Assessment of Excess Mortality in Italy in 2020-2021 as a Function of Selected Macro-Factors

Abstract

Background: Excess mortality (EM) can reliably capture the impact of a pandemic, this study aims at assessing the numerous factors associated with EM during the COVID-19 pandemic in Italy.

Methods: Mortality records (ISTAT 2015-2021) aggregated in the 610 Italian Labour Market Areas (LMAs) were used to obtain the EM P-scores to associate EM with socioeconomic variables. A two-step analysis was implemented: (1) Functional representation of EM and clustering. (2) Distinct functional regression by cluster.

Results: The LMAs are divided into four clusters: 1 low EM; 2 moderate EM; 3 high EM; and 4 high EM-first wave. Low-Income showed a negative association with EM clusters 1 and 4. Population density and percentage of over 70 did not seem to affect EM significantly. Bed availability positively associates with EM during the first wave. The employment rate positively associates with EM during the first two waves, becoming negatively associated when the vaccination campaign began.

Conclusions: The clustering shows diverse behaviours by geography and time, the impact of socioeconomic characteristics, and local governments and health services' responses. The LMAs allow to draw a clear picture of local characteristics associated with the spread of the virus. The employment rate trend confirmed that essential workers were at risk, especially during the first wave.

Keywords: COVID-19; clustering model; correlation; excess death; functional data; labour market areas; macrofactors; regression model.

Figure A1

Number of LMAs in the clusters divided by geographical area.

Figure A2

Distribution of socioeconomic variables within clusters.

Figure A3

Percentage of LMA classes within the clusters.

Figure 1

Statistical analysis workflow.

Figure 2

Average EM by cluster (a) and cluster distribution map (b) for the ${\mathrm{DFM}}_{[{\alpha }_{kj},\beta ]}$ model with 12 bspline basis function, and four cluster. Cluster 1 curve is given in yellow, Cluster 2 in green, Cluster 3 in blue, Cluster 4 in violet.

Figure 3

Estimated functional coefficients. The colour of the curves follows the colours of the clusters, namely, yellow—Cluster 1, green—Cluster 2, blue—Cluster 3, and violet—Cluster 4.