High blood pressure and long-term exposure to indoor noise and air pollution from road traffic

Abstract

Background: Traffic noise has been associated with prevalence of hypertension, but reports are inconsistent for blood pressure (BP). To ascertain noise effects and to disentangle them from those suspected to be from traffic-related air pollution, it may be essential to estimate people's noise exposure indoors in bedrooms.

Objectives: We analyzed associations between long-term exposure to indoor traffic noise in bedrooms and prevalent hypertension and systolic (SBP) and diastolic (DBP) BP, considering long-term exposure to outdoor nitrogen dioxide (NO2).

Methods: We evaluated 1,926 cohort participants at baseline (years 2003-2006; Girona, Spain). Outdoor annual average levels of nighttime traffic noise (Lnight) and NO2 were estimated at postal addresses with a detailed traffic noise model and a land-use regression model, respectively. Individual indoor traffic Lnight levels were derived from outdoor Lnight with application of insulations provided by reported noise-reducing factors. We assessed associations for hypertension and BP with multi-exposure logistic and linear regression models, respectively.

Results: Median levels were 27.1 dB(A) (indoor Lnight), 56.7 dB(A) (outdoor Lnight), and 26.8 μg/m3 (NO2). Spearman correlations between outdoor and indoor Lnight with NO2 were 0.75 and 0.23, respectively. Indoor Lnight was associated both with hypertension (OR = 1.06; 95% CI: 0.99, 1.13) and SBP (β = 0.72; 95% CI: 0.29, 1.15) per 5 dB(A); and NO2 was associated with hypertension (OR = 1.16; 95% CI: 0.99, 1.36), SBP (β = 1.23; 95% CI: 0.21, 2.25), and DBP (β⊇= 0.56; 95% CI: -0.03, 1.14) per 10 μg/m3. In the outdoor noise model, Lnight was associated only with hypertension and NO2 with BP only. The indoor noise-SBP association was stronger and statistically significant with a threshold at 30 dB(A).

Conclusion: Long-term exposure to indoor traffic noise was associated with prevalent hypertension and SBP, independently of NO2. Associations were less consistent for outdoor traffic Lnight and likely affected by collinearity.

Figure 1

Estimated change in prevalent hypertension per increment of 5 dB(A) in annual average levels of nighttime indoor traffic noise at the bedroom by subgroups of population characteristics (n = 1,926). P50, 50th percentile. Each multivariate logistic regression model was adjusted for the corresponding interaction term, one at a time, and annual average NO₂ levels, age, age squared, sex, education, Mediterranean diet, exercise, alcohol consumption, smoking, BMI, diabetes, deprivation, daily temperature, and indoor railway L_night.