A large-scale machine learning study of sociodemographic factors contributing to COVID-19 severity

Abstract

Understanding sociodemographic factors behind COVID-19 severity relates to significant methodological difficulties, such as differences in testing policies and epidemics phase, as well as a large number of predictors that can potentially contribute to severity. To account for these difficulties, we assemble 115 predictors for more than 3,000 US counties and employ a well-defined COVID-19 severity measure derived from epidemiological dynamics modeling. We then use a number of advanced feature selection techniques from machine learning to determine which of these predictors significantly impact the disease severity. We obtain a surprisingly simple result, where only two variables are clearly and robustly selected—population density and proportion of African Americans. Possible causes behind this result are discussed. We argue that the approach may be useful whenever significant determinants of disease progression over diverse geographic regions should be selected from a large number of potentially important factors.

Accuracy and Performance of Machine Learning Methodologies: Novel Assessments of Country Pandemic Vulnerability Based on Non-Pandemic Predictors

“…The RFR and XGBoost models were selected as the most relevant models for feature importance evaluation, frequently utilized by researchers [9], [20], [22], [23], [27], [35]. The K-means-Coefficient of Variance sensitivity analysis was developed as a more sensitive novel machine learning approach, and the Ordinary Least Squares Multifactor Regression methodology was introduced as a validation model.…”

“…Other researchers focused their work on assessing non-clinical factors, such as demographics, travel, environmental factors (temperature, relative humidity, atmospheric pollutants, etc. ), capacity and health related county-level factors, vulnerable population scores, national socio-economic factors, and different epidemiological data [12], [30], [31], [33], [34], [35], [36].…”

Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel‐2 Remote Sensing Data: A Generalizability Analysis

“…It's worth noting that we incorporated the cubic root of the predictors as a predictive parameter. This was done to mitigate data skewness and bring the distribution closer to normal [100]. Henceforth, the results presented for the turbidity modeling are based on the selected parameters presented in Figures 2 and 3, and the cubic root of each predictor.…”