Social disparities in the first wave of COVID-19 infections in Germany: A county-scale explainable machine learning approach

Abstract

BackgroundLittle is known about factors correlated with this geographic spread of the first wave of COVID-19 infections in Germany. Given the lack of individual-level socioeconomic information on COVID-19 cases, we resorted to an ecological study design, exploring regional correlates of COVID-19 diagnoses.Data and MethodWe used data from the Robert-Koch-Institute on COVID-19 diagnoses by sex, age (age groups: 0-4, 5-14, 15-34, 35-59, 60-79, 80+), county (NUTS3 region) differentiating five periods (initial phase: through 15 March; 1st lockdown period: 16 March to 31 March; 2nd lockdown period: from 1 April to 15 April; easing period: 16 April to 30 April; post-lockdown period: 1 May through 23 July). For each period we calculated age-standardized incidence of COVID-19 diagnoses on the county level, using the German age distribution from the year 2018. We characterized the regions by macro variables in nine domains: “Demography”, “Employment”, “Politics, religion, and education”, “Income”, “Settlement structure and environment”, “Health care”, “(structural) Poverty”, “Interrelationship with other regions”, and “Geography”. We trained gradient boosting models to predict the age-standardized incidence rates with the macro structures of the counties, and used SHAP values to characterize the 20 most prominent features in terms of negative/positive correlations with the outcome variable.ResultsThe change in the age-standardized incidence rates over time is reflected in the changing importance of features as indicated by the mean SHAP values for the five periods. The first COVID-19 wave started as a disease in wealthy rural counties in southern Germany, and ventured into poorer urban and agricultural counties during the course of the first wave. The negative social gradient became more pronounced from the 2nd lockdown period onwards, when wealthy counties appeared to be better protected. Population density per se does not appear to be a risk factor, and only in the post-lockdown period did connectedness become an important regional characteristic correlated with higher infections. Features related to economic and educational characteristics of the young population in a county played an important role at the beginning of the pandemic up to the 2nd lockdown phase, as did features related to the population living in nursing homes; those related to international migration and a large proportion of foreigners living in a county became important in the post-lockdown period.DiscussionIn the absence of individual level data, explainable machine learning methods based on regional data may help to better understand the changing nature of the drivers of the pandemic. High mobility of high SES groups may drive the pandemic at the beginning of waves, while mitigation measures and beliefs about the seriousness of the pandemic as well as the compliance with mitigation measures put lower SES groups at higher risks later on.

The second wave of SARS-CoV-2 infections and COVID-19 deaths in Germany – driven by values, social status and migration background? A county-scale explainable machine learning approach

“…Restricting our analysis to those first twenty risk factors identified by Shapley values, we concluded that, similar to the first wave (Doblhammer et al, 2020), SES was an important driver in the second wave. While both social gradients, positive and negative, were present in SARS-CoV-2 infections in October, the negative SES gradient began to dominate over time and was always the dominant one in mortality.…”

“…Note that the feature “%of Roman-Catholics “in a county, which was prominent in the first wave (Doblhammer et al, 2020), lost importance in the second wave. In the first wave, it reflected large gatherings during the carnival season in southern Germany that led to hotspots of infection (Streeck et al, 2020).…”

“…Poorer access to health care and disadvantaged living and working conditions appear to play an important role. With the exception of Doblhammer et al (2020), who found that the proportion of foreigners and migrants was an important regional characteristic for COVID-19 in Germany during the first wave, we are not aware of any other studies for Germany. This is all the more remarkable as the studies above suggested that working environments, cramped living conditions, and language barriers are at odds with social distancing and should put this groups at higher risk.…”

“…These studies used a small number of preselected indicators to characterize the regions. A different approach was taken by two studies (Doblhammer et al, 2020; Scarpone et al, 2020) that relied on machine learning algorithms to identify key regional features that predict SARS-CoV-2 infections and COVID-19 deaths without selecting specific indicators. They concluded that social status played an important role, in addition to features related to geographic location, hotspot events associated with the southern German carnival season, and the proportion of the population at risk in nursing homes.…”

“…They concluded that social status played an important role, in addition to features related to geographic location, hotspot events associated with the southern German carnival season, and the proportion of the population at risk in nursing homes. And they showed that the social gradient already evolved from a positive to a negative one during the first wave (Doblhammer et al, 2020).…”