Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions

Abstract Italy has experienced the epidemic of Severe Acute Respiratory Syndrome Coronavirus 2, which spread at different times and with different intensities throughout its territory. We aimed to identify clusters with similar epidemic patterns across Italian regions. To do that, we defined a set o...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Andrea Maugeri, Martina Barchitta, Guido Basile, Antonella Agodi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d85f1c2647a14bc1ad59c8efc94a4782
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d85f1c2647a14bc1ad59c8efc94a4782
record_format	dspace
spelling	oai:doaj.org-article:d85f1c2647a14bc1ad59c8efc94a47822021-12-02T14:23:32ZApplying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions10.1038/s41598-021-86703-32045-2322https://doaj.org/article/d85f1c2647a14bc1ad59c8efc94a47822021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86703-3https://doaj.org/toc/2045-2322Abstract Italy has experienced the epidemic of Severe Acute Respiratory Syndrome Coronavirus 2, which spread at different times and with different intensities throughout its territory. We aimed to identify clusters with similar epidemic patterns across Italian regions. To do that, we defined a set of regional indicators reflecting different domains and employed a hierarchical clustering on principal component approach to obtain an optimal cluster solution. As of 24 April 2020, Lombardy was the worst hit Italian region and entirely separated from all the others. Sensitivity analysis—by excluding data from Lombardy—partitioned the remaining regions into four clusters. Although cluster 1 (i.e. Veneto) and 2 (i.e. Piedmont and Emilia-Romagna) included the most hit regions beyond Lombardy, this partition reflected differences in the efficacy of restrictions and testing strategies. Cluster 3 was heterogeneous and comprised regions where the epidemic started later and/or where it spread with the lowest intensity. Regions within cluster 4 were those where the epidemic started slightly after Veneto, Emilia-Romagna and Piedmont, favoring timely adoption of control measures. Our findings provide policymakers with a snapshot of the epidemic in Italy, which might help guiding the adoption of countermeasures in accordance with the situation at regional level.Andrea MaugeriMartina BarchittaGuido BasileAntonella AgodiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Andrea Maugeri Martina Barchitta Guido Basile Antonella Agodi Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions
description	Abstract Italy has experienced the epidemic of Severe Acute Respiratory Syndrome Coronavirus 2, which spread at different times and with different intensities throughout its territory. We aimed to identify clusters with similar epidemic patterns across Italian regions. To do that, we defined a set of regional indicators reflecting different domains and employed a hierarchical clustering on principal component approach to obtain an optimal cluster solution. As of 24 April 2020, Lombardy was the worst hit Italian region and entirely separated from all the others. Sensitivity analysis—by excluding data from Lombardy—partitioned the remaining regions into four clusters. Although cluster 1 (i.e. Veneto) and 2 (i.e. Piedmont and Emilia-Romagna) included the most hit regions beyond Lombardy, this partition reflected differences in the efficacy of restrictions and testing strategies. Cluster 3 was heterogeneous and comprised regions where the epidemic started later and/or where it spread with the lowest intensity. Regions within cluster 4 were those where the epidemic started slightly after Veneto, Emilia-Romagna and Piedmont, favoring timely adoption of control measures. Our findings provide policymakers with a snapshot of the epidemic in Italy, which might help guiding the adoption of countermeasures in accordance with the situation at regional level.
format	article
author	Andrea Maugeri Martina Barchitta Guido Basile Antonella Agodi
author_facet	Andrea Maugeri Martina Barchitta Guido Basile Antonella Agodi
author_sort	Andrea Maugeri
title	Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions
title_short	Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions
title_full	Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions
title_fullStr	Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions
title_full_unstemmed	Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions
title_sort	applying a hierarchical clustering on principal components approach to identify different patterns of the sars-cov-2 epidemic across italian regions
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/d85f1c2647a14bc1ad59c8efc94a4782
work_keys_str_mv	AT andreamaugeri applyingahierarchicalclusteringonprincipalcomponentsapproachtoidentifydifferentpatternsofthesarscov2epidemicacrossitalianregions AT martinabarchitta applyingahierarchicalclusteringonprincipalcomponentsapproachtoidentifydifferentpatternsofthesarscov2epidemicacrossitalianregions AT guidobasile applyingahierarchicalclusteringonprincipalcomponentsapproachtoidentifydifferentpatternsofthesarscov2epidemicacrossitalianregions AT antonellaagodi applyingahierarchicalclusteringonprincipalcomponentsapproachtoidentifydifferentpatternsofthesarscov2epidemicacrossitalianregions
_version_	1718391456093175808

Applying a hierarchical clustering on principal components approach to identify different patterns of the SARS-CoV-2 epidemic across Italian regions

Ejemplares similares