Pandemic Vulnerability Index (PVI) and spatial distribution of coronavirus deaths in Brazil: Artificial intelligence with the boosting tree regression method
{"title":"Pandemic Vulnerability Index (PVI) and spatial distribution of coronavirus deaths in Brazil: Artificial intelligence with the boosting tree regression method","authors":"Rogério Pereira , Erick Giovani Sperandio Nascimento","doi":"10.1016/j.rspp.2024.100013","DOIUrl":null,"url":null,"abstract":"<div><p>This article aims to calculate the COVID-19 Pandemic Vulnerability Index (COVID-19-PVI) across Brazilian municipalities, positing that vulnerability to the coronavirus is linked to socioeconomic disparities in this continental-sized country. From data collection on epidemiological, socioeconomic, demographic, and public health systems, it was possible to rank which features were most influential in the spread of COVID-19 using the artificial intelligence implicit in the boosting tree regression method. To ensure the robustness of the findings, this index is tested in Pearson correlations leading to conclusions about which regions were most vulnerable to the pandemic and its consequences, the importance of the spatial distribution of General Hospitals during the COVID-19 outbreak, and the influence of population density on the advancement of the coronavirus in the country.</p></div>","PeriodicalId":45520,"journal":{"name":"Regional Science Policy and Practice","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1757780224000416/pdfft?md5=5e2136efd993b661cd06623dc404903b&pid=1-s2.0-S1757780224000416-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Regional Science Policy and Practice","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1757780224000416","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOGRAPHY","Score":null,"Total":0}
引用次数: 0
Abstract
This article aims to calculate the COVID-19 Pandemic Vulnerability Index (COVID-19-PVI) across Brazilian municipalities, positing that vulnerability to the coronavirus is linked to socioeconomic disparities in this continental-sized country. From data collection on epidemiological, socioeconomic, demographic, and public health systems, it was possible to rank which features were most influential in the spread of COVID-19 using the artificial intelligence implicit in the boosting tree regression method. To ensure the robustness of the findings, this index is tested in Pearson correlations leading to conclusions about which regions were most vulnerable to the pandemic and its consequences, the importance of the spatial distribution of General Hospitals during the COVID-19 outbreak, and the influence of population density on the advancement of the coronavirus in the country.
期刊介绍:
Regional Science Policy & Practice (RSPP) is the official policy and practitioner orientated journal of the Regional Science Association International. It is an international journal that publishes high quality papers in applied regional science that explore policy and practice issues in regional and local development. It welcomes papers from a range of academic disciplines and practitioners including planning, public policy, geography, economics and environmental science and related fields. Papers should address the interface between academic debates and policy development and application. RSPP provides an opportunity for academics and policy makers to develop a dialogue to identify and explore many of the challenges facing local and regional economies.