Background: Communities need to efficiently estimate the burden from specific pollutants and identify those most at risk to make timely informed policy decisions. We developed a risk-based model to estimate the burden of black carbon (BC) and nitrogen dioxide (NO 2) on coronary heart disease (CHD) across environmental justice (EJ) and non-EJ populations in Allegheny County, PA. Methods: Exposure estimates in census tracts were modeled via land use regression and analyzed in relation to US Census data. Tracts were ranked into quartiles of exposure (Q1-Q4). A risk-based model for estimating the CHD burden attributed to BC and NO 2 was developed using county health statistics, census tract level exposure estimates, and quantitative effect estimates available in the literature. Results: For both pollutants, the relative occurrence of EJ tracts (> 20% poverty and/or > 30% non-white minority) in Q2-Q4 compared to Q1 progressively increased and reached a maximum in Q4. EJ tracts were 4 to 25 times more likely to be in the highest quartile of exposure compared to the lowest quartile for BC and NO 2 , respectively. Pollutantspecific risk values (mean [95% CI]) for CHD mortality were higher in EJ tracts (5.49 × 10 − 5 [5.05 × 10 − 5-5.92 × 10 − 5 ]; 5.72 × 10 − 5 [5.44 × 10 − 5-6.01 × 10 − 5 ] for BC and NO 2 , respectively) compared to non-EJ tracts (3.94 × 10 − 5 [3.66 × 10 − 5-4.23 × 10 − 5 ]; 3.49 × 10 − 5 [3.27 × 10 − 5-3.70 × 10 − 5 ] for BC and NO 2 , respectively). While EJ tracts represented 28% of the county population, they accounted for about 40% of the CHD mortality attributed to each pollutant. EJ tracts are disproportionately skewed toward areas of high exposure and EJ residents bear a greater risk for air pollution-related disease compared to other county residents. Conclusions: We have combined a risk-based model with spatially resolved long-term exposure estimates to predict CHD burden from air pollution at the census tract level. It provides quantitative estimates of effects that can be used to assess possible health disparities, track temporal changes, and inform timely local community policy decisions. Such an approach can be further expanded to include other pollutants and adverse health endpoints.