ABSTRACT
Since the sudden outbreak of coronavirus disease 2019 (COVID-19), it has rapidly evolved into a momentous global health concern. Due to the lack of constructive information on the pathogenesis of COVID-19 and specific treatment, it highlights the importance of early diagnosis and timely treatment. In this study, 11 key blood indices were extracted through random forest algorithm to build the final assistant discrimination tool from 49 clinical available blood test data which were derived by commercial blood test equipments. The method presented robust outcome to accurately identify COVID-19 from a variety of suspected patients with similar CT information or similar symptoms, with accuracy of 0.9795 and 0.9697 for the cross-validation set and test set, respectively. The tool also demonstrated its outstanding performance on an external validation set that was completely independent of the modeling process, with sensitivity, specificity, and overall accuracy of 0.9512, 0.9697, and 0.9595, respectively. Besides, 24 samples from overseas infected patients with COVID-19 were used to make an in-depth clinical assessment with accuracy of 0.9167. After multiple verification, the reliability and repeatability of the tool has been fully evaluated, and it has the potential to develop into an emerging technology to identify COVID-19 and lower the burden of global public health. The proposed tool is well-suited to carry out preliminary assessment of suspected patients and help them to get timely treatment and quarantine suggestion. The assistant tool is now available online at http://lishuyan.lzu.edu.cn/COVID2019_2/. FundingThis work was supported by the Fundamental Research Funds for the Central Universities (lzujbky-2020-sp11) and the Gansu Provincial COVID-19 Science and Technology Major Project, China.
ABSTRACT
To understand pathogen spectrum of nontuberculosis Mycobacteria (NTM) and the dominant NTM in Gansu Province and provide the scientific basis for the effective prevention and treatment of NTM diseases,875 Mycobacteria isolates were collected from 2012 to 2014 in Lanzhou Pulmonary Hospital,NTM species were identified by means of PNB/TCH differentiate medium and 16S rRNA gene sequence analysis respectively.Forty-six isolats of NTM were identied from 875 PNB/TCH.Then with 16S rRNA gene sequence analysis,the NTM strains were identified to 3 strains of Nocadia and 43 strains of NTM,including M.intracellulare,M.kansasii,M.avium,M.senegalense,M.gordonae,M.szulgai,M.peregrinumand M.fortuitum.Among them,there were 31 strains of M.intracellulare,which accounted for 72.09% of the total number of NTM strains.The dominant nontuberculosis Mycobacteria in Gansu Province were mainly M.intracellulare.The application of molecular biology can rapidly and accurately identify the species of nontuberculosis Mycobacteria,and can provide relevant evidence for clinical diagnosis and therapy.