Air pollution epidemiology: A simplified Generalized Linear Model approach optimized by bio-inspired metaheuristics.

Studies in air pollution epidemiology are of paramount importance in diagnosing and improve life quality. To explore new methods or modify existing ones is critical to obtain better results. Most air pollution epidemiology studies use the Generalized Linear Model, especially the default version of R, Splus, SAS, and Stata softwares, which use maximum likelihood estimators in parameter optimization. Also, a smooth time function (usually spline) is generally used as a pre-processing step to consider seasonal and long-term tendencies. This investigation introduces a new approach to GLM, proposing the estimation of the free coefficients through bio-inspired metaheuristics - Particle Swarm Optimization (PSO), Genetic Algorithms, and Differential Evolution, as well as the replacement of the spline function by a simple normalization procedure. The considered case studies comprise three important cities of São Paulo state, Brazil with distinct characteristics: São Paulo, Campinas, and Cubatão. We considered the impact of particles with an aerodynamic diameter less than 10 µm (PM10), ambient temperature, and relative humidity in the number of hospital admissions for respiratory diseases (ICD-10, J00 to J99). The results showed that the new approach (especially PSO) brings performance gains compared to the default version of statistical software like R.

Assessing the impact of PM2.5 on respiratory disease using artificial neural networks.

Understanding the impact on human health during peak episodes in air pollution is invaluable for policymakers. Particles less than PM2.5 can penetrate the respiratory system, causing cardiopulmonary and other systemic diseases. Statistical regression models are usually used to assess air pollution impacts on human health. However, when there are databases missing, linear statistical regression may not process well and alternative data processing should be considered. Nonlinear Artificial Neural Networks (ANN) are not employed to research environmental health pollution even though another advantage in using ANN is that the output data can be expressed as the number of hospital admissions. This research applied ANN to assess the impact of air pollution on human health. Three well-known ANN were tested: Multilayer Perceptron (MLP), Extreme Learning Machines (ELM) and Echo State Networks (ESN), to assess the influence of PM2.5, temperature, and relative humidity on hospital admissions due to respiratory diseases. Daily PM2.5 levels were monitored, and hospital admissions for respiratory illness were obtained, from the Brazilian hospital information system for all ages during two sampling campaigns (2008-2011 and 2014-2015) in Curitiba, Brazil. During these periods, the daily number of hospital admissions ranged from 2 to 55, PM2.5 concentrations varied from 0.98 to 54.2 µg m-3, temperature ranged from 8 to 26 °C, and relative humidity ranged from 45 to 100%. Of the ANN used in this study, MLP gave the best results showing a significant influence of PM2.5, temperature and humidity on hospital attendance after one day of exposure. The Anova Friedman's test showed statistical difference between the appliance of each ANN model (p < .001) for 1 lag day between PM2.5 exposure and hospital admission. ANN could be a more sensitive method than statistical regression models for assessing the effects of air pollution on respiratory health, and especially useful when there is limited data available.