A predictive model and scoring system combining clinical and CT characteristics for the diagnosis of COVID-19

Objectives To develop a predictive model and scoring system to enhance the diagnostic efficiency for coronavirus disease 2019 (COVID-19). Methods 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. Results Multivariate logistic regression analysis showed that history of exposure (beta = 3.095, odds ratio (OR) = 22.088), leukocyte count (beta = - 1.495, OR = 0.224), number of segments with peripheral lesions (beta = 1.604, OR = 1.604), and crazy-paving pattern (beta = 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 x history of exposure (0-1 point) - 1 x leukocyte count (0-2 points) + 1 x peripheral lesions (0-1 point) + 2 x crazy-paving pattern (0-1 point), with an optimal cutoff point of 1 (sensitivity, 88.5%; specificity, 91.7%). Conclusions 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.