 This study proposes a three-dimensional convolutional neural network, 3DCNN, to accurately classify CT scans of patients with COVID-19, influenza community acquired pneumonia, CAP, and no infection. The model was trained and validated on retrospective data of 667 adult patients, no infection N equals 188, COVID-19 N equals 230, influenza CAP N equals 249, and 210 adult patients, no infection N equals 70, COVID-19 N equals 70, influenza CAP N equals 70, respectively. The model's performance was independently evaluated on an internal test set of 273 adult patients, no infection N equals 55, COVID-19 N equals 94, influenza CAP N equals 124, and an external validation set from a different center, 305 adult patients, COVID-19 N equals 169, no infection N equals 76, influenza CAP N equals 60. The model showed excellent performance in the external validation set with an area under the curve, AUC, of zero. This article was authored by Akshaya Vaidyanathan, Julian Guyat, Fadila Sarka, and others. We are article.tv, links in the description below.