AUTHOR=Yu Lan , Shi Xiaoli , Liu Xiaoling , Jin Wen , Jia Xiaoqing , Xi Shuxue , Wang Ailan , Li Tianbao , Zhang Xiao , Tian Geng , Sun Dejun 

TITLE=Artificial Intelligence Systems for Diagnosis and Clinical Classification of COVID-19

JOURNAL=Frontiers in Microbiology

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2021.729455

DOI=10.3389/fmicb.2021.729455

ISSN=1664-302X

ABSTRACT=Objectives: COVID-19 is highly infectious and has been widely spread worldwide, with more than 159 million confirmed cases and more than 3 million deaths as by May11th, 2021. It has become a serious public health event threatening people's lives and safety. Due to the rapid transmission and long incubation period, shortage of medical resources would easily occur in the short term of discovering disease cases. Therefore, we aimed to construct an artificial intelligent framework to rapidly distinguish patients with COVID-19 from common pneumonia and non-pneumonia population based on CT images. Furthermore, we explored artificial intelligence algorithms to integrate CT features and laboratory findings on admission to predict the clinical classification of COVID-19. This will ease the burden of doctors in emergency period and aid them to perform appropriate treatment to patients timely.
Methods: We collected all CT images and clinical data of novel coronavirus pneumonia cases in Inner Mongolia, including domestic and imported from abroad, and developed three models based on transfer learning to distinguish COVID-19 from other pneumonia and non-pneumonia population. In addition, CT features and laboratory findings on admission were combined to predict clinical types of COVID-19 using artificial intelligence algorithms and Spearman’s correlation test was applied to study correlations of CT characteristics and laboratory findings.
Results: Among three models to distinguish COVID-19 based on CT, vgg19 showed excellent diagnostic performance, with AUC of the ROC curve 95%. And together with laboratory findings, we were able to predict clinical types of COVID-19 with AUC of the ROC curve 90%. Furthermore, biochemical markers such as CRP, LYM and LDH were identified correlated with CT features.
Conclusions: We developed an artificial intelligent model to identify patients who were positive for COVID-19 according to the results of the first CT examination after admission and predict the progression combined with laboratory findings. In addition, we obtained important clinical characteristics that correlated with the CT image features. Together, our AI system could rapidly diagnose COVID-19 and predict clinical types to assist clinicians perform appropriate clinical management.