Zhang Q, Chen Z, Liu G, et al. - Because of the difficulty to perform RT-PCR tests in real time, the lack of experienced radiologists, clinical low-quality images, and the similarity of imaging features of community-acquired pneumonia and COVID-19, difficulties are encountered in the clinical diagnosis of COVID-19 pneumonia. Hence, an artificial intelligence model GARCD that uses chest CT images has been proposed here to assist in the diagnosis of COVID-19 in real time. Better diagnostic performance can be achieved using this model even when facing low-quality CT images. Of 14,129 CT images acquired from 104 patients, they used 12,929 samples to build artificial intelligence models, and 1200 samples to test its performance. Per findings, the proposed method appeared to be effective in assisting doctors in real-time detection of suspected cases of COVID-19 pneumonia even facing unclear images. It can allow quick isolation of patients in a targeted manner, which is of positive significance for averting the further spread of COVID-19 pneumonia.