Rapid and accurate identification of COVID-19 infection through machine learning based on clinical available blood test results

Jiangpeng Wu; Pengyi Zhang; Liting Zhang; Wenbo Meng; Junfeng Li; Chongxiang Tong; Yonghong Li; Jing Cai; Zengwei Yang; Jinhong Zhu; Meie Zhao; Huirong Huang; Xiaodong Xie; Shuyan Li

After the construction of the assistant discrimination tool was completed, there are some confirmed COVID-19 cases that were imported from outside of China and were received in Gansu Province. In order to make an in-depth assessment for the built tool, 24 samples of 14 patients from Lanzhou Pulmonary Hospital were collected when first performed the routine laboratory blood tests, including 2 routine hematological parameters and 9 biochemical parameters. The prediction results were shown in Figure 5 . 22 of 24 samples were accurately identified through using our designed web server with an . CC-BY-NC-ND 4.0 International license It is made available under a is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity.