A systematic review of natural language processing applied to radiology reports.

A systematic review of natural language processing applied to radiology reports.
复制标题

DOI:
10.1186/s12911-021-01533-7
复制
发表时间:
2021-06-03
影响因子:
3.5
通讯作者:
Alex B
Alex B
中科院分区:
医学3区
文献类型:
--
作者:
Casey A;Davidson E;Poon M;Dong H;Duma D;Grivas A;Grover C;Suárez-Paniagua V;Tobin R;Whiteley W;Wu H;Alex B

文献摘要

参考文献

被引文献

相似文献

自然语言处理(NLP)在推进医疗保健方面发挥着重要作用,并且已被发现是从放射学报告中提取结构化信息的关键。了解NLP应用于放射学的最新发展是有意义的,但最近的评论是有限的。本研究系统地评估和量化了NLP应用于放射学报告的最新文献。我们使用自动过滤、元数据丰富步骤和引文搜索结合人工审稿进行自动文献检索,产生4836个结果。我们的分析基于21个变量,包括放射学特征、NLP方法、表现、研究和临床应用特征。我们对检索到的164篇论文进行了全面分析,其中2019年的论文几乎是2015年的三倍。每份出版物被分类为6个临床应用类别之一。在此期间,深度学习的使用有所增加,但传统的机器学习方法仍然普遍存在。当数据稀缺,并且几乎没有证据表明将深度学习应用于临床实践时,深度学习仍然面临挑战。尽管有17%的研究报告F1得分大于0.85,但由于这些方法大多使用不同的数据集,因此很难对这些方法进行比较评估。只有14项研究提供了他们的数据,15项研究提供了他们的代码,10项研究的结果得到了外部验证。对放射学报告的临床叙述的自动理解具有增强医疗保健过程的潜力,我们表明,在这一领域的研究继续增长。如果该领域要将应用程序转移到临床使用,那么模型的可重复性和可解释性是重要的。可以做更多的工作来共享代码,以便在不同的机构数据上验证方法,并减少研究性质报告的异质性,从而进行研究间比较。我们的结果对该领域的研究人员具有重要意义,提供了现有工作的系统综合,以建立,确定差距,合作机会和避免重复。在线版本包含补充材料,可在10.1186/s12911-021-01533-7获得。
Natural language processing (NLP) has a significant role in advancing healthcare and has been found to be key in extracting structured information from radiology reports. Understanding recent developments in NLP application to radiology is of significance but recent reviews on this are limited. This study systematically assesses and quantifies recent literature in NLP applied to radiology reports. We conduct an automated literature search yielding 4836 results using automated filtering, metadata enriching steps and citation search combined with manual review. Our analysis is based on 21 variables including radiology characteristics, NLP methodology, performance, study, and clinical application characteristics. We present a comprehensive analysis of the 164 publications retrieved with publications in 2019 almost triple those in 2015. Each publication is categorised into one of 6 clinical application categories. Deep learning use increases in the period but conventional machine learning approaches are still prevalent. Deep learning remains challenged when data is scarce and there is little evidence of adoption into clinical practice. Despite 17% of studies reporting greater than 0.85 F1 scores, it is hard to comparatively evaluate these approaches given that most of them use different datasets. Only 14 studies made their data and 15 their code available with 10 externally validating results. Automated understanding of clinical narratives of the radiology reports has the potential to enhance the healthcare process and we show that research in this field continues to grow. Reproducibility and explainability of models are important if the domain is to move applications into clinical use. More could be done to share code enabling validation of methods on different institutional data and to reduce heterogeneity in reporting of study properties allowing inter-study comparisons. Our results have significance for researchers in the field providing a systematic synthesis of existing work to build on, identify gaps, opportunities for collaboration and avoid duplication. The online version contains supplementary material available at 10.1186/s12911-021-01533-7.
放射学报告使用智能单词嵌入的注释:应用于多机构胸部CT队列。
DOI: 10.1016/j.jbi.2017.11.012
发表时间: 2018-01
影响因子: 4.5
作者:
Banerjee I;Chen MC;Lungren MP;Rubin DL
通讯作者: Rubin DL
DOI: 10.1016/j.artmed.2018.11.004
发表时间: 2019-06-01
影响因子: 7.5
作者:
Banerjee, Imon;Ling, Yuan;Lungren, Matthew P.
通讯作者: Lungren, Matthew P.
DOI: 10.1007/s10278-019-00237-9
发表时间: 2019-08-01
影响因子: 4.4
作者:
Bozkurt, Selen;Alkim, Emel;Rubin, Daniel L.
通讯作者: Rubin, Daniel L.
DOI: 10.1016/j.jacr.2018.12.004
发表时间: 2019-06-01
影响因子: 4.5
作者:
Brown, A. D.;Kachura, J. R.
通讯作者: Kachura, J. R.
DOI: 10.1093/jamia/ocv155
发表时间: 2016-04-01
影响因子: 6.4
作者:
Bates, Jonathan;Fodeh, Samah J.;Womack, Julie A.
通讯作者: Womack, Julie A.