Table 7 Summary of hypothesis generating studies using data mining methods to generate new hypotheses to understand the relationship between air pollution and health conditions better
From: A systematic review of data mining and machine learning for air pollution epidemiology
Author | Year | Sub-field | Environmental agents | Data mining techniques | Objective |
|---|---|---|---|---|---|
Chen et al. [22] | 2010 | Outdoor air pollution | Inorganic acids & basic air pollutants | Hierarchical Clustering | Explore relationship between climate and air pollutants |
Zhu et al. [35] | 2012 | Urban outdoor air pollution | SO2, NO2, PM10, Respiratory diseases | ARM, GMDH | Forecasting the number of respiratory patients based on the seasonal effects of air pollution |
Pandy et al. [38] | 2013 | Outdoor air pollution | UFP, PM | DT, RF | Test machine learning classifiers for predicting air quality and assess the impact of weather and traffic related variables on UFP and PM. |
Payus et al. [32] | 2013 | Outdoor air pollution | SO2, NO2, PM10, CO,O3 | ARM | Find associations between combinations of air pollutants with respiratory illness. |
Bobb et al. [31] | 2014 | Mixture of chemicals | Multiple chemicals, neurodevelopment, hemodynamics | Bayesian kernel machine regression (BKMR) | Identifying mixtures (e.g., metals) and components responsible for various health effects (e.g., neurodevelopment) |
Gass et al. [20] | 2014 | Outdoor air pollution | CO, NO2, O3, PM | Classification and regression trees | Apply classification and regression trees to generate hypothesis about exposure to mixtures of pollutants and health effects. They work with children’s asthma emergency visit |
Fernández-Camacho et al. [51] | 2015 | Urban air and noise pollution by traffic | NOx, O3, SO2, Black Carbon | Fuzzy clustering | Find the relationship of noise to the traffic emission |
Bell et al. [63] | 2015 | General chemical exposure | 219 chemicals | ARM | Find relationships between chemicals and health biomarkers or diseases |
Qin et al. [53] | 2015 | Outdoor air pollution | PM | ARM | Exploring relationships of PM spatial-temporal variations and how cities influence each other |
Reid et al. [50] | 2016 | Outdoor air quality with wildfire | PM2.5 Respiratory diseases | Generalized estimating equation and generalized boosting model | Finding the relationship between wildfire and associated increment in PM2.5 affects people with respiratory diseases |
Toti et al. [36] | 2016 | Outdoor air pollution, pediatric asthma | SO2, NO, PM, NO2 | ARM | Exploring relationships of Air Pollution Exposure on Asthma |
Mirto et al. [48] | 2016 | Outdoor air pollution & climate changes | Generic | Spatial data mining, hot spot analysis | Finding correlations between diseases (e.g. respiratory and cardiovascular diseases, cancer, male human infertility) and air pollution due to climatic factors |
Li et al. [45] | 2017 | Outdoor air pollution | PM | Trajectory clustering | Apply clustering to identify transport pathways, sources and seasonal variations of particulate matter (PM2.5 and PM10) in Beijing for regulation purposes |
Stingone et al. [46] | 2017 | Outdoor air pollution | National air toxics assessment | DT | Apply machine learning to identify air pollutants exposure profiles when exploring multiple pollutants (104 ambient air toxics) and then estimate the magnitude of the profile’s effect on math scores in kindergarten children |
Ghanem et al. [69] | 2004 | Outdoor air pollution | SO2,C6H6,NO, NO2,O3 | Hierarchical clustering | Monitor chemicals and outline challenges related to collection and processing. |