Gieraerts Christopher, Dangis Anthony, Janssen Lode, Demeyere Annick, De Bruecker Yves, De Brucker Nele, van Den Bergh Annelies, Lauwerier Tine, Heremans André, Frans Eric, Laurent Michaël, Ector Bavo, Roosen John, Smismans Annick, Frans Johan, Gillis Marc, Symons Rolf
Department of Radiology - Imelda Hospital, Bonheiden, Belgium (C.G., A.D., L.J., A.D., Y.D.B., R.S.); Department of Pulmonology - Imelda Hospital, Bonheiden, Belgium (N.D.B., A.V.D.B., T.L., A.H., E.F.); Department of Intensive Care Medicine - Imelda Hospital, Bonheiden, Belgium (E.F.); Department of Geriatrics - Imelda Hospital, Bonheiden, Belgium (M.L.); Department of Cardiology - Imelda Hospital, Bonheiden, Belgium (B.E., J.R.); Department of Medical Microbiology - Imelda Hospital, Bonheiden, Belgium (A.S., J.F.); Department of Emergency Medicine - Imelda Hospital, Bonheiden, Belgium (M.G.).
Radiol Cardiothorac Imaging. 2020 Oct 22;2(5):e200441. doi: 10.1148/ryct.2020200441. eCollection 2020 Oct.
To compare the prognostic value and reproducibility of visual versus AI-assisted analysis of lung involvement on submillisievert low-dose chest CT in COVID-19 patients.
This was a HIPAA-compliant, institutional review board-approved retrospective study. From March 15 to June 1, 2020, 250 RT-PCR confirmed COVID-19 patients were studied with low-dose chest CT at admission. Visual and AI-assisted analysis of lung involvement was performed by using a semi-quantitative CT score and a quantitative percentage of lung involvement. Adverse outcome was defined as intensive care unit (ICU) admission or death. Cox regression analysis, Kaplan-Meier curves, and cross-validated receiver operating characteristic curve with area under the curve (AUROC) analysis was performed to compare model performance. Intraclass correlation coefficients (ICCs) and Bland- Altman analysis was used to assess intra- and interreader reproducibility.
Adverse outcome occurred in 39 patients (11 deaths, 28 ICU admissions). AUC values from AI-assisted analysis were significantly higher than those from visual analysis for both semi-quantitative CT scores and percentages of lung involvement (all P<0.001). Intrareader and interreader agreement rates were significantly higher for AI-assisted analysis than visual analysis (all ICC ≥0.960 versus ≥0.885). AI-assisted variability for quantitative percentage of lung involvement was 17.2% (coefficient of variation) versus 34.7% for visual analysis. The sample size to detect a 5% change in lung involvement with 90% power and an α error of 0.05 was 250 patients with AI-assisted analysis and 1014 patients with visual analysis.
AI-assisted analysis of lung involvement on submillisievert low-dose chest CT outperformed conventional visual analysis in predicting outcome in COVID-19 patients while reducing CT variability. Lung involvement on chest CT could be used as a reliable metric in future clinical trials.
比较在亚毫西弗特低剂量胸部CT上，视觉分析与人工智能辅助分析对COVID-19患者肺部受累情况的预后价值和可重复性。
这是一项符合健康保险流通与责任法案（HIPAA）且经机构审查委员会批准的回顾性研究。2020年3月15日至6月1日，对250例经逆转录聚合酶链反应（RT-PCR）确诊的COVID-19患者入院时进行低剂量胸部CT检查。采用半定量CT评分和肺部受累定量百分比对肺部受累情况进行视觉分析和人工智能辅助分析。不良结局定义为入住重症监护病房（ICU）或死亡。进行Cox回归分析、Kaplan-Meier曲线分析以及具有曲线下面积（AUROC）分析的交叉验证接收器操作特征曲线分析，以比较模型性能。使用组内相关系数（ICC）和Bland-Altman分析来评估阅片者内和阅片者间的可重复性。
39例患者出现不良结局（11例死亡，28例入住ICU）。对于半定量CT评分和肺部受累百分比，人工智能辅助分析的AUC值均显著高于视觉分析（所有P<0.001）。人工智能辅助分析的阅片者内和阅片者间一致率显著高于视觉分析（所有ICC≥0.960对≥0.885）。肺部受累定量百分比的人工智能辅助变异性为17.2%（变异系数），而视觉分析为34.7%。在检验效能为90%且α错误为0.05的情况下，检测肺部受累5%变化所需的样本量，人工智能辅助分析为250例患者，视觉分析为1014例患者。
在预测COVID-19患者的结局方面，亚毫西弗特低剂量胸部CT上的人工智能辅助肺部受累分析优于传统视觉分析，同时降低了CT变异性。胸部CT上的肺部受累情况可在未来临床试验中用作可靠指标。
