RESUMEN
PURPOSE: The coronavirus disease 2019 (COVID-19) has evolved into a worldwide pandemic. CT although sensitive in detecting changes suffers from poor specificity in discrimination from other causes of ground glass opacities (GGOs). We aimed to develop and validate a CT-based radiomics model to differentiate COVID-19 from other causes of pulmonary GGOs. METHODS: We retrospectively included COVID-19 patients between 24/01/2020 and 31/03/2020 as case group and patients with pulmonary GGOs between 04/02/2012 and 31/03/2020 as a control group. Radiomics features were extracted from contoured GGOs by PyRadiomics. The least absolute shrinkage and selection operator method was used to establish the radiomics model. We assessed the performance using the area under the curve of the receiver operating characteristic curve (AUC). RESULTS: A total of 301 patients (age mean⯱â¯SD: 64⯱â¯15 years; male: 52.8 %) from three hospitals were enrolled, including 33 COVID-19 patients in the case group and 268 patients with malignancies or pneumonia in the control group. Thirteen radiomics features out of 474 were selected to build the model. This model achieved an AUC of 0.905, accuracy of 89.5 %, sensitivity of 83.3 %, specificity of 90.0 % in the testing set. CONCLUSION: We developed a noninvasive radiomics model based on CT imaging for the diagnosis of COVID-19 based on GGO lesions, which could be a promising supplementary tool for improving specificity for COVID-19 in a population confounded by ground glass opacity changes from other etiologies.
RESUMEN
BACKGROUND: Respiratory virus-laden particles are commonly detected in the exhaled breath of symptomatic patients or in air sampled from healthcare settings. However, the temporal relationship of detecting virus-laden particles at nonhealthcare locations vs surveillance data obtained by conventional means has not been fully assessed. METHODS: From October 2016 to June 2018, air was sampled weekly from a university campus in Hong Kong. Viral genomes were detected and quantified by real-time reverse-transcription polymerase chain reaction. Logistic regression models were fitted to examine the adjusted odds ratios (aORs) of ecological and environmental factors associated with the detection of virus-laden airborne particles. RESULTS: Influenza A (16.9% [117/694]) and influenza B (4.5% [31/694]) viruses were detected at higher frequencies in air than rhinovirus (2.2% [6/270]), respiratory syncytial virus (0.4% [1/270]), or human coronaviruses (0% [0/270]). Multivariate analyses showed that increased crowdedness (aOR, 2.3 [95% confidence interval {CI}, 1.5-3.8]; P < .001) and higher indoor temperature (aOR, 1.2 [95% CI, 1.1-1.3]; P < .001) were associated with detection of influenza airborne particles, but absolute humidity was not (aOR, 0.9 [95% CI, .7-1.1]; P = .213). Higher copies of influenza viral genome were detected from airborne particles >4 µm in spring and <1 µm in autumn. Influenza A(H3N2) and influenza B viruses that caused epidemics during the study period were detected in air prior to observing increased influenza activities in the community. CONCLUSIONS: Air sampling as a surveillance tool for monitoring influenza activity at public locations may provide early detection signals on influenza viruses that circulate in the community.