• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

目的:使用基于指南的查询对传统放射学报告和结构化报告进行比较。

Objective Comparison Using Guideline-based Query of Conventional Radiological Reports and Structured Reports.

作者信息

Maros Máté E, Wenz Ralf, Förster Alex, Froelich Matthias F, Groden Christoph, Sommer Wieland H, Schönberg Stefan O, Henzler Thomas, Wenz Holger

机构信息

Department of Neuroradiology, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany.

Department of Life Sciences, Faculty of Natural Sciences, Imperial College London, London, U.K.

出版信息

In Vivo. 2018 Jul-Aug;32(4):843-849. doi: 10.21873/invivo.11318.

DOI:10.21873/invivo.11318
PMID:29936469
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC6117779/
Abstract

BACKGROUND

This feasibility study of text-mining-based scoring algorithm provides an objective comparison of structured reports (SR) and conventional free-text reports (cFTR) by means of guideline-based key terms. Furthermore, an open-source online version of this ranking algorithm was provided with multilingual text-retrieval pipeline, customizable query and real-time-scoring.

MATERIALS AND METHODS

Twenty-five patients with suspected stroke and magnetic resonance imaging were re-assessed by two independent/blinded readers [inexperienced: 3 years; experienced >6 years/Board-certified). SR and cFTR were compared with guideline-query using the cosine similarity score (CSS) and Wilcoxon signed-rank test.

RESULTS

All pathological findings (18/18) were identified by SR and cFTR. The impressions section of the SRs of the inexperienced reader had the highest median (0.145) and maximal (0.214) CSS and were rated significantly higher (p=2.21×10 and p=1.4×10, respectively) than cFTR (median=0.102). CSS was robust to variations of query.

CONCLUSION

Objective guideline-based comparison of SRs and cFTRs using the CSS is feasible and provides a scalable quality measure that can facilitate the adoption of structured reports in all fields of radiology.

摘要

背景

这项基于文本挖掘的评分算法的可行性研究,通过基于指南的关键词,对结构化报告(SR)和传统自由文本报告(cFTR)进行了客观比较。此外,该排名算法的开源在线版本配备了多语言文本检索管道、可定制查询和实时评分功能。

材料与方法

25例疑似中风且接受了磁共振成像检查的患者,由两名独立的/不知情的读者(经验不足:3年;经验丰富:>6年/获得委员会认证)重新评估。使用余弦相似性评分(CSS)和威尔科克森符号秩检验,将SR和cFTR与指南查询进行比较。

结果

所有病理结果(18/18)均由SR和cFTR识别。经验不足的读者的SR的印象部分,CSS中位数最高(0.145),最大值(0.214),且评分显著高于cFTR(中位数=0.102)(分别为p=2.21×10和p=1.4×10)。CSS对查询变化具有鲁棒性。

结论

使用CSS对SR和cFTR进行基于指南的客观比较是可行的,并提供了一种可扩展的质量度量,有助于在放射学的所有领域采用结构化报告。

相似文献

1
Objective Comparison Using Guideline-based Query of Conventional Radiological Reports and Structured Reports.目的:使用基于指南的查询对传统放射学报告和结构化报告进行比较。
In Vivo. 2018 Jul-Aug;32(4):843-849. doi: 10.21873/invivo.11318.
2
Cohort study of structured reporting compared with conventional dictation.结构化报告与传统口述的队列研究。
Radiology. 2009 Oct;253(1):74-80. doi: 10.1148/radiol.2531090138. Epub 2009 Aug 25.
3
Increasing the Efficiency on Producing Radiology Reports for Breast Cancer Diagnosis by Means of Structured Reports. A Comparative Study.通过结构化报告提高乳腺癌诊断放射学报告的生成效率。一项比较研究。
Methods Inf Med. 2017 May 18;56(3):248-260. doi: 10.3414/ME16-01-0091. Epub 2017 Feb 21.
4
Structured reporting of MRI of the shoulder - improvement of report quality?磁共振成像(MRI)肩结构报告 - 提高报告质量?
Eur Radiol. 2017 Oct;27(10):4110-4119. doi: 10.1007/s00330-017-4778-z. Epub 2017 Mar 13.
5
Unsupervised Topic Modeling in a Large Free Text Radiology Report Repository.大型自由文本放射学报告库中的无监督主题建模
J Digit Imaging. 2016 Feb;29(1):59-62. doi: 10.1007/s10278-015-9823-3.
6
Structured reporting in petrous bone MRI examinations: impact on report completeness and quality.岩骨 MRI 检查中的结构化报告:对报告完整性和质量的影响。
Int J Comput Assist Radiol Surg. 2018 Dec;13(12):1971-1980. doi: 10.1007/s11548-018-1828-1. Epub 2018 Jul 23.
7
A natural language processing pipeline for pairing measurements uniquely across free-text CT reports.一种用于在自由文本CT报告中唯一配对测量值的自然语言处理管道。
J Biomed Inform. 2015 Feb;53:36-48. doi: 10.1016/j.jbi.2014.08.015. Epub 2014 Sep 6.
8
A Statistical Analysis of Term Occurrences in Radiology Reporting.放射学报告中术语出现情况的统计分析
Stud Health Technol Inform. 2015;216:1085.
9
Quality outcomes of reinterpretation of brain CT studies by subspecialty experts in stroke imaging.对脑卒中影像学亚专科专家重新解读脑 CT 研究的质量结果。
AJR Am J Roentgenol. 2012 Dec;199(6):1365-70. doi: 10.2214/AJR.11.8358.
10
An ontology-based similarity measure for biomedical data-application to radiology reports.基于本体的生物医学数据相似度测量-在放射学报告中的应用。
J Biomed Inform. 2013 Oct;46(5):857-68. doi: 10.1016/j.jbi.2013.06.013. Epub 2013 Jul 11.

引用本文的文献

1
Individual glioblastoma cells harbor both proliferative and invasive capabilities during tumor progression.在肿瘤进展过程中,单个胶质母细胞瘤细胞具有增殖和侵袭的能力。
Neuro Oncol. 2023 Dec 8;25(12):2150-2162. doi: 10.1093/neuonc/noad109.
2
Myelofibrosis progression grading based on type I and type III collagen and fibrillin 1 expression boosted by whole slide image analysis.基于 I 型和 III 型胶原及原纤维蛋白 1 表达的骨髓纤维化进展分级,通过全玻片图像分析得到增强。
Histopathology. 2023 Mar;82(4):622-632. doi: 10.1111/his.14846. Epub 2022 Dec 12.
3
Correlations Between the Expression of Stromal Cell Activation Related Biomarkers, L-NGFR, Phospho-ERK1-2 and CXCL12, and Primary Myelofibrosis Progression.基质细胞激活相关生物标志物 L-NGFR、磷酸化 ERK1-2 和 CXCL12 的表达与原发性骨髓纤维化进展的相关性。
Pathol Oncol Res. 2022 Mar 14;28:1610217. doi: 10.3389/pore.2022.1610217. eCollection 2022.
4
A systematic review of natural language processing applied to radiology reports.自然语言处理在放射学报告中的应用的系统评价。
BMC Med Inform Decis Mak. 2021 Jun 3;21(1):179. doi: 10.1186/s12911-021-01533-7.
5
Comparative analysis of machine learning algorithms for computer-assisted reporting based on fully automated cross-lingual RadLex mappings.基于全自动跨语言 RadLex 映射的计算机辅助报告机器学习算法的比较分析。
Sci Rep. 2021 Mar 9;11(1):5529. doi: 10.1038/s41598-021-85016-9.
6
Viewing Imaging Studies: How Patient Location and Imaging Site Affect Referring Physicians.查看影像学研究:患者位置和影像学检查部位如何影响转诊医师。
J Digit Imaging. 2020 Apr;33(2):334-340. doi: 10.1007/s10278-019-00279-z.

本文引用的文献

1
Usage of structured reporting in radiological practice: results from an Italian online survey.结构化报告在放射学实践中的应用:一项意大利在线调查的结果。
Eur Radiol. 2017 May;27(5):1934-1943. doi: 10.1007/s00330-016-4553-6. Epub 2016 Aug 29.
2
Natural Language Processing in Radiology: A Systematic Review.自然语言处理在放射学中的应用:系统评价。
Radiology. 2016 May;279(2):329-43. doi: 10.1148/radiol.16142770.
3
Conversion of Radiology Reporting Templates to the MRRT Standard.将放射学报告模板转换为MRRT标准。
J Digit Imaging. 2015 Oct;28(5):528-36. doi: 10.1007/s10278-015-9787-3.
4
Reporting initiative of the Radiological Society of North America: progress and new directions.北美放射学会的报告倡议:进展与新方向。
Radiology. 2014 Dec;273(3):642-5. doi: 10.1148/radiol.14141227.
5
Imaging recommendations for acute stroke and transient ischemic attack patients: a joint statement by the American Society of Neuroradiology, the American College of Radiology and the Society of NeuroInterventional Surgery.急性卒中和短暂性脑缺血发作患者的影像学推荐:美国神经放射学会、美国放射学院和神经介入外科学会的联合声明。
J Am Coll Radiol. 2013 Nov;10(11):828-32. doi: 10.1016/j.jacr.2013.06.019. Epub 2013 Aug 13.
6
Content analysis of reporting templates and free-text radiology reports.报告模板和放射学报告的内容分析。
J Digit Imaging. 2013 Oct;26(5):843-9. doi: 10.1007/s10278-013-9597-4.
7
From guidelines to practice: how reporting templates promote the use of radiology practice guidelines.从指南到实践:报告模板如何促进放射科实践指南的使用。
J Am Coll Radiol. 2013 Apr;10(4):268-73. doi: 10.1016/j.jacr.2012.09.025. Epub 2013 Jan 16.
8
Intelligent image retrieval based on radiology reports.基于放射报告的智能图像检索。
Eur Radiol. 2012 Dec;22(12):2750-8. doi: 10.1007/s00330-012-2608-x. Epub 2012 Aug 4.
9
An open-standards grammar for outline-style radiology report templates.用于大纲样式放射学报告模板的开放标准语法。
J Digit Imaging. 2012 Jun;25(3):359-64. doi: 10.1007/s10278-012-9456-8.
10
Critical finding capture in the impression section of radiology reports.放射学报告印象部分中的关键发现记录。
AMIA Annu Symp Proc. 2011;2011:465-9. Epub 2011 Oct 22.