Use of machine learning algorithms to determine the relationship between air pollution and cognitive impairment in Taiwan.

Air pollution has become a major global threat to human health. Urbanization and industrialization over the past few decades have increased the air pollution. Plausible connections have been made between air pollutants and dementia. This study used machine learning algorithms (k-nearest neighbors, random forest, gradient-boosted decision trees, eXtreme gradient boosting, and CatBoost) to investigate the association between cognitive impairment and air pollution. Data from the Taiwan Biobank and 75 air-pollution-monitoring stations in Taiwan were analyzed to determine individual levels of exposure to air pollutants. The pollutants examined were particulate matter with a diameter of ≤ 2.5 µm (PM2.5), nitrogen dioxide, nitric oxide, carbon monoxide, and ozone. The results revealed that the most strongly correlated with cognitive impairment were ozone, PM2.5, and carbon monoxide levels with adjustment of educational level, age, and household income. The model based on these factors achieved accuracy as high as 0.97 for detecting cognitive impairment, indicating a positive association between air pollutions and cognitive impairment.

Mediation analysis for TNF-α as a mediator between multiple metal exposure and kidney function.

The association between metal mixtures and kidney function has been reported. However, reports on the mechanism of metal toxicity were limited. Oxidative stress was reported as a possible cause. This study aimed to determine the association between of kidney function and metals, such as arsenic (As), cadmium (Cd), cobalt (Co), copper (Cu), lead (Pb), selenium (Se), and zinc (Zn), and to explore the possible mediating role of tumor necrosis factor alpha (TNF-α) between metal toxicity and kidney function. In this study, we recruited 421 adults from a health examination. The concentration of blood metals was analyzed using inductively coupled plasma mass spectrometry. We used linear regression models to assess the association between metals and TNF-α. Then, mediation analysis was applied to investigate the relationship between metal exposure, TNF-α, and kidney function. In univariate linear regression, blood As, Cd, Co, Cu, Pb, and Zn levels significantly increased TNF-α and decreased kidney function. Higher blood As and Pb levels significantly increased TNF-α in multivariable linear regressions after adjusting for covariates. We found that blood levels of As (coefficients = -0.021, p = 0.011), Pb (coefficients = -0.060, p < 0.001), and Zn (coefficients = -0.230, p < 0.001) showed a significant negative association with eGFR in the multiple-metal model. Furthermore, mediation analysis showed that TNF-α mediated 41.7 %, 38.8 %, and 20.8 % of blood Cd, As and Pb, respectively. Among the essential elements, TNF-α mediated 24.5 %, 21.5 % and 19.9 % in the effects of blood Co, Cu, and Zn on kidney function, respectively. TNF-α, acting as a mediator, accounted for 20.1 % of the contribution between the WQS score of metal mixtures and the eGFR (p < 0.001). This study suggested that TNF-α may be a persuasive pathway mediating the association between metals and kidney function. Inflammation and kidney injury could be the underlying mechanisms of metal exposure. However, there is still a need to clarify the biochemical mechanism in follow-up studies.