ABSTRACT
Background: Considering the current situation of the novel coronavirus disease (COVID-19) epidemic control, it is highly likely that COVID-19 and influenza may coincide during the approaching winter season. However, there is no available tool that can rapidly and precisely distinguish between these two diseases in the absence of laboratory evidence of specific pathogens. Methods: Laboratory confirmed COVID-19 and influenza patients from Zhongnan Hospital of Wuhan University (ZHWU) and Wuhan No.1 Hospital (WNH) between December 1, 2019 and February 29, 2020, were included for analysis. A machine learning-based decision model was developed using the XGBoost algorithms. The specificity, sensitivity, positive and negative predictive values (PPV/NPV), accuracy and area under the receiver operating characteristic curve (AUC) were calculated to evaluate the model performance. Findings: The data from 357 COVID-19 and 1893 influenza patients from ZHWU were divided into a training and a testing set in the ratio 7:3. The external test used the data of 308 COVID-19 and 312 influenza patients from WNH. In the training and testing sets, the model achieved good performance in identifying COVID-19 from influenza with an accuracy of 0.968 (AUC, 0.943 (95%CI 0.925, 0.962)) and 0.960 (AUC, 0.928 (95%CI 0.897, 0.959)), respectively. Our decision tree suggested that older age (>16 years), higher hsCRP (>14.2 mg/L) and lower monocyte (≤0.68×109/L) drive the prediction towards COVID-19. In addition, the external test determined a COVID-19 prediction accuracy of 0.839 (AUC, 0.839 (95%CI: 0.811, 0.868). Interpretation: Machine learning provides a tool that can rapidly and accurately distinguish between COVID-19 and influenza cases. This finding would be particularly useful in regions having massive COVID-19 and influenza cases while limited resources for laboratory test of specific pathogens. Funding: National Natural Science Foundation of China (81900097) and the Emergency Response Project of Hubei Science and Technology Department (2020FCA002, 2020FCA023).Declaration of Interests: None reported.Ethics Approval Statement: This study was approved by the Medical Ethics Committee, Zhongnan Hospital of Wuhan University (Clinical Ethical Approval No. 2020020).
Subject(s)
COVID-19ABSTRACT
Background Since the outbreak of COVID-19, the application of appropriate treatment strategy for COVID-19 patients, notably for the severe patients, was a huge challenge in case management. Therefore, we aimed to evaluate the effectiveness of antiviral treatment in severe COVID-19 patients.Methods A retrospective cohort study was conducted from January 8, 2020 to March 9, 2020 in four designated hospitals of COVID-19 in Wuhan, China. 138 severe COVID-19patients with above 18 years were included in this study. 109 patients receiving the antiviral treatment were selected in antiviral group. The remaining 29 patients were in control group. The primary outcome of the study was in-hospital death and length of hospitalization. Secondary outcomes included ICU admission, length of stays in ICU, use of mechanical ventilation, length of mechanical ventilation, and the development of complications. Univariate analysis and Kaplan-Meier curves were used to examined the association between antiviral treatment and the clinical outcomes of the COVID-19 patients.Results 48 (44.0%) and 15 (51.7%) deaths were occurred in antiviral and control groups, respectively. Antiviral treatment was not associated with the rate of fatal outcome in COVID-19 patients (P > 0.05). Among the survival patients, the median length of hospitalization was 11.0 days (IQR: 6.5–18.0) and 16.0 days (IQR: 8.5–26.0) in antiviral and control groups, respectively. No significant association was identified between the antiviral treatment and the length of hospitalization in survival patients (P > 0.05). Moreover, the antiviral treatment was not statistically associated with ICU admission, mechanical ventilation and length of mechanical ventilation (P > 0.05, respectively). However, the length of ICU stays in deaths was different both groups (P < 0.05). The median length of ICU stays in deaths was 7.0 days (IQR: 3.0-14.3) and 15.5 days (IQR: 8.3–21.8) in antiviral and control groups, respectively. The occurrence of majority of complications were similar both groups. Sepsis was the single complication in which the occurrence rates were statistical different between the antiviral group and control group (40.4% vs 13.8%, P < 0.01).Conclusion No benefit of antiviral treatment in severe COVID-19 patients was observed in our study. Clinical physicians should cautiously prescribe the antiviral drugs in severe COVID-19 patients.
Subject(s)
COVID-19 , Sepsis , DeathABSTRACT
Understanding the epidemiological and clinical characteristics of fatal cases infected with SARS-CoV-2 is import to develop appropriate preventable intervention programs in hospitals. Demographic data, clinical symptoms, clinical course, co-morbidities, laboratory findings, CT scans, treatments and complications of 162 fatal cases were retrieved from electric medical records in 5 hospitals of Wuhan, China. The median age was 69.5 years old (IQR: 63.0-77.25; range: 29-96). 112 (69.1%) cases were men. Hypertension (45.1%) was the most common co-morbidity, but 59 (36.4%) cases had no co-morbidity. At admission, 131 (81.9%) cases were assessed as severe or critical. However, 39 (18.1%) were assessed as moderate. Moderate cases had a higher prevalence of hypertension and chronic lung disease comparing with severe or critical cases (P<0.05, respectively). 126 (77.8%) and 132 (81.5%) cases received antiviral treatment and glucocorticoids, respectively. 116 (71.6%) cases were admitted to ICU and 137 (85.1%) cases received mechanical ventilation. Respiratory failure or acute respiratory distress syndrome (93.2%) was the most common complication. The young cases of COVID-19, without co-morbidity and in a moderate condition at admission could develop fatal outcome. We need to be more cautious in case management of COVID-19 for preventing the fatal outcomes.