A diagnostic model for coronavirus disease 2019 (COVID-19) based on radiological semantic and clinical features: a multi-center study

We aim to identify differences in CT imaging and clinical manifestations between pneumonia patients with and without COVID19, and to develop and validate a diagnostic model for COVID-19 based on radiological semantic and clinical features alone

Xiaofeng Chen

2020

Scholarcy highlights

  • On January 30, 2020, the World Health Organization has declared the severe acute respiratory syndrome coronavirus 2 outbreak as a global health emergency of international concern
  • A diagnostic model for COVID-19 was developed and validated using radiological semantic and clinical features, which had an area under the curve value of 0.986 and 0.936 in the primary and validation cohorts, respectively
  • To develop an optimal model, we evaluated 3 models by analyzing the clinical features model, radiological semantic features model, and the combination of clinical and radiological semantic features model by multivariate logistic regression analysis
  • C, R, and CR indicate the predicted model based on clinical features, radiological features, and the combination of clinical features and clinical radiological features, respectively
  • To determine the clinical usefulness of the diagnostic model, we developed the decision curve, which showed better performances for the CR model compared with that for the C model and the R model
  • By comparing the “total points” scale and the “probability” scale, the individual probability of COVID-19 infection could be obtained. In this multi-center study, statistical analysis was performed in comparing imaging and clinical manifestations between pneumonia patients with and without COVID-19
  • Electronic supplementary material The online version of this article contains supplementary material, which is available to authorized users

Need more features? Save interactive summary cards to your Scholarcy Library.