Prospective Associations of Body Composition and Body Shape With the Risk of Developing Pancreatic Cancer in the UK Biobank Cohort

Background: Obesity and diabetes are positively associated with pancreatic cancer risk. It is unclear, however, whether fat or fat-free mass plays a role in these relationships, whether abdominal obesity is more important than general obesity or whether the associations with anthropometric indices and diabetes are independent of each other. Methods: We used multivariable Cox proportional hazards models to examine the prospective associations of body composition (allometric fat-mass index (AFI) and allometric lean-mass index (ALI), based on bioelectrical impedance, uncorrelated with each other and with height), waist size (allometric waist-to-hip index (WHI), uncorrelated with weight and height) and diabetes with pancreatic cancer risk in UK Biobank. We tested heterogeneity by sex, age and follow-up time with the augmentation method (p_het). Results: During a mean follow-up of 10.4 years, 999 pancreatic cancer cases were ascertained in 427,939 participants. AFI was positively associated with pancreatic cancer risk in participants overall, independent of ALI, WHI, diabetes and covariates (hazard ratio HR = 1.102; 95% confidence interval CI = 1.033-1.176 per 1 standard deviation (SD) increase), more strongly in women aged under 55 years at recruitment (HR = 1.457; 95% CI = 1.181-1.797; p_het = 0.007) and in men only for follow-up 6 years or longer (HR = 1.159; 95% CI = 1.037-1.295; p_het = 0.075). ALI was positively associated with pancreatic cancer risk in participants overall (HR = 1.072; 95% CI = 1.005-1.145), more specifically in men (HR = 1.132; 95% CI = 1.035-1.238; p_het = 0.091). A positive association of WHI with pancreatic cancer risk was observed only in unadjusted models but was lost after adjustment for smoking status and diabetes. Independent of anthropometric indices, diabetes was associated positively with pancreatic cancer risk in participants overall (HR = 1.688; 95% CI = 1.365-2.087), but in women only for follow-up under 6 years (HR = 2.467; 95% CI = 1.477-4.121; p_het = 0.042). Conclusions: General obesity (reflected in AFI and ALI) and diabetes but not abdominal obesity were associated positively with pancreatic cancer risk, independent of each other and covariates.