Accuracy comparison of ARIMA and XGBoost forecasting models in predicting the incidence of COVID-19 in Bangladesh.

Accurate predictive time series modelling is important in public health planning and response during the emergence of a novel pandemic. Therefore, the aims of the study are three-fold: (a) to model the overall trend of COVID-19 confirmed cases and deaths in Bangladesh; (b) to generate a short-term forecast of 8 weeks of COVID-19 cases and deaths; (c) to compare the predictive accuracy of the Autoregressive Integrated Moving Average (ARIMA) and eXtreme Gradient Boosting (XGBoost) for precise modelling of non-linear features and seasonal trends of the time series. The data were collected from the onset of the epidemic in Bangladesh from the Directorate General of Health Service (DGHS) and Institute of Epidemiology, Disease Control and Research (IEDCR). The daily confirmed cases and deaths of COVID-19 of 633 days in Bangladesh were divided into several training and test sets. The ARIMA and XGBoost models were established using those training data, and the test sets were used to evaluate each model's ability to forecast and finally averaged all the predictive performances to choose the best model. The predictive accuracy of the models was assessed using the mean absolute error (MAE), mean percentage error (MPE), root mean square error (RMSE) and mean absolute percentage error (MAPE). The findings reveal the existence of a nonlinear trend and weekly seasonality in the dataset. The average error measures of the ARIMA model for both COVID-19 confirmed cases and deaths were lower than XGBoost model. Hence, in our study, the ARIMA model performed better than the XGBoost model in predicting COVID-19 confirmed cases and deaths in Bangladesh. The suggested prediction model might play a critical role in estimating the spread of a novel pandemic in Bangladesh and similar countries.

Climate change and dengue fever knowledge, attitudes and practices in Bangladesh: a social media-based cross-sectional survey.

BACKGROUND: Bangladesh experienced its worst dengue fever (DF) outbreak in 2019. This study investigated the knowledge, attitudes and practices (KAP) among university students in Bangladesh and significant factors associated with their prevention practices related to climate change and DF. METHODS: A social media-based (Facebook) cross-sectional KAP survey was conducted and secondary data of reported DF cases in 2019 extracted. Logistic regression and spatial analysis were run to examine the data. RESULTS: Of 1500 respondents, 76% believed that climate change can affect DF transmission. However, participants reported good climate change knowledge (76.7%), attitudes (87.9%) and practices (39.1%). The corresponding figures for DF were knowledge (47.9%), attitudes (80.3%) and practices (25.9%). Good knowledge and attitudes were significantly associated with good climate change adaptation or mitigation practices (p<0.05). Good knowledge, attitudes and previous DF experiences were also found to be significantly associated with good DF prevention practices (p<0.001). There was no significant positive correlation between climate change and DF KAP scores and the number of DF cases. CONCLUSIONS: Findings from this study provide baseline data that can be used to promote educational campaigns and intervention programs focusing on climate change adaptation and mitigation and effective DF prevention strategies among various communities in Bangladesh and similar dengue-endemic countries.

COVID-19 Epidemic in Bangladesh among Rural and Urban Residents: An Online Cross-Sectional Survey of Knowledge, Attitudes, and Practices.

As other nations around the world, Bangladesh is facing enormous challenges with the novel coronavirus (COVID-19) epidemic. To design a prevention and control strategy for this new infectious disease, it is essential to first understand people's knowledge, attitudes, and practices (KAP) regarding COVID-19. This study sought to determine KAP among rural and urban residents as well as predictors of preventive practices associated with COVID-19 in Bangladesh. A social media-based (Facebook) cross-sectional survey was conducted to explore these variables among Bangladeshi adults. Of 1520 respondents who completed the questionnaire, low level of good or sufficient knowledge of COVID-19 (70.8%) and practices associated with COVID-19 (73.8%) were found. Despite the low level of knowledge and practices, respondents' attitude (78.9%) towards COVID-19 was relatively high. Results suggest that compared to urban, rural residents are at a particularly high risk of COVID-19 because they were found to have significantly lower knowledge (p = 0.001) and practice levels (p = 0.002) than were urban residents. Multivariable logistic regression analysis identified gender, education, knowledge of COVID-19 transmission, signs and symptoms, and sources of information as factors significantly associated with preventive practices against COVID-19. Further attention and effort should be directed toward increasing both knowledge and practices targeting the general population in Bangladesh, particularly the rural and less educated residents. Findings from this study provide baseline data that can be used to promote integrated awareness of and effective health education programs about COVID-19 prevention and control strategies in Bangladesh, and similar COVID-19 endemic countries.