Predictive performance of CT for adverse outcomes among COVID-19 suspected patients: a two-center retrospective study

To compare the performance of various CT reporting tools, including Zonal CT Visual Score (ZCVS), the number of involved lobes, and Radiological Society of North America (RSNA) categorization in predicting adverse outcomes among patients hospitalized due to lower respiratory symptoms during the COVID-19 pandemic. A total of 405 patients admitted with severe respiratory symptoms who underwent a chest CT were enrolled. The primary adverse outcome was ICU admission of patients. Predictive performances of reporting tools were compared using the area under the receiver operating characteristic curves (AUC ROC). Among the 405 patients, 39 (9.63%) required ICU support during their hospital stay. At least two or more observers reported a typical and indeterminate COVID-19 pneumonia CT pattern according to RSNA categorization in 70% (285/405) of patients. Among these, 63% (179/285) had a positive PCR test for the SARS-CoV-2 virus. The median number of lobes involved according to CT was higher in patients who required ICU support (median [IQR], 5[3; 5] vs. 3[0; 5]). The median ZCVS score was higher among the patients that subsequently required ICU support (median [IQR], 4[0; 12] vs. 13[5.75; 24]). The bootstrap comparisons of AUC ROC showed significant differences between reporting tools, and the ZCVS was found to be superior (AUC ROC, 71 to 75 %). The ZCVS score at the first admission showed a linear and significant association with adverse outcomes among patients with lower respiratory tract symptoms during the COVID-19 pandemic.