A spatiotemporal analysis of the social determinants of health for COVID-19.

This research aims to uncover how the association between social determinants of health and COVID-19 cases and fatality rate have changed across time and space. To begin to understand these associations and show the benefits of analysing temporal and spatial variations in COVID-19, we utilized Geographically Weighted Regression (GWR). The results emphasize the advantages for using GWR in data with a spatial component, while showing the changing spatiotemporal magnitude of association between a given social determinant and cases or fatalities. While previous research has demonstrated the merits of GWR for spatial epidemiology, our study fills a gap in the literature, by examining a suite of variables across time to reveal how the pandemic unfolded across the US at a county-level spatial scale. The results speak to the importance of understanding the local effects that a social determinant may have on populations at the county level. From a public health perspective, these results can be used for an understanding of the disproportionate disease burden felt by different populations, while upholding and building upon trends observed in epidemiological literature.

Feature selection and association rule learning identify risk factors of malnutrition among Ethiopian schoolchildren.

Introduction: Previous studies have sought to identify risk factors for malnutrition in populations of schoolchildren, depending on traditional logistic regression methods. However, holistic machine learning (ML) approaches are emerging that may provide a more comprehensive analysis of risk factors. Methods: This study employed feature selection and association rule learning ML methods in conjunction with logistic regression on epidemiological survey data from 1,036 Ethiopian school children. Our first analysis used the entire dataset and then we reran this analysis on age, residence, and sex population subsets. Results: Both logistic regression and ML methods identified older childhood age as a significant risk factor, while females and vaccinated individuals showed reduced odds of stunting. Our machine learning analyses provided additional insights into the data, as feature selection identified that age, school latrine cleanliness, large family size, and nail trimming habits were significant risk factors for stunting, underweight, and thinness. Association rule learning revealed an association between co-occurring hygiene and socio-economical variables with malnutrition that was otherwise missed using traditional statistical methods. Discussion: Our analysis supports the benefit of integrating feature selection methods, association rules learning techniques, and logistic regression to identify comprehensive risk factors associated with malnutrition in young children.