常规增强胸部CT上偶发肺栓塞的检测:人工智能算法与临床报告的比较
本回顾性研究纳入2555例患者共3003次常规增强胸部CT检查,评估商业AI算法检测偶发肺栓塞(iPE)的诊断性能,并以多读者裁决为参考标准与临床报告比较。AI检出4例临床报告漏诊的iPE,临床报告检出7例AI漏诊的iPE;AI的PPV(86.8% vs 97.3%,p=.03)和特异度(99.8% vs 100.0%,p=.045)显著低于临床报告,敏感度(82.5% vs 90.0%,p=.37)和NPV(99.8% vs 99.9%,p=.36)差异不显著。作者认为AI对iPE检测有高NPV和中等PPV,可作为第二读者或工作列表分诊工具。
要点
- AI检出4例临床报告漏诊的偶发肺栓塞,临床报告检出7例AI漏诊的偶发肺栓塞。
- AI的PPV 86.8%显著低于临床报告97.3%(p=.03),特异度99.8%显著低于100.0%(p=.045)。
- AI假阳性原因包括转移性淋巴结和肺静脉充盈缺损,假阴性原因包括术后解剖改变和小口径亚段血管。
核心结论
- AI对偶发肺栓塞检测具有高NPV和中等PPV,能检出部分放射科医师漏诊的偶发肺栓塞。
研究设计与样本
- 回顾性研究,纳入2555例患者(平均年龄53.2±14.5岁;女性1340例,男性1215例)共3003次常规增强胸部CT检查(非肺栓塞CTA方案),时间范围为2019年9月至2020年2月;以多读者裁决过程为参考标准,并应用商业AI算法检测急性偶发肺栓塞、供应商提供的自然语言处理算法识别临床报告中的偶发肺栓塞。
关键影像表现/征象
- AI假阳性解释包括转移性淋巴结和肺静脉充盈缺损。
- AI假阴性解释包括术后解剖改变和小口径亚段血管。
- 基于裁决过程,偶发肺栓塞的频率为1.3%(40/3003)。
诊断标准与关键数值
- AI检测偶发肺栓塞的敏感度为82.5%,临床报告为90.0%(p=.37,差异不显著)。
- AI检测偶发肺栓塞的特异度为99.8%,临床报告为100.0%(p=.045)。
- AI检测偶发肺栓塞的PPV为86.8%,临床报告为97.3%(p=.03)。
- AI检测偶发肺栓塞的NPV为99.8%,临床报告为99.9%(p=.36,差异不显著)。
- AI的敏感度和特异度与年龄、性别、患者状态或癌症相关临床场景均无显著关联(所有p>.05)。
临床应用与阅片要点
- 作者认为AI工具的潜在应用包括作为第二读者帮助检出额外偶发肺栓塞,或作为工作列表分诊工具以便更早发现和干预偶发肺栓塞。
- AI误分类的各种解释可为模型改进提供靶点。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND. Artificial intelligence (AI) algorithms have shown strong performance for detection of pulmonary embolism (PE) on CT examinations performed using a dedicated protocol for PE detection. AI performance is less well studied for detecting PE on examinations ordered for reasons other than suspected PE (i.e., incidental PE [iPE]). OBJECTIVE. The purpose of this study was to assess the diagnostic performance of an AI algorithm for detection of iPE on conventional contrast-enhanced chest CT examinations. METHODS. This retrospective study included 2555 patients (mean age, 53.2 ± 14.5 [SD] years; 1340 women, 1215 men) who underwent 3003 conventional contrast-enhanced chest CT examinations (i.e., not using pulmonary CTA protocols) between September 2019 and February 2020. A commercial AI algorithm was applied to the images to detect acute iPE. A vendor-supplied natural language processing (NLP) algorithm was applied to the clinical reports to identify examinations interpreted as positive for iPE. For all examinations that were positive by the AI-based image review or by NLP-based report review, a multireader adjudication process was implemented to establish a reference standard for iPE. Images were also reviewed to identify explanations of AI misclassifications. RESULTS. On the basis of the adjudication process, the frequency of iPE was 1.3% (40/3003). AI detected four iPEs missed by clinical reports, and clinical reports detected seven iPEs missed by AI. AI, compared with clinical reports, exhibited significantly lower PPV (86.8% vs 97.3%, p = .03) and specificity (99.8% vs 100.0%, p = .045). Differences in sensitivity (82.5% vs 90.0%, p = .37) and NPV (99.8% vs 99.9%, p = .36) were not significant. For AI, neither sensitivity nor specificity varied significantly in association with age, sex, patient status, or cancer-related clinical scenario (all p > .05). Explanations of false-positives by AI included metastatic lymph nodes and pulmonary venous filling defect, and explanations of false-negatives by AI included surgically altered anatomy and small-caliber subsegmental vessels. CONCLUSION. AI had high NPV and moderate PPV for iPE detection, detecting some iPEs missed by radiologists. CLINICAL IMPACT. Potential applications of the AI tool include serving as a second reader to help detect additional iPEs or as a worklist triage tool to allow earlier iPE detection and intervention. Various explanations of AI misclassifications may provide targets for model improvement.
引用
- Batra, Xi, Al-Hreish, et al. Detection of Incidental Pulmonary Embolism on Conventional Contrast-Enhanced Chest CT: Comparison of an Artificial Intelligence Algorithm and Clinical Reports. AJR Am J Roentgenol. 2022. PMID: 35822644. doi:10.2214/AJR.22.27895
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。