Associations of Source-apportioned Fine Particles with Cause-specific Mortality in California

Abstract

Background: Exposure to ambient fine particulate matter (PM2.5) has been linked with premature mortality, but sources of PM2.5 have been less studied.

Methods: We evaluated associations between source-specific PM2.5 exposures and cause-specific short-term mortality in eight California locations from 2002 to 2011. Speciated PM2.5 measurements were source-apportioned using Positive Matrix Factorization into eight sources and combined with death certificate data. We used time-stratified case-crossover analysis with conditional logistic regression by location and meta-analysis to calculate pooled estimates.

Results: Biomass burning was associated with all-cause mortality lagged 2 days after exposure (lag2) (% changelag2 in odds per interquartile range width increase in biomass burning PM2.5 = 0.8, 95% confidence interval [CI] = 0.2, 1.4), cardiovascular (% changelag2 = 1.3, 95% CI = 0.3, 2.4), and ischemic heart disease (% changelag2 = 2.0, 95% CI = 0.6, 3.5). Vehicular emissions were associated with increases in cardiovascular mortality (% changelag0 = 1.4, 95% CI = 0.0, 2.9). Several other sources exhibited positive associations as well. Many findings persisted during the cool season. Warm season biomass burning was associated with respiratory/thoracic cancer mortality (% changelag1 = 5.9, 95% CI = 0.7, 11.3), and warm season traffic was associated with all-cause (% changelag0 = 1.9, 95% CI = 0.1, 3.6) and cardiovascular (% changelag0 = 2.9, 95% CI = 0.1, 5.7) mortality.

Conclusions: Our results suggest that acute exposures to biomass burning and vehicular emissions are linked with cardiovascular mortality, with additional sources (i.e., soil, secondary nitrate, secondary sulfate, aged sea salt, and chlorine sources) showing associations with other specific mortality types.