检索增强科学索赔验证。

IF 2.5 Q2 HEALTH CARE SCIENCES & SERVICES
JAMIA Open Pub Date : 2024-02-21 eCollection Date: 2024-04-01 DOI:10.1093/jamiaopen/ooae021
Hao Liu, Ali Soroush, Jordan G Nestor, Elizabeth Park, Betina Idnay, Yilu Fang, Jane Pan, Stan Liao, Marguerite Bernard, Yifan Peng, Chunhua Weng
{"title":"检索增强科学索赔验证。","authors":"Hao Liu, Ali Soroush, Jordan G Nestor, Elizabeth Park, Betina Idnay, Yilu Fang, Jane Pan, Stan Liao, Marguerite Bernard, Yifan Peng, Chunhua Weng","doi":"10.1093/jamiaopen/ooae021","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>To automate scientific claim verification using PubMed abstracts.</p><p><strong>Materials and methods: </strong>We developed CliVER, an end-to-end scientific <b>Cl</b>a<b>i</b>m <b>VER</b>ification system that leverages retrieval-augmented techniques to automatically retrieve relevant clinical trial abstracts, extract pertinent sentences, and use the PICO framework to support or refute a scientific claim. We also created an ensemble of three state-of-the-art deep learning models to classify rationale of support, refute, and neutral. We then constructed CoVERt, a new <b>CO</b>VID <b>VER</b>ifica<b>t</b>ion dataset comprising 15 PICO-encoded drug claims accompanied by 96 manually selected and labeled clinical trial abstracts that either support or refute each claim. We used CoVERt and SciFact (a public scientific claim verification dataset) to assess CliVER's performance in predicting labels. Finally, we compared CliVER to clinicians in the verification of 19 claims from 6 disease domains, using 189 648 PubMed abstracts extracted from January 2010 to October 2021.</p><p><strong>Results: </strong>In the evaluation of label prediction accuracy on CoVERt, CliVER achieved a notable F1 score of 0.92, highlighting the efficacy of the retrieval-augmented models. The ensemble model outperforms each individual state-of-the-art model by an absolute increase from 3% to 11% in the F1 score. Moreover, when compared with four clinicians, CliVER achieved a precision of 79.0% for abstract retrieval, 67.4% for sentence selection, and 63.2% for label prediction, respectively.</p><p><strong>Conclusion: </strong>CliVER demonstrates its early potential to automate scientific claim verification using retrieval-augmented strategies to harness the wealth of clinical trial abstracts in PubMed. Future studies are warranted to further test its clinical utility.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10919922/pdf/","citationCount":"0","resultStr":"{\"title\":\"Retrieval augmented scientific claim verification.\",\"authors\":\"Hao Liu, Ali Soroush, Jordan G Nestor, Elizabeth Park, Betina Idnay, Yilu Fang, Jane Pan, Stan Liao, Marguerite Bernard, Yifan Peng, Chunhua Weng\",\"doi\":\"10.1093/jamiaopen/ooae021\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>To automate scientific claim verification using PubMed abstracts.</p><p><strong>Materials and methods: </strong>We developed CliVER, an end-to-end scientific <b>Cl</b>a<b>i</b>m <b>VER</b>ification system that leverages retrieval-augmented techniques to automatically retrieve relevant clinical trial abstracts, extract pertinent sentences, and use the PICO framework to support or refute a scientific claim. We also created an ensemble of three state-of-the-art deep learning models to classify rationale of support, refute, and neutral. We then constructed CoVERt, a new <b>CO</b>VID <b>VER</b>ifica<b>t</b>ion dataset comprising 15 PICO-encoded drug claims accompanied by 96 manually selected and labeled clinical trial abstracts that either support or refute each claim. We used CoVERt and SciFact (a public scientific claim verification dataset) to assess CliVER's performance in predicting labels. Finally, we compared CliVER to clinicians in the verification of 19 claims from 6 disease domains, using 189 648 PubMed abstracts extracted from January 2010 to October 2021.</p><p><strong>Results: </strong>In the evaluation of label prediction accuracy on CoVERt, CliVER achieved a notable F1 score of 0.92, highlighting the efficacy of the retrieval-augmented models. The ensemble model outperforms each individual state-of-the-art model by an absolute increase from 3% to 11% in the F1 score. Moreover, when compared with four clinicians, CliVER achieved a precision of 79.0% for abstract retrieval, 67.4% for sentence selection, and 63.2% for label prediction, respectively.</p><p><strong>Conclusion: </strong>CliVER demonstrates its early potential to automate scientific claim verification using retrieval-augmented strategies to harness the wealth of clinical trial abstracts in PubMed. Future studies are warranted to further test its clinical utility.</p>\",\"PeriodicalId\":36278,\"journal\":{\"name\":\"JAMIA Open\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2024-02-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10919922/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JAMIA Open\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/jamiaopen/ooae021\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/4/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JAMIA Open","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/jamiaopen/ooae021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/4/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 0

摘要

目的利用 PubMed 摘要自动验证科学索赔:我们开发了 CliVER,这是一个端到端的科学主张验证系统,它利用检索增强技术自动检索相关临床试验摘要、提取相关句子,并使用 PICO 框架来支持或反驳科学主张。我们还创建了由三个最先进的深度学习模型组成的集合,对支持、反驳和中立的理由进行分类。然后,我们构建了一个新的 COVID 验证数据集 CoVERt,该数据集由 15 个 PICO 编码的药物声明以及 96 个人工选择和标记的临床试验摘要组成,这些摘要支持或反驳了每个声明。我们使用 CoVERt 和 SciFact(一个公开的科学声明验证数据集)来评估 CliVER 在预测标签方面的性能。最后,我们使用 2010 年 1 月至 2021 年 10 月期间提取的 189 648 篇 PubMed 摘要,在验证 6 个疾病领域的 19 项索赔时,将 CliVER 与临床医生进行了比较:在对CoVERt上的标签预测准确性进行评估时,CliVER取得了0.92的显著F1分数,突出显示了检索增强模型的功效。集合模型的 F1 分数绝对值提高了 3% 到 11%,超过了每个单独的最先进模型。此外,与四位临床医生相比,CliVER 在摘要检索、句子选择和标签预测方面的精确度分别达到了 79.0%、67.4% 和 63.2%:CliVER利用检索增强策略,利用PubMed中丰富的临床试验摘要,展示了其在科学声明验证自动化方面的早期潜力。未来的研究将进一步检验其临床实用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Retrieval augmented scientific claim verification.

Objective: To automate scientific claim verification using PubMed abstracts.

Materials and methods: We developed CliVER, an end-to-end scientific Claim VERification system that leverages retrieval-augmented techniques to automatically retrieve relevant clinical trial abstracts, extract pertinent sentences, and use the PICO framework to support or refute a scientific claim. We also created an ensemble of three state-of-the-art deep learning models to classify rationale of support, refute, and neutral. We then constructed CoVERt, a new COVID VERification dataset comprising 15 PICO-encoded drug claims accompanied by 96 manually selected and labeled clinical trial abstracts that either support or refute each claim. We used CoVERt and SciFact (a public scientific claim verification dataset) to assess CliVER's performance in predicting labels. Finally, we compared CliVER to clinicians in the verification of 19 claims from 6 disease domains, using 189 648 PubMed abstracts extracted from January 2010 to October 2021.

Results: In the evaluation of label prediction accuracy on CoVERt, CliVER achieved a notable F1 score of 0.92, highlighting the efficacy of the retrieval-augmented models. The ensemble model outperforms each individual state-of-the-art model by an absolute increase from 3% to 11% in the F1 score. Moreover, when compared with four clinicians, CliVER achieved a precision of 79.0% for abstract retrieval, 67.4% for sentence selection, and 63.2% for label prediction, respectively.

Conclusion: CliVER demonstrates its early potential to automate scientific claim verification using retrieval-augmented strategies to harness the wealth of clinical trial abstracts in PubMed. Future studies are warranted to further test its clinical utility.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
JAMIA Open
JAMIA Open Medicine-Health Informatics
CiteScore
4.10
自引率
4.80%
发文量
102
审稿时长
16 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信