Institute of Environmental, Chemical and Pharmaceutical Sciences, Federal University of Sao Paulo (UNIFESP), Diadema 09913030, Brazil.
Int J Environ Res Public Health. 2023 Apr 11;20(8):5458. doi: 10.3390/ijerph20085458.
Traditionally, studies that associate air pollution with health effects relate individual pollutants to outcomes such as mortality or hospital admissions. However, models capable of analyzing the effects resulting from the atmosphere mixture are demanded. In this study, multilayer perceptron neural networks were evaluated to associate PM, NO, and SO concentrations, temperature, wind speed, and relative air humidity with cardiorespiratory mortality among the elderly in São Paulo, Brazil. Daily data from 2007 to 2019 were considered and different numbers of neurons on the hidden layer, algorithms, and a combination of activation functions were tested. The best-fitted artificial neural network (ANN) resulted in a MAPE equal to 13.46%. When individual season data were analyzed, the MAPE decreased to 11%. The most influential variables in cardiorespiratory mortality among the elderly were PM and NO concentrations. The relative humidity variable is more important during the dry season, and temperature is more important during the rainy season. The models were not subjected to the multicollinearity issue as with classical regression models. The use of ANNs to relate air quality to health outcomes is still very incipient, and this work highlights that it is a powerful tool that should be further explored.
传统上，将空气污染与健康影响相关联的研究将个别污染物与死亡率或住院率等结果相关联。然而，需要能够分析大气混合物产生的影响的模型。在这项研究中，评估了多层感知器神经网络，以将 PM、NO 和 SO 浓度、温度、风速和相对空气湿度与巴西圣保罗老年人的心肺死亡率相关联。考虑了 2007 年至 2019 年的每日数据，并测试了不同数量的隐藏层神经元、算法和激活函数的组合。最佳拟合的人工神经网络 (ANN) 的平均绝对百分比误差 (MAPE) 等于 13.46%。当分析个别季节数据时，MAPE 下降到 11%。对老年人心肺死亡率影响最大的变量是 PM 和 NO 浓度。相对湿度变量在旱季更为重要，温度在雨季更为重要。与经典回归模型不同，这些模型没有受到多重共线性问题的影响。使用神经网络将空气质量与健康结果相关联的应用仍处于起步阶段，这项工作强调了它是一种强大的工具，应该进一步探索。
