architecture enables the developed models to exploit more context information and forms an ensemble for creating a stronger recognizer. ? 2019 The Author(s) 2019. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076585983&doi=10.1093%2fjamia%2focz120&partnerID=40&md5=e2b01c30adffb54d0bc36d2d98457d75 https://scholars.lib.ntu.edu.tw/handle/123456789/520456 |
ISSN: | 1067-5027 | DOI: | 10.1093/jamia/ocz120 | SDG/關鍵字: | adverse drug event and medication extraction; adverse drug reaction; Article; clinical effectiveness; clinical evaluation; convolutional neural network; drug isolation; drug labeling; electronic health record; embedding; feature extraction; language processing; principal component analysis; algorithm; human; information retrieval; natural language processing; nomenclature; procedures; verbal communication; conditional random field; data extraction; long short term memory network; machine learning; Algorithms; Drug-Related Side Effects and Adverse Reactions; Electronic Health Records; Humans; Information Storage and Retrieval; Narration; Natural Language Processing; Neural Networks, Computer; Terminology as Topic |
顯示於: | 流行病學與預防醫學研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。