Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 2 de 2
Epidemiol Infect ; 148: e168, 2020 08 04.
Article in English | MEDLINE | ID: covidwho-1537262


This study aimed to identify clinical features for prognosing mortality risk using machine-learning methods in patients with coronavirus disease 2019 (COVID-19). A retrospective study of the inpatients with COVID-19 admitted from 15 January to 15 March 2020 in Wuhan is reported. The data of symptoms, comorbidity, demographic, vital sign, CT scans results and laboratory test results on admission were collected. Machine-learning methods (Random Forest and XGboost) were used to rank clinical features for mortality risk. Multivariate logistic regression models were applied to identify clinical features with statistical significance. The predictors of mortality were lactate dehydrogenase (LDH), C-reactive protein (CRP) and age based on 500 bootstrapped samples. A multivariate logistic regression model was formed to predict mortality 292 in-sample patients with area under the receiver operating characteristics (AUROC) of 0.9521, which was better than CURB-65 (AUROC of 0.8501) and the machine-learning-based model (AUROC of 0.4530). An out-sample data set of 13 patients was further tested to show our model (AUROC of 0.6061) was also better than CURB-65 (AUROC of 0.4608) and the machine-learning-based model (AUROC of 0.2292). LDH, CRP and age can be used to identify severe patients with COVID-19 on hospital admission.

Coronavirus Infections/mortality , Coronavirus Infections/therapy , Logistic Models , Machine Learning , Pneumonia, Viral/mortality , Pneumonia, Viral/therapy , Adolescent , Adult , Aged , COVID-19 , China/epidemiology , Female , Hospitalization , Humans , Male , Middle Aged , Pandemics , Prognosis , ROC Curve , Reproducibility of Results , Retrospective Studies , Risk Assessment/methods , Young Adult
PLoS One ; 15(7): e0236387, 2020.
Article in English | MEDLINE | ID: covidwho-666013


Population migration and urban traffic are two important aspects of the socioeconomic system. We analyze the trends of social production and resumption of life after the coronavirus disease 2019 (COVID-19)-influenced Spring Festival in 2020 with statistics on reported cases of COVID-19 from China's National Health Commission and big data from Baidu Migration (a platform collecting population migration data). We find that (1) the distribution of COVID-19 cases throughout mainland China has a specific spatial pattern. Provinces in eastern China have more reported cases than those in western China, and provinces adjacent to Hubei have more confirmed COVID-19 cases than nonadjacent provinces. Densely populated regions with well-developed economies and transportation are more likely to have cluster infection incidents. (2) The COVID-19 epidemic severely impacts the return of the migrant population in the Spring Festival travel rush, as demonstrated by the significant reduction in the return scale, along with the extended timespan and uncertainty regarding the end of the travel rush. Among 33 provinces, special administrative regions, autonomous regions and municipalities, 23 of them (approximately 70%) have a return rate below 60%. Hubei, Hong Kong, Xinjiang, and Inner Mongolia have the lowest return rates (below 5%), whereas the return rates in Hainan and Shandong, 272.72% and 97.35%, respectively, indicate the best trend of resumption. Due to government regulations, the population return in densely populated and well-developed regions shows a positive trend. (3) The resumption of urban traffic is slow and varies greatly in different regions. The urban traffic conditions in 22 provinces and municipalities have a more than 60% level of resumption. Guizhou and Yunnan have the highest level of resumption of urban traffic, whereas Xinjiang, Hubei, and Heilongjiang have the lowest (29.37%, 35.76%, and 37.90%, respectively). However, provinces and municipalities with well-developed intercity traffic have a lower level of resumption, mainly because of regulatory methods such as lockdowns and traffic restrictions. The increased public awareness of epidemic prevention and the decreased frequency of outdoor activities are also two positive factors slowing the spread of the epidemic. (4) Time will be necessary to fully resume social production and life throughout China. Xining and Jinan have the highest levels of resumption, 82.14% and 71.51%, respectively. Urumqi and Wuhan are the cities with the lowest levels of resumption, only 0.11% and 0.61%, respectively. Currently, 12 of 33 provinces and municipalities have levels of resumption of more than 80%; among them, Guizhou, Yunnan, and Gansu have with the highest levels of resumption and have nearly resumed the 2019 levels of work and life, whereas Xinjiang and Hubei have the lowest resumption rates, only 0.09% and 7.57%, respectively. Thus, relevant government departments should focus more on densely populated and well-developed provinces and cities when applying epidemic prevention and work resumption methods. We reveal the general conditions of the epidemic and the population return scale across China, along with urban traffic conditions and the resumption of social production and life under COVID-19, providing a scientific basis for local governments to make further decisions on work resumption.

Coronavirus Infections/epidemiology , Pneumonia, Viral/epidemiology , Travel/statistics & numerical data , Automobile Driving , Betacoronavirus , COVID-19 , China/epidemiology , Cities , Human Activities/statistics & numerical data , Humans , Pandemics , SARS-CoV-2 , Spatio-Temporal Analysis