JMIR Medical Informatics (Sep 2020)

Nomogram for Predicting COVID-19 Disease Progression Based on Single-Center Data: Observational Study and Model Development

  • Fan, Tao,
  • Hao, Bo,
  • Yang, Shuo,
  • Shen, Bo,
  • Huang, Zhixin,
  • Lu, Zilong,
  • Xiong, Rui,
  • Shen, Xiaokang,
  • Jiang, Wenyang,
  • Zhang, Lin,
  • Li, Donghang,
  • He, Ruyuan,
  • Meng, Heng,
  • Lin, Weichen,
  • Feng, Haojie,
  • Geng, Qing

Journal volume & issue
Vol. 8, no. 9
p. e19588


Read online

BackgroundIn late December 2019, a pneumonia caused by SARS-CoV-2 was first reported in Wuhan and spread worldwide rapidly. Currently, no specific medicine is available to treat infection with COVID-19. ObjectiveThe aims of this study were to summarize the epidemiological and clinical characteristics of 175 patients with SARS-CoV-2 infection who were hospitalized in Renmin Hospital of Wuhan University from January 1 to January 31, 2020, and to establish a tool to identify potential critical patients with COVID-19 and help clinical physicians prevent progression of this disease. MethodsIn this retrospective study, clinical characteristics of 175 confirmed COVID-19 cases were collected and analyzed. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to select variables. Multivariate analysis was applied to identify independent risk factors in COVID-19 progression. We established a nomogram to evaluate the probability of progression of the condition of a patient with COVID-19 to severe within three weeks of disease onset. The nomogram was verified using calibration curves and receiver operating characteristic curves. ResultsA total of 18 variables were considered to be risk factors after the univariate regression analysis of the laboratory parameters (P<.05), and LASSO regression analysis screened out 10 risk factors for further study. The six independent risk factors revealed by multivariate Cox regression were age (OR 1.035, 95% CI 1.017-1.054; P<.001), CK level (OR 1.002, 95% CI 1.0003-1.0039; P=.02), CD4 count (OR 0.995, 95% CI 0.992-0.998; P=.002), CD8 % (OR 1.007, 95% CI 1.004-1.012, P<.001), CD8 count (OR 0.881, 95% CI 0.835-0.931; P<.001), and C3 count (OR 6.93, 95% CI 1.945-24.691; P=.003). The areas under the curve of the prediction model for 0.5-week, 1-week, 2-week and 3-week nonsevere probability were 0.721, 0.742, 0.87, and 0.832, respectively. The calibration curves showed that the model had good prediction ability within three weeks of disease onset. ConclusionsThis study presents a predictive nomogram of critical patients with COVID-19 based on LASSO and Cox regression analysis. Clinical use of the nomogram may enable timely detection of potential critical patients with COVID-19 and instruct clinicians to administer early intervention to these patients to prevent the disease from worsening.