Validation of questionnaire-based long-term dietary exposure to polychlorinated biphenyls using biomarkers

Scope The health consequences of lifelong low-level exposure to polychlorinated biphenyls (PCBs) via food are largely unknown, mainly due to the lack of large population-based prospective studies addressing this issue. We validated long-term food frequency questionnaire (FFQ)-based dietary PCB exposure against concentrations of six PCB congeners in serum. Methods and results Dietary PCB exposure was estimated in the Swedish Mammography Cohort by constructing a recipe-based database of CB-153, an indicator for total PCBs in food. The Spearman rank correlation (adjusted for within-person variability) was assessed between concurrent (20042006), past (1997), and long-term (mean of 1997 and 20042006) FFQ-based dietary PCB exposure, respectively, and the following serum PCB congeners, CB-118, CB-138, CB-153, CB-156, CB-170, and CB-180, in women (5685 years of age, n = 201). The correlation between FFQ-based dietary PCB exposure and serum CB-153 was 0.41 (p < 0.001) for the concurrent (median 1.6 ng/kg body weight) and 0.34 (p < 0.05) for the past (median 2.6 ng/kg body weight) exposure assessment. Long-term validity of FFQ-based PCB estimates and the six serum PCB congeners ranged from 0.30 to 0.58 (p < 0.05). Conclusion FFQ-based PCB exposure estimates show acceptable validity in relation to PCB concentrations in serum, justifying their use in large-scale epidemiological studies.