Nomogram to identify severe Coronavirus Disease 2019 (COVID-19) based on initial clinical and CT characteristics: a multi-center study

Abstract

Background: To develop and validate a nomogram for early identification of severe coronavirus disease 2019 (COVID-19) based on initial clinical and CT characteristics.Methods: The initial clinical and CT imaging data of 217 patients with COVID-19 were analyzed retrospectively from January to March 2020. 217 patients with 146 mild cases and 71 severe cases were randomly divided into training and validation cohorts. Independent risk factors were selected to construct the nomogram for predicting severe COVID-19. Nomogram performance in terms of discrimination and calibration ability was evaluated using the area under the curve (AUC), calibration curve, decision curve, clinical impact curve and risk chart.Results: In the training cohort, the severity score of lung in the severe group (7, interquartile range [IQR]:5-9) was significantly higher than that of the mild group (4, IQR:2-5) (P < 0.001). Age, density, mosaic perfusion sign and severity score of lung were independent risk factors for severe COVID-19. The nomogram had a AUC of 0.929 (95% CI, 0.889-0.969), sensitivity of 84.0% and specificity of 86.3%, in the training cohort, and a AUC of 0.936 (95% CI, 0.867-1.000), sensitivity of 90.5% and specificity of 88.6% in the validation cohort. The calibration curve, decision curve, clinical impact curve and risk chart showed that nomogram had high accuracy and superior net benefit in predicting severe COVID-19.Conclusion: The nomogram incorporating initial clinical and CT characteristics may help to identify the severe patients with COVID-19 in the early stage.

COVID-19: A qualitative chest CT model to identify severe form of the disease

“…Area of consolidation, bronchiectasis and traction bronchiectasis were significantly more often found in the severe group of patients. In line with some other studies, air bronchogram sign [13,17] and pleural effusion [17] were also significantly more often found. Unlike in some other studies, pericardial effusion was not found as a criteria associated with a severe form, nor was lymph node enlargement, nor was crazy-paving pattern [13,17].…”

“…In line with some other studies, air bronchogram sign [13,17] and pleural effusion [17] were also significantly more often found. Unlike in some other studies, pericardial effusion was not found as a criteria associated with a severe form, nor was lymph node enlargement, nor was crazy-paving pattern [13,17]. The most relevant CT features were all related to the extent of the disease.…”

“…Of note, calculation of well-aerated lung in COVID-19 patients using automatic software has been reported as taking a median time of as much as 270 seconds, even though software-assisted calculations are meant to be quicker than human quantifications [27]. Moreover, the use of a total semiquantitative CT score seems difficult to translate to daily practice as the way to calculate the score widely vary throughout the different studies [12,13,19,20,28]. Besides, the cutoffs used to differentiate non severe and severe forms of COVID-19 also vary, depending on the type of score used, the outcome of the study, the type and size of the population, the number of severe cases included [15,17,18,21,29].…”

“…The gold standard for establishing the diagnosis of SARS-CoV-2 infection is based on the biological analysis of respiratory secretions by real-time reverse transcriptase-polymerase chain reaction (RT-PCR) assay. Computed tomography (CT) not only can help make the diagnosis of COVID-19 with greater sensitivity than RT-PCR test [7][8][9][10][11], but has also been used to suggest disease severity or outcome of the disease [12][13][14]. Indeed, some clinical, biological and radiological features are associated with the severity of the disease [15].…”