Risk of breast cancer following exposure to tetrachloroethylene-contaminated drinking water in Cape Cod, Massachusetts: reanalysis of a case-control study using a modified exposure assessment

Abstract

Background: Tetrachloroethylene (PCE) is an important occupational chemical used in metal degreasing and drycleaning and a prevalent drinking water contaminant. Exposure often occurs with other chemicals but it occurred alone in a pattern that reduced the likelihood of confounding in a unique scenario on Cape Cod, Massachusetts. We previously found a small to moderate increased risk of breast cancer among women with the highest exposures using a simple exposure model. We have taken advantage of technical improvements in publically available software to incorporate a more sophisticated determination of water flow and direction to see if previous results were robust to more accurate exposure assessment.

Methods: The current analysis used PCE exposure estimates generated with the addition of water distribution modeling software (EPANET 2.0) to test model assumptions, compare exposure distributions to prior methods, and re-examine the risk of breast cancer. In addition, we applied data smoothing to examine nonlinear relationships between breast cancer and exposure. We also compared a set of measured PCE concentrations in water samples collected in 1980 to modeled estimates.

Results: Thirty-nine percent of individuals considered unexposed in prior epidemiological analyses were considered exposed using the current method, but mostly at low exposure levels. As a result, the exposure distribution was shifted downward resulting in a lower value for the 90th percentile, the definition of "high exposure" in prior analyses. The current analyses confirmed a modest increase in the risk of breast cancer for women with high PCE exposure levels defined by either the 90th percentile (adjusted ORs 1.0-1.5 for 0-19 year latency assumptions) or smoothing analysis cut point (adjusted ORs 1.3-2.0 for 0-15 year latency assumptions). Current exposure estimates had a higher correlation with PCE concentrations in water samples (Spearman correlation coefficient = 0.65, p < 0.0001) than estimates generated using the prior method (0.54, p < 0.0001).

Conclusions: The incorporation of sophisticated flow estimates in the exposure assessment method shifted the PCE exposure distribution downward, but did not meaningfully affect the exposure ranking of subjects or the strength of the association with the risk of breast cancer found in earlier analyses. Thus, the current analyses show a slightly elevated breast cancer risk for highly exposed women, with strengthened exposure assessment and minimization of misclassification by using the latest technology.

Figure 1

Comparison of Ln Measured PCE Concentration (ug/L) with Ln Model Estimated PCE Concentration (ug/L): Automated Method. This figure depicts the relationship between measured PCE concentration and model estimated PCE concentration using the automated method. There was a moderate level of correlation between measured and modeled PCE concentrations using the automated method (Spearman rank correlation coefficient (ρ = 0.65, p < 0.0001).

Figure 2

Comparison of Ln Measured PCE Concentration (ug/L) with Ln Model Estimated PCE Concentration (ug/L): Manual Method. This figure depicts the relationship between measured PCE concentration and model estimated PCE concentration using the manual method. There was a moderate level of correlation between measured and modeled PCE concentrations using the manual method (ρ = 0.54, p < 0.001) but the magnitude of correlation was lower than that of the automated method.