Suppr超能文献

比较用于诊断肺炎的胸片印象:考虑语言确定性类别。

Comparison of Chest Radiograph Impressions for Diagnosing Pneumonia: Accounting for Categories of Language Certainty.

机构信息

Institute of Health Systems Science, Feinstein Institutes for Medical Research, Northwell Health, Manhasset, New York; Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, New York.

Director, Geriatric Hospitalist Service, Institute of Health Systems Science, Feinstein Institutes for Medical Research, Northwell Health, Manhasset, New York; Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, New York.

出版信息

J Am Coll Radiol. 2022 Oct;19(10):1130-1137. doi: 10.1016/j.jacr.2022.05.020. Epub 2022 Jul 2.

Abstract

OBJECTIVES

Uncertain language in chest radiograph (CXR) reports for the diagnosis of pneumonia is prevalent. The purpose of this study is to validate an a priori stratification of CXR results for diagnosing pneumonia based on language of certainty.

DESIGN

Retrospective chart review.

SETTING AND PARTICIPANTS

CXR reports of 2,411 patient visits ≥ 18 years, admitted to medicine, who received a CXR and noncontrast chest CT within 48 hours of emergency department registration at two large academic hospitals (tertiary and quaternary care) were reviewed.

METHODS

The CXR and CT report impressions were categorized as negative, uncertain, or positive. Uncertain CXRs were further stratified into four categories based on language modifiers for the degree of pneumonia certainty. Comparison of CXR and CT results were determined using χ test; a P value of less than .0033 was considered significant to account for multiple comparisons.

RESULTS

CXR reports for the diagnosis of pneumonia revealed the following distribution: 61% negative, 32% uncertain, and 7% positive; CT reports were 55% negative, 22% uncertain, and 23% positive for the diagnosis of pneumonia. There were significant differences between CXR categories compared with CT categories for diagnosis of pneumonia (P < .001). Negative CXR results were not significantly different than the uncertain category with the most uncertain language (P = .030) but were significantly different from all other uncertain categories and positive CXR results (each P < .001). Positive CXR results were not significantly different than the least uncertain category (most certain language) (P = .130) but were significantly different from all other categories (each P < .001).

CONCLUSIONS AND IMPLICATIONS

Language used in CXR reports to diagnose pneumonia exists in categories of varying certainty and should be considered when evaluating patients for pneumonia.

摘要

目的

胸部 X 光片(CXR)报告中用于诊断肺炎的不确定语言较为常见。本研究的目的是验证基于语言确定性对 CXR 结果进行肺炎诊断的预先分层。

设计

回顾性图表审查。

地点和参与者

对在两家大型学术医院(三级和四级保健)急诊登记后 48 小时内接受 CXR 和非对比胸部 CT 的 2411 例≥18 岁患者的 CXR 报告进行了回顾。

方法

CXR 和 CT 报告印象分为阴性、不确定或阳性。不确定的 CXR 根据肺炎确定性的语言修饰符进一步分为四个类别。使用 χ 检验比较 CXR 和 CT 结果;P 值小于 0.0033 被认为具有统计学意义,以考虑多次比较。

结果

用于诊断肺炎的 CXR 报告显示以下分布:61%为阴性,32%为不确定,7%为阳性;CT 报告为 55%为阴性,22%为不确定,23%为阳性,用于诊断肺炎。与 CT 类别相比,CXR 类别在诊断肺炎方面存在显著差异(P < 0.001)。阴性 CXR 结果与最不确定类别(语言最不确定)无显著差异(P = 0.030),但与所有其他不确定类别和阳性 CXR 结果有显著差异(各 P < 0.001)。阳性 CXR 结果与最不确定类别(语言最确定)无显著差异(P = 0.130),但与所有其他类别有显著差异(各 P < 0.001)。

结论和意义

用于诊断肺炎的 CXR 报告中的语言存在不同的确定性类别,在评估肺炎患者时应予以考虑。

相似文献

本文引用的文献

9
The antimicrobial resistance crisis: causes, consequences, and management.抗菌药物耐药性危机:原因、后果和管理。
Front Public Health. 2014 Sep 16;2:145. doi: 10.3389/fpubh.2014.00145. eCollection 2014.
10
Natural Language Processing to identify pneumonia from radiology reports.自然语言处理技术从放射学报告中识别肺炎。
Pharmacoepidemiol Drug Saf. 2013 Aug;22(8):834-41. doi: 10.1002/pds.3418. Epub 2013 Apr 1.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验