人工智能在检测COVID-19肺炎的诊断性能 胸部成像
Savannah R Chapman1, Lauren Willner1, Alex Abouafech1
1School of Medicine, Lake Erie College of Osteopathic Medicine, Bradenton, USA.
Cureus
|February 19, 2026
概括
人工智能 (AI) 在使用胸部成像 (CXR和CT) 检测COVID-19肺炎方面表现有希望,其性能通常与放射科医生相匹配. 然而,普遍性和信任方面的挑战需要进一步研究以确保安全的临床整合.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 传染病诊断 传染病诊断 传染病诊断
背景情况:
- 由于COVID-19的流行,人们需要快速准确的诊断工具.
- 胸部成像 (CXR,CT) 和人工智能系统成为COVID-19诊断和工作流程的关键.
- 人工智能开发旨在支持图像解释和提高效率.
研究的目的:
- 审查使用CXR和CT检测COVID-19肺炎的AI模型的证据.
- 综合这些人工智能系统的诊断性能,局限性和临床影响.
- 评估包含的研究中的质量和偏差风险.
主要方法:
- 进行了PubMed文献搜索,截至2025年10月.
- 包括评估AI用于CXR/CT上的COVID-19肺炎检测的研究.
- 评估了诊断指标 (灵敏度,特异性,精度,AUC) 并使用QUADAS-2进行质量评估.
主要成果:
- 十一项研究符合纳入标准.
- CXR AI:灵敏度为80-98%,特异性为82-96%. CT AI:准确度在90-96%之间.
- 人工智能显示出强大的内部性能,但在外部验证上精度降低,突出了概括性问题.
结论:
- 人工智能模型在胸部成像上展示了COVID-19肺炎的有希望的诊断性能.
- 人工智能可以提高放射科医生的效率,但在概括性,适应性和临床医生的信任方面面临挑战.
- 未来的研究必须专注于外部验证和透明报告,以确保安全的AI集成.
相关概念视频
Pneumonia III: Complications and Assessment
938
Pneumonia poses the potential for numerous complications that warrant consideration. These complications include the following:
938
Imaging Studies for Cardiovascular System III: X-Ray
502
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
502


