Department of Radiology, Shanghai Jiao Tong University Medical School Affiliated Ruijin Hospital, No. 197, Ruijin Er Road, Shanghai, 200025, China.
Department of Radiology, Ruian People's Hospital, No. 108, Wan Song Road, Ruian, 325200, Zhejiang Province, China.
Eur Radiol. 2020 Dec;30(12):6797-6807. doi: 10.1007/s00330-020-07022-1. Epub 2020 Jul 1.
To develop a predictive model and scoring system to enhance the diagnostic efficiency for coronavirus disease 2019 (COVID-19).
From January 19 to February 6, 2020, 88 confirmed COVID-19 patients presenting with pneumonia and 80 non-COVID-19 patients suffering from pneumonia of other origins were retrospectively enrolled. Clinical data and laboratory results were collected. CT features and scores were evaluated at the segmental level according to the lesions' position, attenuation, and form. Scores were calculated based on the size of the pneumonia lesion, which graded at the range of 1 to 4. Air bronchogram, tree-in-bud sign, crazy-paving pattern, subpleural curvilinear line, bronchiectasis, air space, pleural effusion, and mediastinal and/or hilar lymphadenopathy were also evaluated.
Multivariate logistic regression analysis showed that history of exposure (β = 3.095, odds ratio (OR) = 22.088), leukocyte count (β = - 1.495, OR = 0.224), number of segments with peripheral lesions (β = 1.604, OR = 1.604), and crazy-paving pattern (β = 2.836, OR = 2.836) were used for establishing the predictive model to identify COVID-19-positive patients (p < 0.05). In this model, values of area under curve (AUC) in the training and testing groups were 0.910 and 0.914, respectively (p < 0.001). A predicted score for COVID-19 (PSC-19) was calculated based on the predictive model by the following formula: PSC-19 = 2 × history of exposure (0-1 point) - 1 × leukocyte count (0-2 points) + 1 × peripheral lesions (0-1 point) + 2 × crazy-paving pattern (0-1 point), with an optimal cutoff point of 1 (sensitivity, 88.5%; specificity, 91.7%).
Our predictive model and PSC-19 can be applied for identification of COVID-19-positive cases, assisting physicians and radiologists until receiving the results of reverse transcription-polymerase chain reaction (RT-PCR) tests.
• Prediction of RT-PCR positivity is crucial for fast diagnosis of patients suspected of having coronavirus disease 2019 (COVID-19). • Typical CT manifestations are advantageous for diagnosing COVID-19 and differentiation of COVID-19 from other types of pneumonia. • A predictive model and scoring system combining both clinical and CT features were herein developed to enable high diagnostic efficiency for COVID-19.
开发一种预测模型和评分系统，以提高对 2019 年冠状病毒病（COVID-19）的诊断效率。
2020 年 1 月 19 日至 2 月 6 日，回顾性纳入了 88 例确诊为 COVID-19 肺炎的患者和 80 例非 COVID-19 肺炎的患者。收集临床数据和实验室结果。根据病变位置、衰减和形态，在节段水平评估 CT 特征和评分。根据肺炎病变的大小计算评分，范围为 1 到 4 分。还评估了空气支气管征、树芽征、铺路石征、胸膜下线、支气管扩张、气腔、胸腔积液以及纵隔和/或肺门淋巴结肿大。
多变量逻辑回归分析显示，接触史（β=3.095，优势比（OR）=22.088）、白细胞计数（β=-1.495，OR=0.224）、外周病变节段数（β=1.604，OR=1.604）和铺路石征（β=2.836，OR=2.836）用于建立预测模型以识别 COVID-19 阳性患者（p<0.05）。在该模型中，训练组和测试组的曲线下面积（AUC）值分别为 0.910 和 0.914（p<0.001）。根据预测模型计算 COVID-19 预测评分（PSC-19），公式如下：PSC-19=2×接触史（0-1 分）-1×白细胞计数（0-2 分）+1×外周病变（0-1 分）+2×铺路石征（0-1 分），最佳截断点为 1（敏感性为 88.5%，特异性为 91.7%）。
我们的预测模型和 PSC-19 可用于识别 COVID-19 阳性病例，有助于医生和放射科医生在收到逆转录-聚合酶链反应（RT-PCR）检测结果之前进行诊断。
预测 RT-PCR 阳性对于快速诊断疑似 COVID-19 的患者至关重要。
COVID-19 的典型 CT 表现有助于诊断 COVID-19 并与其他类型肺炎相区分。
本文开发了一种结合临床和 CT 特征的预测模型和评分系统，以提高 COVID-19 的诊断效率。
