Spatial Assessment of COVID-19 First-Wave Mortality Risk in the Global South

Abstract

The coronavirus disease (COVID-19) that appeared in 2019 gave rise to a major global health crisis that is still topping global health, socioeconomic, and intervention program agendas. Although the outbreak of COVID-19 has had substantial and devastating impacts on developed countries, the countries of the Global South share a higher proportion of the epidemic’s effects as shown particularly in morbidity and mortality rates in low-income countries. Modeling the effects of underlying factors and disease mortality is essential to plan effective control strategies for disease transmission and risks. The relationship between COVID-19 mortality rates and sociodemographic and health determinants can highlight various epidemic fatality risks. In this research, geographic information systems (GIS) and a multilayer perceptron (MLP) artificial neural network (ANN) were adopted to model and examine variations in COVID-19 mortality rates in the Global South. The model’s performance was tested using statistical measures of mean square error (MSE), root mean square error (RMSE), mean bias error (MBE), and the coefficient of determination (R²). The findings indicated that the most important variables in explaining spatial mortality rate variations were the size of the elderly (sixty-five and older) population, accessibility to handwashing facilities, and hospital beds per 1,000 population. Mapping the explanatory variables and estimated mortality rates and determining the importance of each variable in explaining the spatial variation of COVID-19 death rates across countries of the Global South can shed light on how public health care and demographic structures can offer policymakers invaluable guidelines to planning effective intervention strategies.

2019新冠病毒（COVID-19）引发了一场全球性重大健康危机, 至今仍然是全球健康、社会经济和干预计划的首要议题。虽然新冠病毒的爆发对发达国家有深远和毁灭性的影响, 但发展中国家在流行病影响中所占比例更大, 特别是低收入国家的发病率和死亡率。建立相关因素和疾病死亡率的影响模型, 对疾病传播和风险控制措施的有效规划至关重要。新冠病毒死亡率与社会人口和健康因素之间的关系, 可以突出各种流行病的致命性风险。本研究采用地理信息系统和多层感知器（MultiLayer Perceptron）人工神经网络, 对发展中国家新冠病毒死亡率的差异进行了建模和探讨。模型验证采用均方差（Mean Square Error）、均方根误差（Root Mean Square Error）、平均偏差误差（Mean Bias Error）和决定系数（R²）等统计度量。研究结果表明, 死亡率空间差异的最重要解释变量是老年（65岁及以上）人口数量、洗手设施的可达性和每1000人的医院床位。对解释变量和估计死亡率的制图、确定发展中国家新冠病毒死亡率空间差异的每个解释变量的重要性, 可以揭示公共卫生保健和人口结构如何引导决策者去规划有效的干预策略。

La enfermedad causada por el coronavirus (COVID-19), que apareció en 2019, dio lugar a una notable crisis sanitaria mundial que todavía sigue encabezando las agendas sanitarias, socioeconómicas y de los programas de intervención. Si bien el brote del COVID-19 ha tenido impactos sustanciales y devastadores en los países desarrollados, los países del Sur Global comparten una proporción muy alta de los efetos de la epidemia, como se evidencia particularmente en las tasas de morbilidad y mortalidad en los países de bajo ingreso. Modelar los efectos de los factores subyacentes y de la mortalidad de la enfermedad es esencial para planificar estrategias efectivas para controlar el riesgo de transmisión de la enfermedad. La relación entre las tasas de mortalidad del COVID-19 y los determinantes sociodemográficos y sanitarios puede destacar varios riesgos de fatalidad epidémica. En esta investigación se adoptaron los sistemas de información geográfica (SIG) y las redes neuronales artificiales (ANN) para modelar y examinar las variaciones en las tasas de mortalidad por COVID-19 en el Sur Global. El desempeño del modelo se puso a prueba usando las medidas estadísticas del error cuadrático medio (MSE), raíz media del error cuadrático (RMSE) y el coeficiente de determinación (R²). Los descubrimientos logrados indicaron que las variables más importantes para explicar las variaciones espaciales de las tasas de mortalidad eran el tamaño de la población de edad avanzada (65 años o más), la accesibilidad a las instalaciones para lavarse las manos y el número de camas hospitalarias por cada 1.000 habitantes. Cartografiar las variables explicativas y las tasas estimadas de mortalidad, y determinar la importancia de cada variable para explicar la variación espacial de las tasas de mortalidad por COVID-19 en los países del Sur Global, puede arrojar luz sobre cómo la atención sanitaria pública y la estructura demográfica pueden ofrecer a los gobernantes directrices invaluables para planificar estrategias de intervención efectivas.

Key Words:

• ANN
• COVID-19 mortality
• GIS modeling
• Global South
• sociodemographic determinants

关键词:

• 人工神经网络
• 新冠病毒死亡率
• 地理信息系统建模
• 发展中国家
• 社会人口决定因素。

Palabras clave:

• ANN
• determinantes sociodemográficos
• modelización con SIG
• mortalidad por COVID-19
• Sur Global

Acknowledgments

Authors’ contributions: Conceptualization, methodology, data curation, geospatial analysis, investigation, writing—original draft, S.M.; writing introduction section, data curation, writing—review and editing, A.A; data curation, writing—review and editing, M.A; data curation, writing—review and editing, E.R. All authors have read and agreed to the published version of the article.

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.

Additional information

Notes on contributors

Shawky Mansour

SHAWKY MANSOUR is an Associate Professor of GIS in the Department of Geography and GIS, Faculty of Arts, Alexandria University, Egypt, and in the Geography Department, College of Arts and Social Sciences, Sultan Qaboos University, Muscat 123, Al Khoud, Oman. E-mail: [email protected]. He is a specialist in GIS with particular interests in GIScience and spatial modeling. His research focuses on developing and utilizing advanced geospatial techniques to model and analyze the interrelationships between environmental, socioeconomic, and demographic phenomena.

Ammar Abulibdeh

AMMAR ABULIBDEH is an Assistant Professor in the Department of Humanities, College of Arts and Science, Qatar University, Doha, Qatar. E-mail: [email protected]. His research focuses on smart urban planning and design, sustainable built environment, sustainable transportation, and the water– energy–food nexus.

Mohammed Alahmadi

MOHAMMED ALAHMADI is an Associate Professor in the National Center for Remote Sensing Technology at King Abdulaziz City for Science and Technology (KACST), Riyadh 11442, Saudi Arabia. E-mail: [email protected]. He is an expert in modeling small area population data from satellite data. His research focuses on the application of machine learning, space–time modeling, and global environmental change.

Elnazir Ramadan

ELNAZIR RAMADAN is an Assistant Professor in the Geography Department, Sultan Qaboos University, Muscat 123, Al Khoud, Oman. E-mail [email protected]. His research interests cover issues related to land use planning and spatial development issues including sustainable urbanization with emphasis on the Global South. Further research interests include geospatial technologies application in spatial planning as well as urban governance and sustainability issues.