ABSTRACT
Objectives: To develop and validate a radiomics model for distinguishing coronavirus disease 2019 (COVID-19) pneumonia from influenza virus pneumonia. Materials and Methods: A radiomics model was developed on the basis of 56 patients with COVID-19 pneumonia and 90 patients with influenza virus pneumonia in this retrospective study. Radiomics features were extracted from CT images. The radiomics features were reduced by the Max-Relevance and Min-Redundancy algorithm and the least absolute shrinkage and selection operator method. The radiomics model was built using the multivariate backward stepwise logistic regression. A nomogram of the radiomics model was established, and the decision curve showed the clinical usefulness of the radiomics nomogram. Results: The radiomics features, consisting of nine selected features, were significantly different between COVID-19 pneumonia and influenza virus pneumonia in both training and validation data sets. The receiver operator characteristic curve of the radiomics model showed good discrimination in the training sample [area under the receiver operating characteristic curve (AUC), 0.909; 95% confidence interval (CI), 0.859-0.958] and in the validation sample (AUC, 0.911; 95% CI, 0.753-1.000). The nomogram was established and had good calibration. Decision curve analysis showed that the radiomics nomogram was clinically useful. Conclusions: The radiomics model has good performance for distinguishing COVID-19 pneumonia from influenza virus pneumonia and may aid in the diagnosis of COVID-19 pneumonia.
Subject(s)
COVID-19 , Orthomyxoviridae , Humans , Retrospective Studies , SARS-CoV-2 , Tomography, X-Ray ComputedABSTRACT
With the capability of inducing elevated expression of ACE2 (angiotensin-converting enzyme 2), the cellular receptor for severe acute respiratory syndrome coronavirus 2, angiotensin II receptor blockers (ARBs) or ACE inhibitors treatment may have a controversial role in both facilitating virus infection and reducing pathogenic inflammation. We aimed to evaluate the effects of ARBs/ACE inhibitors on coronavirus disease 2019 (COVID-19) in a retrospective, single-center study. One hundred twenty-six patients with COVID-19 and preexisting hypertension at Hubei Provincial Hospital of Traditional Chinese Medicine in Wuhan from January 5 to February 22, 2020, were retrospectively allocated to ARBs/ACE inhibitors group (n=43) and non-ARBs/ACE inhibitors group (n=83) according to their antihypertensive medication. One hundred twenty-five age- and sex-matched patients with COVID-19 without hypertension were randomly selected as nonhypertension controls. In addition, the medication history of 1942 patients with hypertension that were admitted to Hubei Provincial Hospital of Traditional Chinese Medicine from November 1 to December 31, 2019, before the COVID-19 outbreak were also reviewed for external comparison. Epidemiological, demographic, clinical, and laboratory data were collected, analyzed, and compared between these groups. The frequency of ARBs/ACE inhibitors usage in patients with hypertension with or without COVID-19 were comparable. Among patients with COVID-19 and hypertension, those received either ARBs/ACE inhibitors or non-ARBs/ACE inhibitors had comparable blood pressure. However, ARBs/ACE inhibitors group had significantly lower concentrations of hs-CRP (high-sensitivity C-reactive protein; P=0.049) and PCT (procalcitonin, P=0.008). Furthermore, a lower proportion of critical patients (9.3% versus 22.9%; P=0.061) and a lower death rate (4.7% versus 13.3%; P=0.216) were observed in ARBs/ACE inhibitors group than non-ARBs/ACE inhibitors group, although these differences failed to reach statistical significance. Our findings thus support the use of ARBs/ACE inhibitors in patients with COVID-19 and preexisting hypertension.