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
Open Forum Infect Dis ; 7(7): ofaa283, 2020 Jul.
Article in English | MEDLINE | ID: covidwho-846713


BACKGROUND: Clinical manifestation and neonatal outcomes of pregnant women with coronavirus disease 2019 (COVID-19) were unclear in Wuhan, China. METHODS: We retrospectively analyzed clinical characteristics of pregnant and nonpregnant women with COVID-19 aged from 20 to 40, admitted between January 15 and March 15, 2020 at Union Hospital, Wuhan, and symptoms of pregnant women with COVID-19 and compared the clinical characteristics and symptoms to historic data previously reported for H1N1. RESULTS: Among 64 patients, 34 (53.13%) were pregnant, with higher proportion of exposure history (29.41% vs 6.67%) and more pulmonary infiltration on computed tomography test (50% vs 10%) compared to nonpregnant women. Of pregnant patients, 27 (79.41%) completed pregnancy, 5 (14.71%) had natural delivery, 18 (52.94%) had cesarean section, and 4 (11.76%) had abortion; 5 (14.71%) patients were asymptomatic. All 23 newborns had negative reverse-transcription polymerase chain results, and an average 1-minute Apgar score was 8-9 points. Pregnant and nonpregnant patients show differences in symptoms such as fever, expectoration, and fatigue and on laboratory tests such as neurophils, fibrinogen, D-dimer, and erythrocyte sedimentation rate. Pregnant patients with COVID-19 tend to have more milder symptoms than those with H1N1. CONCLUSIONS: Clinical characteristics of pregnant patients with COVID-19 are less serious than nonpregnant. No evidence indicated that pregnant women may have fetal infection through vertical transmission of COVID-19. Pregnant patients with H1N1 had more serious condition than those with COVID-19.