Effects of particulate air pollution on cardiovascular health: a population health risk assessment

Abstract

Particulate matter (PM) air pollution is increasingly recognized as an important and modifiable risk factor for adverse health outcomes including cardiovascular disease (CVD). However, there are still gaps regarding large population risk assessment. Results from the nationwide Behavioral Risk Factor Surveillance System (BRFSS) were used along with air quality monitoring measurements to implement a systematic evaluation of PM-related CVD risks at the national and regional scales. CVD status and individual-level risk factors were collected from more than 500,000 BRFSS respondents across 2,231 contiguous U.S. counties for 2007 and 2009. Chronic exposures to PM pollutants were estimated with spatial modeling from measurement data. CVD outcomes attributable to PM pollutants were assessed by mixed-effects logistic regression and latent class regression (LCR), with adjustment for multicausality. There were positive associations between CVD and PM after accounting for competing risk factors: the multivariable-adjusted odds for the multiplicity of CVD outcomes increased by 1.32 (95% confidence interval: 1.23-1.43) and 1.15 (1.07-1.22) times per 10 µg/m(3) increase in PM(2.5) and PM(10) respectively in the LCR analyses. After controlling for spatial confounding, there were moderate estimated effects of PM exposure on multiple cardiovascular manifestations. These results suggest that chronic exposures to ambient particulates are important environmental risk factors for cardiovascular morbidity.

Figure 1. A schematic depiction of the multilevel latent class regression model.

Figure 2. Estimated background PM₁₀ and PM_2.5 concentrations (µg/m³) across contiguous U.S. counties.

A—PM₁₀ yearly median concentrations (averaging 1999–2005), assessed with ordinary kriging, exponential covariance, lag distance = 125 km, nugget = 0.037, range = 1,538 km, partial sill = 0.083; B—PM_2.5 yearly median concentrations (averaging 1999–2005), assessed with ordinary kriging, spherical covariance, lag distance = 170 km, nugget = 0.014, range = 1,687 km, partial sill = 0.066.

Figure 3. Multivariable-adjusted odds ratios (AOR) and lower and upper 95% confidence limits (LCL & UCL) for CVD complications from PM₁₀-fitted models —assessed with samples from the 2007 and 2009 Behavioral Risk Factor Surveillance System.

Both regionally and non-regionally adjusted results were presented, with the former graphically displayed. BMI and (BMI-squared)/100 were included as continuous variables. PM₁₀-related effects were associated with 10 µg/m³ increment in yearly median levels.

Figure 4. Multivariable-adjusted odds ratios (AOR) and lower and upper 95% confidence limits (LCL & UCL) for CVD complications from PM_2.5-fitted models —assessed with samples from the 2007 and 2009 Behavioral Risk Factor Surveillance System.

Both regionally and non-regionally adjusted results were presented, with the former graphically displayed. BMI and (BMI-squared)/100 were included as continuous variables. PM_2.5-related effects were associated with 10 µg/m³ increment in yearly median levels.

Figure 5. Region-specific multivariable-adjusted odds ratios (AOR) and lower and upper 95% confidence limits (LCL & UCL) per 10 µg/m³ increment in PM for CVD complications, controlling for age, gender, race, education, income, smoking status, physical activeness, BMI (linear and quadratic terms), hypertension, hypercholesteraemia, diabetes, and year of interview.