An Assessment of the Possible Extent of Confounding in Epidemiological Studies of Lung Cancer Risk Among Roofers

Abstract

The U.S. roofing industry employs about 200,000 workers and estimates indicate about 50,000 on-roof workers are exposed to asphalt fumes during approximately 40% of their working hours. Numerous epidemiological studies have been conducted to evaluate cancer outcomes among roofers, including exposure to asphalt/bitumen fume. However, most studies relied on job title as a surrogate for exposure to asphalt or asphalt fumes because individual exposure data were not available. Therefore, it is unclear whether reported results of an increased risk of lung cancer reflect the direct impact of asphalt exposure on employee health, or if findings are due to bias, such as the presence of other risk factors for lung cancer (i.e., “confounding” exposures) or the use of comparison populations that are inherently different with respect to lung cancer risk. We evaluated the likelihood and extent to which the observed increased risk of lung cancer may be due to confounding (a mixing of effects of multiple exposures) by co-exposure to other potential carcinogens present in roofing or to lifestyle variables. We conducted a review of the epidemiological and industrial hygiene literature of asphalt-exposed workers. Peer-reviewed epidemiological studies of asphalt fumes, related occupational exposures, and confounding factors were identified from MEDLINE (1966– early 2004). Industrial hygiene studies of asphalt workers were identified through MEDLINE, publicly available government documents, and asphalt industry documents. Using well-established statistical methods, we quantified the extent to which lung cancer relative risk estimates among roofers reflect confounding from other exposures, using different prevalence and risk scenarios. The relative risk of lung cancer varied from 1.2 to 5.0 in 13 epidemiological studies of roofers; most studies reported a relative risk between 1.2 and 1.4. Smoking, asbestos and coal tar were the most likely confounders, but the prevalence of these factors varied over time. For example, smoking prevalence declined more steadily in the general population than among roofers, and coal tar and asbestos exposures among roofers have declined over the past 50 years. Depending on prevalence estimates used, the relative risk due to confounding ranged from 1.17 to 1.52 (current smoking); 1.36 to 1.78 (asbestos); and 1.04 to 2.32 (coal tar). The results of the study indicate that much of the observed risk reported in epidemiological studies of cancer among roofers is well within the range of what may have resulted from confounding by reasonable and expected levels of smoking, asbestos or coal tar. This may be particularly true for those studies that did not adjust for these confounders and where the exposure was defined as employment in the roofing industry. In addition to poorly defined asphalt exposure, uncontrolled confounding cannot reliably be ruled out in studies of lung cancer among asphalt-exposed roofers. Therefore, it is not possible to conclude whether roofers are at increased risk of lung cancer due to asphalt exposure. Future studies of roofers will require improved quantification of asphalt/bitumen exposure and confounding factors to provide more direct evidence regarding the specific role of occupational asphalt exposure in the etiology of lung cancer among roofers.

Keywords:

• lung neoplasms
• confounding factors
• epidemiology
• asphalt
• bitumen
• roofers

ACKNOWLEDGMENTS

This project was sponsored by the Asphalt Roofing Environmental Council (AREC), a group of industry trade associations including the Asphalt Roofing Manufacturers Association (ARMA), National Roofing Contractors Association (NRCA), and the Asphalt Institute (AI). The authors would like to acknowledge the support of the AREC members and their parent companies that provided information in the field interviews, Dr. Kannan Vembu of ENVIRON International Corp. for his contributions to the field interviews, and Dr. Paolo Boffetta for providing critical comments on an earlier draft of this paper.

Notes

^A Study population is included in multicenter study by Vineis et al.^{( 59 )}

^B Cucino,^{( 62 )} Minder,^{( 64 )} Robinson,^{( 66 )} and Wang^{( 67 )} did not include risk estimates for lung cancer, and were not considered further.

^A Reference category: building and ground construction workers.