COVID-19 early warning score: a multi-parameter screening tool to identify highly suspected patients

Cong-Ying Song; Jia Xu; Jian-Qin He; Yuan-Qiang Lu

We included clinical data of a total of 1,311 patients who came to the First Affiliated Hospital, School of Medicine, Zhejiang University and performed at least once SARS-CoV-2 nucleicacid detection for analysis. This study was approved by the Ethical Committee of the First Affiliated Hospital, School of Medicine, Zhejiang University (code number IIT20200025A). Data of patients between January 20 th , 2020 and February 5 th , 2020 were enrolled into training dataset, and between February 6 th , 2020 and February 19 th , 2020 were enrolled into validate dataset. All patients who had a positive SARS-CoV-2 nucleicacid detection result were classified into COVID-19 group, while the others were classified into non-COVID-19 group. Due to the huge number of non-COVID-19 group patients, we eliminated the enrolled patients according to the following steps: (1) all negative patients from the COVID-19 designated district, Zhijiang District of the First Affiliated Hospital of Zhejiang University School of Medicine; (2) negative outpatients from Qingchun District were sorted by "Z-A" based on Chinese first name, the first 60% between January 20 th , 2020 and February 5 th , 2020, and the first 40% between February 6 th , 2020 and February 19 th , 2020 were included. Exclusion criteria: (1) asymptomatic patients without history of exposure but had strong willingness for detection;