PM2.5 as a major predictor of COVID-19 basic reproduction number in the USA
| Autor: | Magdalena Djordjevic, Ognjen Milicevic, Marko Djordjevic, Igor Salom, Dusan Zigic, Marko Tumbas, Sofija Markovic, Andjela Rodic |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Elastic net regularization
Principal component analysis Basic Reproduction Number Feature selection 010501 environmental sciences 01 natural sciences Biochemistry Article 03 medical and health sciences 0302 clinical medicine Lasso (statistics) Machine learning Linear regression Statistics Humans 030212 general & internal medicine Quantitative Biology - Populations and Evolution 0105 earth and related environmental sciences General Environmental Science Mathematics Air Pollutants Outdoor air pollutants SARS-CoV-2 Populations and Evolution (q-bio.PE) COVID-19 pollution dependence COVID-19 United States Transmissibility (vibration) Ranking FOS: Biological sciences Particulate Matter Basic reproduction number |
| Zdroj: | Environmental Research |
| ISSN: | 0013-9351 |
| DOI: | 10.1016/j.envres.2021.111526 |
| Popis: | Many studies have proposed a relationship between COVID-19 transmissibility and ambient pollution levels. However, a major limitation in establishing such associations is to adequately account for complex disease dynamics, influenced by e.g. significant differences in control measures and testing policies. Another difficulty is appropriately controlling the effects of other potentially important factors, due to both their mutual correlations and a limited dataset. To overcome these difficulties, we will here use the basic reproduction number ($R_0$) that we estimate for USA states using non-linear dynamics methods. To account for a large number of predictors (many of which are mutually strongly correlated), combined with a limited dataset, we employ machine-learning methods. Specifically, to reduce dimensionality without complicating the variable interpretation, we employ Principal Component Analysis on subsets of mutually related (and correlated) predictors. Methods that allow feature (predictor) selection, and ranking their importance, are then used, including both linear regressions with regularization and feature selection (Lasso and Elastic Net) and non-parametric methods based on ensembles of weak-learners (Random Forest and Gradient Boost). Through these substantially different approaches, we robustly obtain that PM$_{2.5}$ is a major predictor of $R_0$ in USA states, with corrections from factors such as other pollutants, prosperity measures, population density, chronic disease levels, and possibly racial composition. As a rough magnitude estimate, we obtain that a relative change in $R_0$, with variations in pollution levels observed in the USA, is typically ~30%, which further underscores the importance of pollution in COVID-19 transmissibility. 25 pages, 4 figures. Environmental Research, in press (2021) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect