Environ Health. 2009 Dec 9;8:56. doi: 10.1186/1476-069X-8-56.
The International Commission on Radiological Protection (ICRP) recommended annual occupational dose limit is 20 mSv. Cancer mortality in Japanese A-bomb survivors exposed to less than 20 mSv external radiation in 1945 was analysed previously, using a latency model with non-linear dose response. Questions were raised regarding statistical inference with this model.
Cancers with over 100 deaths in the 0 - 20 mSv subcohort of the 1950-1990 Life Span Study are analysed with Poisson regression models incorporating latency, allowing linear and non-linear dose response. Bootstrap percentile and Bias-corrected accelerated (BCa) methods and simulation of the Likelihood Ratio Test lead to Confidence Intervals for Excess Relative Risk (ERR) and tests against the linear model.
The linear model shows significant large, positive values of ERR for liver and urinary cancers at latencies from 37 - 43 years. Dose response below 20 mSv is strongly non-linear at the optimal latencies for the stomach (11.89 years), liver (36.9), lung (13.6), leukaemia (23.66), and pancreas (11.86) and across broad latency ranges. Confidence Intervals for ERR are comparable using Bootstrap and Likelihood Ratio Test methods and BCa 95% Confidence Intervals are strictly positive across latency ranges for all 5 cancers. Similar risk estimates for 10 mSv (lagged dose) are obtained from the 0 - 20 mSv and 5 - 500 mSv data for the stomach, liver, lung and leukaemia. Dose response for the latter 3 cancers is significantly non-linear in the 5 - 500 mSv range.
Liver and urinary cancer mortality risk is significantly raised using a latency model with linear dose response. A non-linear model is strongly superior for the stomach, liver, lung, pancreas and leukaemia. Bootstrap and Likelihood-based confidence intervals are broadly comparable and ERR is strictly positive by bootstrap methods for all 5 cancers. Except for the pancreas, similar estimates of latency and risk from 10 mSv are obtained from the 0 - 20 mSv and 5 - 500 mSv subcohorts. Large and significant cancer risks for Japanese survivors exposed to less than 20 mSv external radiation from the atomic bombs in 1945 cast doubt on the ICRP recommended annual occupational dose limit.
国际辐射防护委员会（ICRP）建议的年职业剂量限值为 20mSv。此前，曾使用具有非线性剂量反应的潜伏期模型分析过 1945 年遭受小于 20mSv 外照射的日本原子弹幸存者的癌症死亡率。人们对该模型的统计推断提出了质疑。
使用包含潜伏期的泊松回归模型分析了 1950-1990 年寿命研究中 0-20mSv 亚组中癌症死亡人数超过 100 人的队列，允许线性和非线性剂量反应。使用自举百分位和偏差校正加速（BCa）方法以及似然比检验模拟，得出超额相对风险（ERR）的置信区间，并对线性模型进行检验。
线性模型显示，在潜伏期为 37-43 年时，肝脏和泌尿系统癌症的 ERR 值显著较大且为正。在胃（11.89 年）、肝脏（36.9）、肺（13.6）、白血病（23.66）和胰腺（11.86）的最佳潜伏期以及广泛的潜伏期范围内，低于 20mSv 的剂量反应呈强烈非线性。使用自举和似然比检验方法，ERR 的置信区间是可比的，BCa95%置信区间在所有 5 种癌症的潜伏期范围内均为正。对于胃、肝、肺和白血病，从 0-20mSv 和 5-500mSv 数据中得到了 10mSv（滞后剂量）的相似风险估计值。对于后三种癌症，在 5-500mSv 范围内，剂量反应呈显著非线性。
使用具有线性剂量反应的潜伏期模型，肝脏和泌尿系统癌症的死亡率风险显著增加。对于胃、肝、肺、胰腺和白血病，非线性模型具有明显优势。自举和基于似然的置信区间在所有 5 种癌症中广泛可比，并且自举方法的 ERR 为正。除了胰腺，从 0-20mSv 和 5-500mSv 亚组中可以获得日本幸存者在 1945 年原子弹爆炸中受到的小于 20mSv 外照射的潜伏期和风险的相似估计值。1945 年遭受小于 20mSv 外照射的日本幸存者的癌症风险较大且显著，这对 ICRP 建议的年职业剂量限值提出了质疑。
