Night Shift Work and Breast Cancer Incidence: Three Prospective Studies and Meta-analysis of Published Studies

Abstract

Background: It has been proposed that night shift work could increase breast cancer incidence. A 2007 World Health Organization review concluded, mainly from animal evidence, that shift work involving circadian disruption is probably carcinogenic to humans. We therefore aimed to generate prospective epidemiological evidence on night shift work and breast cancer incidence.

Methods: Overall, 522 246 Million Women Study, 22 559 EPIC-Oxford, and 251 045 UK Biobank participants answered questions on shift work and were followed for incident cancer. Cox regression yielded multivariable-adjusted breast cancer incidence rate ratios (RRs) and 95% confidence intervals (CIs) for night shift work vs no night shift work, and likelihood ratio tests for interaction were used to assess heterogeneity. Our meta-analyses combined these and relative risks from the seven previously published prospective studies (1.4 million women in total), using inverse-variance weighted averages of the study-specific log RRs.

Results: In the Million Women Study, EPIC-Oxford, and UK Biobank, respectively, 673, 28, and 67 women who reported night shift work developed breast cancer, and the RRs for any vs no night shift work were 1.00 (95% CI = 0.92 to 1.08), 1.07 (95% CI = 0.71 to 1.62), and 0.78 (95% CI = 0.61 to 1.00). In the Million Women Study, the RR for 20 or more years of night shift work was 1.00 (95% CI = 0.81 to 1.23), with no statistically significant heterogeneity by sleep patterns or breast cancer risk factors. Our meta-analysis of all 10 prospective studies included 4660 breast cancers in women reporting night shift work; compared with other women, the combined relative risks were 0.99 (95% CI = 0.95 to 1.03) for any night shift work, 1.01 (95% CI = 0.93 to 1.10) for 20 or more years of night shift work, and 1.00 (95% CI = 0.87 to 1.14) for 30 or more years.

Conclusions: The totality of the prospective evidence shows that night shift work, including long-term shift work, has little or no effect on breast cancer incidence.

Figure 1.

Relative risk of breast cancer in Million Women Study participants who worked night shifts by selected characteristics. *Relative to never night shift workers, stratified by region and with attained age as the underlying time variable and adjustment for socioeconomic status, parity and age at first birth, body mass index, alcohol intake, strenuous physical activity, family history of breast cancer, age at menarche, oral contraceptive use, smoking, living with a partner, and use of menopausal hormone therapy. Relative risks (RRs) are represented by squares (with their 95% confidence intervals [CIs] as lines), each with area inversely proportional to the variance of the log RR, thereby indicating the amount of statistical information for that particular RR.

Figure 2.

Meta-analysis of prospective studies on the risk of breast cancer in women who ever vs never worked night shifts. *All women. Study-specific relative risks (RRs) are represented by squares (with their 95% confidence intervals [CIs] as lines), each with area inversely proportional to the variance of the log RR. RRs were combined using inverse- variance-weighted averages of the log RRs in the separate studies, yielding a result and its 95% CI, which is plotted as a diamond.

Figure 3.

Meta-analysis of prospective studies on the risk of breast cancer associated with long-duration night shift work. A) Worked night shifts for 20 or more years vs never worked night shifts. B) Worked night shifts for 30 or more years vs never worked night shifts. *Results for 20 to 29 years not reported separately. †Approximate numbers, estimated from confidence limits. ‡Worked night shifts for more than 27.5 years. Study-specific relative risks (RRs) are represented by squares (with their 95% confidence intervals [CIs] as lines), each with area inversely proportional to the variance of the log RR. RRs were combined using inverse-variance-weighted averages of the log RRs in the separate studies, yielding a result and its 95% CI, which is plotted as a diamond.