Longitudinal mercury monitoring within the Japanese and Korean communities (United States): implications for exposure determination and public health protection

Abstract

Background: Estimates of exposure to toxicants are predominantly obtained from single time-point data. Fish consumption guidance based on these data may be incomplete, as recommendations are unlikely to consider impact from factors such as intraindividual variability, seasonal differences in consumption behavior, and species consumed.

Objectives/methods: We studied populations of Korean (n = 108) and Japanese (n = 106) women living in the Puget Sound area in Washington State to estimate mercury exposure based on fish intake and hair Hg levels at two and three time points, respectively. Our goals were to examine changes in hair Hg levels, fish intake behavior, and Hg body burden over time; and to determine if data from multiple time points could improve guidance.

Results/conclusion: More than 50 fish species were consumed, with eight species representing approximately three-fourths of fish consumed by the Japanese and 10 species representing approximately four-fifths of fish intake by the Koreans. Fish species responsible for most Hg intake did not change over time; < 10 species accounted for most of the Hg body burden in each population. Longitudinal variability of hair Hg levels changed slowly across the study period. Japanese with hair Hg levels > 1.2 ppm (mean, 2.2 ppm) consumed approximately 150% more fish than those with levels < or = 1.2 ppm (mean, 0.7 ppm). However, because many participants consumed substantial amounts of fish while having hair-Hg levels < or = 1.2 ppm, the nutritional benefits offered from fish consumption should be obtainable without exceeding the RfD. We observed a 100% difference in fish intake between open-ended and 2-week recall fish consumption surveys. Open-ended survey data better represent Hg intake as determined from hair Hg levels. Single time-point fish intake data appear to be adequate for deriving guidance, but caution is warranted, as study is required to determine the significance of the different outcomes observed using the two survey time frames.

Keywords: consumption; exposure; fish; fish advisories; hair; longitudinal; mercury; reference dose; temporal.

Figure 1

Illustration of hypothetical longitudinal sampling capturing temporal variance otherwise missed by single time-point sampling. Multiple sampling could capture the full range of the process variability missed by sampling at a single time. A process that changes rapidly (blue curve) compared with the sampling frequency (dashed lines) can produce sample values that represent the full range of the process variability. When the values change slowly (black curve) compared with the sampling frequency, as was the case with the Japanese population, the samples show only part of the total variation.