DSpace Repository

Identification of Adverse Drug Event–Related Japanese Articles: Natural Language Processing Analysis

Show simple item record

dc.contributor.author Ujiie, Shogo
dc.contributor.author Yada, Shuntaro
dc.contributor.author Wakamiya, Shoko
dc.contributor.author Aramaki, Eiji
dc.date.accessioned 2020-12-25T01:06:57Z
dc.date.available 2020-12-25T01:06:57Z
dc.date.issued 2020-11-27
dc.identifier.uri http://hdl.handle.net/10061/14172
dc.description.abstract Background: Medical articles covering adverse drug events (ADEs) are systematically reported by pharmaceutical companies for drug safety information purposes. Although policies governing reporting to regulatory bodies vary among countries and regions, all medical article reporting may be categorized as precision or recall based. Recall-based reporting, which is implemented in Japan, requires the reporting of any possible ADE. Therefore, recall-based reporting can introduce numerous false negatives or substantial amounts of noise, a problem that is difficult to address using limited manual labor. Objective: Our aim was to develop an automated system that could identify ADE-related medical articles, support recall-based reporting, and alleviate manual labor in Japanese pharmaceutical companies. Methods: Using medical articles as input, our system based on natural language processing applies document-level classification to extract articles containing ADEs (replacing manual labor in the first screening) and sentence-level classification to extract sentences within those articles that imply ADEs (thus supporting experts in the second screening). We used 509 Japanese medical articles annotated by a medical engineer to evaluate the performance of the proposed system. Results: Document-level classification yielded an F1 of 0.903. Sentence-level classification yielded an F1 of 0.413. These were averages of fivefold cross-validations. Conclusions: A simple automated system may alleviate the manual labor involved in screening drug safety–related medical articles in pharmaceutical companies. After improving the accuracy of the sentence-level classification by considering a wider context, we intend to apply this system toward real-world postmarketing surveillance. ja_JP
dc.language.iso en ja_JP
dc.publisher JMIR Publicatoins ja_JP
dc.relation.isreplacedby https://medinform.jmir.org/2020/11/e22661 ja_JP
dc.rights ©Shogo Ujiie, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 27.11.2020. This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on http://medinform.jmir.org/, as well as this copyright and license information must be included. ja_JP
dc.subject adverse drug events ja_JP
dc.subject medical informatics ja_JP
dc.subject natural language processing ja_JP
dc.subject pharmacovigilance ja_JP
dc.title Identification of Adverse Drug Event–Related Japanese Articles: Natural Language Processing Analysis ja_JP
dc.type.nii Journal Article ja_JP
dc.contributor.transcription ウジイエ, ショウゴ
dc.contributor.transcription ヤダ, シュンタロウ
dc.contributor.transcription ワカミヤ, ショウコ
dc.contributor.transcription アラマキ, エイジ
dc.contributor.alternative 氏家, 翔吾
dc.contributor.alternative 矢田, 竣太郎
dc.contributor.alternative 若宮, 翔子
dc.contributor.alternative 荒牧, 英治
dc.textversion none ja_JP
dc.identifier.eissn 2291-9694
dc.identifier.jtitle JMIR Medical Informatics ja_JP
dc.identifier.volume 8 ja_JP
dc.identifier.issue 11 ja_JP
dc.relation.doi 10.2196/22661 ja_JP
dc.identifier.NAIST-ID 74655911 ja_JP
dc.identifier.NAIST-ID 74655929 ja_JP
dc.identifier.NAIST-ID 74652314 ja_JP
dc.identifier.NAIST-ID 74652181 ja_JP


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account