A MACHINE LEARNING APPROACH TO DETECT ASSOCIATIONS BETWEEN AIR QUALITY AND ASTHMA IN URBAN ENVIRONMENTS

Abstract

Traffic and power generation constitute the primary sources of urban air pollution. The notion that outdoor air pollution can aggravate pre-existing asthma is substantiated by a substantial body of evidence accumulated over several decades, with numerous studies indicating a potential role in the onset of new asthma cases as well. This paper examines the impacts of particulate matter (PM), gaseous pollutants (ozone, nitrogen dioxide, and sulfur dioxide), and air pollution from mixed traffic sources. We concentrate on clinical studies, encompassing both epidemiological and experimental research, published within the last five years. From a mechanistic standpoint, air pollutants likely induce oxidative damage to the airways, resulting in inflammation, remodeling, and an elevated risk of sensitization. While numerous pollutants have been associated with the onset of asthma, the robustness of the evidence varies. We also examine clinical implications, policy concerns, and research deficiencies pertinent to air pollution and asthma.