Improved deep learning model for differentiating novel coronavirus pneumonia and influenza pneumonia

Min Zhou; Yong Chen; Dexiang Wang; Yanping Xu; Weiwu Yao; Jingwen Huang; Xiaoyan Jin; Zilai Pan; Jingwen Tan; Lan Wang; Yihan Xia; Longkuan Zou; Xin Xu; Jingqi Wei; Mingxin Guan; Jianxing Feng; Huan Zhang; Jieming Qu

Currently, SARS-CoV-2 is wildly spreading around the world, efficient and accurate diagnosis of NCP is crucial for prevention and control. Our deep learning model potentially provides an accurate early diagnostic tool for NCP, especially when nucleic acid test kits are short of supply, which is a common problem during outbreaks. This could help reduce the missed diagnosis rate and diagnosis time, ensure prompt patient isolation and early treatment, improve prognosis and largely prevent transmission. The high efficiency of our model to differentiate NCP and IP could be very beneficial to reduce misdiagnosis rate and optimize the allocation of medical resources, particularly in areas with high prevalence of both NCP and IP.