Relationship between Socio-Demographics and COVID-19: A Case Study in Three Texas Regions
TL;DR: The COVID-19 is a global pandemic and crisis of public health as mentioned in this paper, and most of the studies are based on the macro factors of the COVID19 pandemic.
Abstract: The COVID-19 is a global pandemic and crisis of public health Although studies investigate the spatial factors of COVID-19, most of them are based on the macro
Citations
More filters
TL;DR: This review presents a comprehensive analysis of the use of AI techniques for spatio-temporal modeling and forecasting and impact modeling on diverse populations as it relates to COVID-19 and lists potential paths of research for which AI based techniques can be used for greater impact in tackling the pandemic.
Abstract: The COVID-19 pandemic, within a short time span, has had a significant impact on every aspect of life in almost every country on the planet. As it evolved from a local epidemic isolated to certain regions of China, to the deadliest pandemic since the influenza outbreak of 1918, scientists all over the world have only amplified their efforts to combat it. In that battle, Artificial Intelligence, or AI, with its wide ranging capabilities and versatility, has played a vital role and thus has had a sizable impact. In this review, we present a comprehensive analysis of the use of AI techniques for spatio-temporal modeling and forecasting and impact modeling on diverse populations as it relates to COVID-19. Furthermore, we catalogue the articles in these areas based on spatio-temporal modeling, intrinsic parameters, extrinsic parameters, dynamic parameters and multivariate inputs (to ascertain the penetration of AI usage in each sub area). The manner in which AI is used and the associated techniques utilized vary for each body of work. Majority of articles use deep learning models, compartment models, stochastic methods and numerous statistical methods. We conclude by listing potential paths of research for which AI based techniques can be used for greater impact in tackling the pandemic.
8 citations
TL;DR: In this paper , the authors identify spatiotemporal clusters and the socioeconomic drivers of COVID-19 in Toronto using Moran's I, and space-time scan statistic to identify spatial and spatio-temporal clusters.
2 citations
TL;DR: In this paper , a Bayesian hierarchical spatio-temporal model that incorporates satellite-derived remote sensing data on land surface temperature (LST) from January 2020 to October 2021 (89 weeks) and several socioeconomic covariates of the 140 neighbourhoods in Toronto was used to predict COVID-19 risk at a spatial scale.
Abstract: Spatiotemporal patterns and trends of COVID-19 at a local spatial scale using Bayesian approaches are hardly observed in literature. Also, studies rarely use satellite-derived long time-series data on the environment to predict COVID-19 risk at a spatial scale. In this study, we modelled the COVID-19 pandemic risk using a Bayesian hierarchical spatiotemporal model that incorporates satellite-derived remote sensing data on land surface temperature (LST) from January 2020 to October 2021 (89 weeks) and several socioeconomic covariates of the 140 neighbourhoods in Toronto. The spatial patterns of risk were heterogeneous in space with multiple high-risk neighbourhoods in Western and Southern Toronto. Higher risk was observed during Spring 2021. The spatiotemporal risk patterns identified 60% of neighbourhoods had a stable, 37% had an increasing, and 2% had a decreasing trend over the study period. LST was positively, and higher education was negatively associated with the COVID-19 incidence. We believe the use of Bayesian spatial modelling and the remote sensing technologies in this study provided a strong versatility and strengthened our analysis in identifying the spatial risk of COVID-19. The findings would help in prevention planning, and the framework of this study may be replicated in other highly transmissible infectious diseases.
1 citations
TL;DR: In this article , the authors used multiscale geographically weighted regression (MGWR) to identify the spatially heterogeneous relationship between COVID-19 vaccination rates and socioeconomic factors in England.
Abstract: Abstract Background Mass vaccination has been a key strategy in effectively containing global COVID-19 pandemic that posed unprecedented social and economic challenges to many countries. However, vaccination rates vary across space and socio-economic factors, and are likely to depend on the accessibility to vaccination services, which is under-researched in literature. This study aims to empirically identify the spatially heterogeneous relationship between COVID-19 vaccination rates and socio-economic factors in England. Methods We investigated the percentage of over-18 fully vaccinated people at the small-area level across England up to 18 November 2021. We used multiscale geographically weighted regression (MGWR) to model the spatially heterogeneous relationship between vaccination rates and socio-economic determinants, including ethnic, age, economic, and accessibility factors. Results This study indicates that the selected MGWR model can explain 83.2% of the total variance of vaccination rates. The variables exhibiting a positive association with vaccination rates in most areas include proportion of population over 40, car ownership, average household income, and spatial accessibility to vaccination. In contrast, population under 40, less deprived population, and black or mixed ethnicity are negatively associated with the vaccination rates. Conclusions Our findings indicate the importance of improving the spatial accessibility to vaccinations in developing regions and among specific population groups in order to promote COVID-19 vaccination.