Development and External Evaluation of Predictions Models for Mortality of COVID-19 Patients using Machine Learning Method (preprint)

Background To develop and evaluate the prognostic machine-learning model for mortality in patients with coronavirus disease 2019 (COVID-19).Methods Clinical data of confirmed COVID-19 were retrospectively collected from Wuhan between 18th January and 29th March 2020. Gradient Boosting Decision Tree (GBDT), logistic regression (LR) model, and simplified LR with selected 5 features (LR-5) model were built to predict the mortality of COVID-19. 5-fold area under curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated and compared between models.Results A total of 2,924 patients were included in the final analysis, 257(8.8%) of whom died during hospitalization and 2,667 (91.2%) survived. There were 21(0.7%) mild cases, 2,051(70.1%) moderate case, 779(26.6%) severe cases, and 73(2.5%) critically severe cases of COVID-19 on admission. The overall 5-fold AUC was observed highest in GBDT model (0.941), followed by LR (0.928) and LR-5 (0.913). The diagnostic accuracy were 0.889 in GBDT, 0.868 in LR and 0.887 in LR-5. GBDT model also showed the highest sensitivity (0.899) and speciality (0.889). The NPV of all three models exceeded 97%, while the PPV were relatively low in all models, 0.381 for LR, 0.402 for LR-5 and 0.432 for GBDT. In subgroups analysis with severe cases only, GBDT model also performed the best with a accuracy of 0.799 and 5-fold AUC (0.918).Conclusion The finding revealed that mortality prediction performance of the GBDT was superior to the LR models in confirmed cases of COVID-19, regardless of disease severity.

The residents' mental health status and community's role during COVID-19 epidemic : a community-based cross-sectional study in China (preprint)

BACKGROUND The related research of coronavirus disease 2019 (COVID-19) epidemic on mental health of community residents is still lacking. Here we reported the mental health status of Chinese residents as well as community’s prevention and control during the epidemic period of COVID-19, and further explored the influencing factors of mental status. METHODS In this cross-sectional study, a convenience sampling and snowball sampling methods were adopted from February16 to February 23, 2020 and Chinese community residents were included according to the inclusion and exclusion criteria. Three questionnaires including General Anxiety Disorder 7(GAD-7), Patient Health Questionnaire 9 (PHQ-9), and a self-designed “Community prevention and control questionnaire” were used. A multivariate linear regression analysis was conducted to analyze the impact factors of anxiety and depression. RESULTS A total of 3001 community residents were included in this study. 85.6% and 83.7% of participants had minimal anxiety and depression respectively. 16.6% of participants demonstrated that the communities they lived in had confirmed cases. 95.3% of participants reported that the residents were screened for mobility and contact history. 97.8% of participants reported entrance and exit of community were managed in their communities. 97.5% and 99% of participants were required to take body temperature and wear masks in their communities. 92% communities had their public areas and facilities disinfected every day and 95.4% communities have conducted health education about COVID-19. Factors including gender, education level, chronic illness, the frequency of going out, achieving information about COVID-19 by community and newspaper, and confirmed cases in the community, show association with community residents’ anxiety and depression.                                        CONCLUSIONS the vast majority of Chinese residents have little anxiety and depression, and most communities had adopted standardized control measures in accordance with government’s regulations and policy which plays an important role in the control of COVID-19 and improving residents’ anxiety and depression.