Overdiagnosis among women attending a population-based mammography screening program

Abstract

Increased incidence of ductal carcinoma in situ (DCIS) and invasive breast cancer (IBC) after introduction of organized screening has prompted debate about overdiagnosis. The aim was to examine the excess in incidence of DCIS and IBC during the screening period and the deficit after women left the program, and thereby to estimate the proportion of overdiagnosis. Women invited to the Norwegian Breast Cancer Screening Program were analyzed for DCIS or IBC during the period 1995-2009. Incidence rate ratios (IRRs) were calculated for attended vs. never attended women. The IRRs were adjusted by Mantel-Haenszel (MH) method and applied to a set of reference rates and a reference population to estimate the proportion of overdiagnosis during the women's lifespan after the age of 50 years. A total of 702,131 women were invited to the program. An excess of DCIS and IBC was observed among women who attended screening during the screening period; prevalently invited women aged 50-51 years had a MH IRR of 1.86 (95% CI 1.65-2.09) and subsequently invited women aged 52-69 years had a MH IRR of 1.56 (95% CI 1.45-1.68). In women aged 70-79 years, a deficit of 30% (MH IRR 0.70, 95% CI 0.62-0.80) was observed 1-10 years after they left the screening program. The estimated proportion of overdiagnosis varied from 10 to 20% depending on outcome and whether the women were invited or actually screened. The results highlight the need for individual data with longitudinal screening history and long-term follow-up as a basis for estimating overdiagnosis.

Figure 1

Attendance (%) by age for prevalently and subsequently invited women to the Norwegian Breast Cancer Screening Program.

Figure 2

Incidence of DCIS and IBC (a) and IBC (b) per 100,000 women-years by age at diagnosis. Solid line: reference (period approach). Dotted line: reference multiplied with the MH IRRs. Abbreviations: DCIS: ductal carcinoma in situ; IBC: invasive breast cancer; MH IRR: incidence rate ratio of attending vs. never-attending women adjusted by county and calendar period using the Mantel-Haenszel method.