Cargando…

Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach

After the start of the COVID-19 pandemic and its spread across the world, countries have adopted containment measures to stop its transmission, limit fatalities, and relieve hospitals from straining and overwhelming conditions imposed by the virus. Many countries implemented social distancing and lo...

Descripción completa

Detalles Bibliográficos
Autores principales: Kazemi, Mehrdad, Bragazzi, Nicola Luigi, Kong, Jude Dzevela
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8879459/
https://www.ncbi.nlm.nih.gov/pubmed/35214653
http://dx.doi.org/10.3390/vaccines10020194
_version_ 1784658896521003008
author Kazemi, Mehrdad
Bragazzi, Nicola Luigi
Kong, Jude Dzevela
author_facet Kazemi, Mehrdad
Bragazzi, Nicola Luigi
Kong, Jude Dzevela
author_sort Kazemi, Mehrdad
collection PubMed
description After the start of the COVID-19 pandemic and its spread across the world, countries have adopted containment measures to stop its transmission, limit fatalities, and relieve hospitals from straining and overwhelming conditions imposed by the virus. Many countries implemented social distancing and lockdown strategies that negatively impacted their economies and the psychological wellbeing of their citizens, even though they contributed to saving lives. Recently approved and available, COVID-19 vaccines can provide a really viable and sustainable option for controlling the pandemic. However, their uptake represents a global challenge due to vaccine hesitancy and logistic–organizational hurdles that have made its distribution stagnant in several developed countries despite several appeals by the media, policy- and decision-makers, and community leaders. Vaccine distribution is also a concern in developing countries, where there is a scarcity of doses. The objective of the present study was to set up a metric to assess vaccination uptake and identify national socio-economic factors influencing this indicator. We conducted a cross-country study. We first estimated the vaccination uptake rate across countries by fitting a logistic model to reported daily case numbers. Using the uptake rate, we estimated the vaccine roll-out index. Next, we used Random Forest, an “off-the-shelf” machine learning algorithm, to study the association between vaccination uptake rate and socio-economic factors. We found that the mean vaccine roll-out index is 0.016 (standard deviation 0.016), with a range between 0.0001 (Haiti) and 0.0829 (Mongolia). The top four factors associated with the vaccine roll-out index are the median per capita income, human development index, percentage of individuals who have used the internet in the last three months, and health expenditure per capita. The still-ongoing COVID-19 pandemic has shed light on the disparity in vaccine adoption across low- and high-income countries, which represents a global public health challenge. We must pave the way for universal access to vaccines and other approved treatments, regardless of demographic structures and underlying health conditions. Income disparity remains, instead, an important cause of vaccine inequity, which restricts the functioning of the global vaccine allocation framework and, thus, the ending of the pandemic. Stronger mechanisms are needed to foster countries’ political willingness to promote vaccine and drug access equity in a globalized society where future pandemics and other global health crises can be anticipated.
format Online
Article
Text
id pubmed-8879459
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88794592022-02-26 Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach Kazemi, Mehrdad Bragazzi, Nicola Luigi Kong, Jude Dzevela Vaccines (Basel) Article After the start of the COVID-19 pandemic and its spread across the world, countries have adopted containment measures to stop its transmission, limit fatalities, and relieve hospitals from straining and overwhelming conditions imposed by the virus. Many countries implemented social distancing and lockdown strategies that negatively impacted their economies and the psychological wellbeing of their citizens, even though they contributed to saving lives. Recently approved and available, COVID-19 vaccines can provide a really viable and sustainable option for controlling the pandemic. However, their uptake represents a global challenge due to vaccine hesitancy and logistic–organizational hurdles that have made its distribution stagnant in several developed countries despite several appeals by the media, policy- and decision-makers, and community leaders. Vaccine distribution is also a concern in developing countries, where there is a scarcity of doses. The objective of the present study was to set up a metric to assess vaccination uptake and identify national socio-economic factors influencing this indicator. We conducted a cross-country study. We first estimated the vaccination uptake rate across countries by fitting a logistic model to reported daily case numbers. Using the uptake rate, we estimated the vaccine roll-out index. Next, we used Random Forest, an “off-the-shelf” machine learning algorithm, to study the association between vaccination uptake rate and socio-economic factors. We found that the mean vaccine roll-out index is 0.016 (standard deviation 0.016), with a range between 0.0001 (Haiti) and 0.0829 (Mongolia). The top four factors associated with the vaccine roll-out index are the median per capita income, human development index, percentage of individuals who have used the internet in the last three months, and health expenditure per capita. The still-ongoing COVID-19 pandemic has shed light on the disparity in vaccine adoption across low- and high-income countries, which represents a global public health challenge. We must pave the way for universal access to vaccines and other approved treatments, regardless of demographic structures and underlying health conditions. Income disparity remains, instead, an important cause of vaccine inequity, which restricts the functioning of the global vaccine allocation framework and, thus, the ending of the pandemic. Stronger mechanisms are needed to foster countries’ political willingness to promote vaccine and drug access equity in a globalized society where future pandemics and other global health crises can be anticipated. MDPI 2022-01-26 /pmc/articles/PMC8879459/ /pubmed/35214653 http://dx.doi.org/10.3390/vaccines10020194 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kazemi, Mehrdad
Bragazzi, Nicola Luigi
Kong, Jude Dzevela
Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach
title Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach
title_full Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach
title_fullStr Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach
title_full_unstemmed Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach
title_short Assessing Inequities in COVID-19 Vaccine Roll-Out Strategy Programs: A Cross-Country Study Using a Machine Learning Approach
title_sort assessing inequities in covid-19 vaccine roll-out strategy programs: a cross-country study using a machine learning approach
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8879459/
https://www.ncbi.nlm.nih.gov/pubmed/35214653
http://dx.doi.org/10.3390/vaccines10020194
work_keys_str_mv AT kazemimehrdad assessinginequitiesincovid19vaccinerolloutstrategyprogramsacrosscountrystudyusingamachinelearningapproach
AT bragazzinicolaluigi assessinginequitiesincovid19vaccinerolloutstrategyprogramsacrosscountrystudyusingamachinelearningapproach
AT kongjudedzevela assessinginequitiesincovid19vaccinerolloutstrategyprogramsacrosscountrystudyusingamachinelearningapproach