An analysis of the impact of policies and political affiliation on racial disparities in COVID-19 infections and deaths in the USA

Abstract

This research aimed to quantify the racial disparities of COVID-19 for primarily positive tests and deaths across the US and territories individually and collectively. The first research hypothesis investigated whether positive cases and death rates were higher for people of color (POC) than the White ethnic group. The second hypothesis examined whether there is a significant difference in confirmed positive cases and death rates between ethnic groups across the US and territories. The third hypothesis investigated if political party control and governmental policies affected the number of cases and death proportion rates across ethnic groups. The research findings suggest that POC positive cases and death rates were higher in some states. Black ethnic groups were dying at a high rate in the southeastern states, the District of Columbia, and in Maryland. Specifically, in the District of Columbia, the death rate is five times higher than the White ethnic group. For Latinx ethnic groups, the high cases and death rates have mostly occurred in western states, including Texas. The Latinx ethnic group accounted for half the total deaths in Texas and California. The Latinx ethnic group death rate is higher than the White ethnic group in four states: Texas, California, New Mexico, and the District of Columbia. The research findings also show that the rate of deaths and cases per ethnic group for policies and political factors were significant except for the mask mandate policy. Based on the analyzed data, mask mandates were not a factor in the cases or death rates of any ethnic group. Each state’s policies for bars, curfews, public schools, and travel—along with legislative party control—had the most influences across ethnic groups. The research results for the death rates and number of cases due to these implemented policies varied between ethnic groups.

Geometry-Inference based Clustering-Heuristic: An empirical method for kmeans optimal clusters determination

“…Since its first appearance in the 1950's and 1960's (Forgy 1965;Lloyd 1982), the kmeans algorithm has been used as a major clustering technique in Unsupervised Machine Learning (ML) as a vector quantization by minimizing a formal objective function that is the meansquared-error distortion between data and the corresponding clusters' centres (Mantao Xu and Franti 2004;Gupta et al 2018) . Even though the kmeans algorithm is considered a NP-Hard problem and is then time consuming (Käärik and Pärna 2009), the corresponding heuristic is quite simple to implement (Mantao Xu and Franti 2004) leading to a broad use in a plethora of engineering areas (Alsaaideh et al 2017;Song et al 2017), from computer vision image processing (Celebi 2011;Mosorov and Tomczak 2014;Deng et al 2018;Fu et al 2021) to computational chemistry data modelling (Spyrakis et al 2015;Bremer et al 2020), or in finance and market analytics (Ahmed et al 2016;Ahmed et al 2017), but also in biostatistics and epidemiology Hamilton et al 2022). According to the success of kmeans algorithm, it is thoroughly still getting interest in Academia, and by extension, as a practical technique that is encapsulated within toolbox's software platforms (Matlab 2022-1;Github 2022;scikit-learn 2022).…”

AI and data science for smart emergency, crisis and disaster resilience

“…The roles of AI and data science in COVID-19 are multiaspect and substantial. Examples include [ 10 ]: diagnosis and treatment of COVID-19 diseases and its SARS-CoV-2 viruses, including through medical imaging analysis [ 11 ]; quantification and understanding of the COVID-19 disease complexities, virus mutations, and disease resurgences [ 12 ]; efficacy modeling of COVID-19 medical treatment, vaccinations and pharmaceutical interventions [ 13 ]; discovery of drugs, vaccines, and biomedical products [ 14 ]; effectiveness modeling of non-pharmaceutical interventions and policies [ 15 ]; characterization of social, economic and political impact of COVID-19 [ 16 ]. In the massive literature on modeling COVID-19 [ 10 ] and the global scientific response to COVID-19 [ 17 ], we can find that comprehensive AI and data science technologies have been applied to address the above COVID-19 issues.…”

AI in Combating the COVID-19 Pandemic

“…Various works 3 have reported or compared the performance of specific AI techniques in tackling the SARS-COV-2 virus, the COVID-19 disease, and the pandemic. Typical examples are the rapid COVID-19 diagnosis on X-ray and other medical imaging resources, 8,9 the prediction of COVID-19 cases, spread and resurgence, 10 the discovery of antibodies for drug development, 11 the impact estimation of NPIs, 10,12 policies, 13 and human mobility 14 on the COVID-19 spread and death, the influence analysis of public health actions on controlling the virus mutation, 15 the misinformation impact on COVID-19-related knowledge circulation and vaccination intention, 16 and analyzing the mental and socioeconomic impact of COVID-19. 17 However, the commitment from each country is very biased and imbalanced in the researched problems and techniques.…”