ABSTRACT
Since December 2019, the world has witnessed the stringent effect of an unprecedented global pandemic, coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). As of January 29,2021, there have been 100,819,363 confirmed cases and 2,176,159 deaths reported. Among the countries affected severely by COVID-19, the United States tops the list. Research has been conducted to discuss the causal associations between explanatory factors and COVID-19 transmission in the contiguous United States. However, most of these studies focus more on spatial associations of the estimated parameters, yet exploring the time-varying dimension in spatial econometric modeling appears to be utmost essential. This research adopts various relevant approaches to explore the potential effects of driving factors on COVID-19 counts in the contiguous United States. A total of three global spatial regression models and two local spatial regression models, the latter including geographically weighted regression (GWR) and multiscale GWR (MGWR), are performed at the county scale to take into account the scale effects. For COVID-19 cases, ethnicity, crime, and income factors are found to be the strongest covariates and explain most of the variance of the modeling estimation. For COVID-19 deaths, migration (domestic and international) and income factors play a critical role in explaining spatial differences of COVID-19 deaths across counties. Such associations also exhibit temporal variations from March to July, as supported by better performance of MGWR than GWR. Both global and local associations among the parameters vary highly over space and change across time. Therefore, time dimension should be paid more attention to in the spatial epidemiological analysis. Among the two local spatial regression models, MGWR performs more accurately, as it has slightly higher Adj. R2 values (for cases, R2â¯=â¯0.961; for deaths, R2â¯=â¯0.962), compared to GWR's Adj. R2 values (for cases, R2â¯=â¯0.954; for deaths, R2â¯=â¯0.954). To inform policy-makers at the nation and state levels, understanding the place-based characteristics of the explanatory forces and related spatial patterns of the driving factors is of paramount importance. Since it is not the first time humans are facing public health emergency, the findings of the present research on COVID-19 therefore can be used as a reference for policy designing and effective decision making.
ABSTRACT
Coronavirus disease, a novel severe acute respiratory syndrome (SARS COVID-19), has become a global health concern due to its unpredictable nature and lack of adequate medicines. Machine Learning (ML) models could be effective in identifying the most critical factors which are responsible for the overall fatalities caused by COVID-19. The functional capabilities of ML models in epidemiological research, especially for COVID-19, are not substantially explored. To bridge this gap, this study has adopted two advanced ML models, viz. Random Forest (RF) and Gradient Boosted Machine (GBM), to perform the regression modelling and provide subsequent interpretation. Five successive steps were followed to carry out the analysis: (1) identification of relevant key explanatory variables; (2) application of data dimensionality reduction for eliminating redundant information; (3) utilizing ML models for measuring relative influence (RI) of the explanatory variables; (4) evaluating interconnections between and among the key explanatory variables and COVID-19 case and death counts; (5) time series analysis for examining the rate of incidences of COVID-19 cases and deaths. Among the explanatory variables considered in this study, air pollution, migration, economy, and demographic factor were found to be the most significant controlling factors. Since a very limited research is available to discuss the superiority of ML models for identifying the key determinants of COVID-19, this study could be a reference for future public health research. Additionally, all the models and data used in this study are open source and freely available, thereby, reproducibility and scientific replication will be achievable easily.
