Cancer incidence in atomic bomb survivors. Part IV: Comparison of cancer incidence and mortality

Abstract

This report compares cancer incidence and mortality among atomic bomb survivors in the Radiation Effects Research Foundation Life Span Study (LSS) cohort. Because the incidence data are derived from the Hiroshima and Nagasaki tumor registries, case ascertainment is limited to the time (1958-1987) and geographic restrictions (Hiroshima and Nagasaki) of the registries, whereas mortality data are available from 1950-1987 anywhere in Japan. With these conditions, there were 9,014 first primary incident cancer cases identified among LSS cohort members compared with 7,308 deaths for which cancer was listed as the underlying cause of death on death certificates. When deaths were limited to those occurring between 1958-1987 in Hiroshima or Nagasaki, there were 3,155 more incident cancer cases overall, and 1,262 more cancers of the digestive system. For cancers of the oral cavity and pharynx, skin, breast, female and male genital organs, urinary system and thyroid, the incidence series was at least twice as large as the comparable mortality series. Although the incidence and mortality data are dissimilar in many ways, the overall conclusions regarding which solid cancers provide evidence of a significant dose response generally confirm the mortality findings. When either incidence or mortality data are evaluated, significant excess risks are observed for all solid cancers, stomach, colon, liver (when it is defined as primary liver cancer or liver cancer not otherwise specified on the death certificate), lung, breast, ovary and urinary bladder. No significant radiation effect is seen for cancers of the pharynx, rectum, gallbladder, pancreas, nose, larynx, uterus, prostate or kidney in either series. There is evidence of a significant excess of nonmelanoma skin cancer in the incidence data, but not in the mortality series. Cancers of the salivary gland and thyroid are also in excess in the incidence series, but they were not evaluated in the earlier mortality analyses. For all solid tumors the estimated excess relative risk at 1 Sv (ERR1Sv) for incidence (ERR1Sv = 0.63) is 40% larger than the excess relative risk (ERR) based on mortality data from 1950-1987 in all Japan (ERR1Sv = 0.45). The corresponding excess absolute risk (EAR) point estimate is 2.7 times greater for incidence than mortality. For some cancer sites, the difference in the magnitude of risk between incidence and mortality is greater. These differences reflect the greater diagnostic accuracy of the incidence data and the lack of full representation of radiosensitive but relatively nonfatal cancers, such as breast and thyroid, in the mortality data. Analyses of both incidence and mortality data are needed since the two end points provide complementary information for risk assessment.