The effect of body weight on tumor incidence and carcinogenicity testing in B6C3F1 mice and F344 rats.

Associations between animal body weights and tumor incidence were examined using individual control animal data from 55 mouse and 53 rat studies conducted by the National Toxicology Program. Several statistically significant associations were found, the strongest of which were positive relationships between body weight and risk of liver tumors in both sexes of mice, pituitary gland tumors in both sexes of rats, and mammary gland tumors in female rats. The most compelling evidence that these relationships were causal in nature was the replication of the correlations across individual experiments. In addition, significant correlations between tumor occurrence and body weights occurred in animals as young as 9 weeks of age. Logistic regression models relating 12-month body weight to tumor risk were developed for the strongest relationships, and utilized in the reanalysis of tumor data from two National Toxicology Program studies with treatment-related decreases in body weight. A simulation study based on the logistic regression models indicated that statistical power to detect a treatment-related increase in tumor incidence can be seriously diminished when mean body weight in treated animals is depressed by as little as 10%. Conversely, when mean body weight in control animals is 10% lower than that of treated animals, false positive rates can increase to 20-30%. The severity of the effects of such commonly observed treatment-related disparities in body weight suggests that alternative data analysis methods or experimental designs should be considered to address this potential problem in carcinogenicity testing.