A Methodological Approach to Use Contextual Factors for Epidemiological Studies on Chronic Exposure to Air Pollution and COVID-19 in Italy

Abstract

The large availability of both air pollution and COVID-19 data, and the simplicity to make geographical correlations between them, led to a proliferation of ecological studies relating the levels of pollution in administrative areas to COVID-19 incidence, mortality or lethality rates. However, the major drawback of these studies is the ecological fallacy that can lead to spurious associations. In this frame, an increasing concern has been addressed to clarify the possible role of contextual variables such as municipalities' characteristics (including urban, rural, semi-rural settings), those of the resident communities, the network of social relations, the mobility of people, and the responsiveness of the National Health Service (NHS), to better clarify the dynamics of the phenomenon. The objective of this paper is to identify and collect the municipalities' and community contextual factors and to synthesize their information content to produce suitable indicators in national environmental epidemiological studies, with specific emphasis on assessing the possible role of air pollution on the incidence and severity of the COVID-19 disease. A first step was to synthesize the content of spatial information, available at the municipal level, in a smaller set of "summary indexes" that can be more easily viewed and analyzed. For the 7903 Italian municipalities (1 January 2020-ISTAT), 44 variables were identified, collected, and grouped into five information dimensions a priori defined: (i) geographic characteristics of the municipality, (ii) demographic and anthropogenic characteristics, (iii) mobility, (iv) socio-economic-health area, and (v) healthcare offer (source: ISTAT, EUROSTAT or Ministry of Health, and further ad hoc elaborations (e.g., OpenStreetMaps)). Principal component analysis (PCA) was carried out for the five identified dimensions, with the aim of reducing the large number of initial variables into a smaller number of components, limiting as much as possible the loss of information content (variability). We also included in the analysis PM_2.5, PM₁₀ and NO₂ population weighted exposure (PWE) values obtained using a four-stage approach based on the machine learning method, "random forest", which uses space-time predictors, satellite data, and air quality monitoring data estimated at the national level. Overall, the PCA made it possible to extract twelve components: three for the territorial characteristics dimension of the municipality (variance explained 72%), two for the demographic and anthropogenic characteristics dimension (variance explained 62%), three for the mobility dimension (variance explained 83%), two for the socio-economic-health sector (variance explained 58%) and two for the health offer dimension (variance explained 72%). All the components of the different dimensions are only marginally correlated with each other, demonstrating their potential ability to grasp different aspects of the spatial distribution of the COVID-19 pathology. This work provides a national repository of contextual variables at the municipality level collapsed into twelve informative factors suitable to be used in studies on the association between chronic exposure to air pollution and COVID-19 pathology, as well as for investigations on the role of air pollution on the health of the Italian population.

Keywords: COVID-19; air pollution; contextual factors; data synthesis techniques; epidemiology; principal component analysis (PCA).

Figure 1

Spearman correlation matrices among the variables within each dimension: geographic characteristic (a), demographic and anthropogenic characteristics (b), mobility (c), socio-economic-health characteristics (d), availability of health care (e). Variable labels are listed in Table 1.

Figure 2

Results of the principal component analysis (PCA); the contributions of individual contextual covariates on the selected components are displayed for the five dimensions (geographic characteristic (a), demographic and anthropogenic characteristics (b), mobility (c), socio-economic and health status of the population (d), availability of health care (e)). Variable labels are listed in Table 1.

Figure 3

Correlation matrix among the components resulted from the principal component analysis.