The association between body fatness and mortality among breast cancer survivors: results from a prospective cohort study

Abstract

Evidence linking body fatness to breast cancer (BC) prognosis is limited. While it seems that excess adiposity is associated with poorer BC survival, there is uncertainty over whether weight changes reduce mortality. This study aimed to assess the association between body fatness and weight changes pre- and postdiagnosis and overall mortality and BC-specific mortality among BC survivors. Our study included 13,624 BC survivors from the European Prospective Investigation into Cancer and Nutrition (EPIC) study, with a mean follow-up of 8.6 years after diagnosis. Anthropometric data were obtained at recruitment for all cases and at a second assessment during follow-up for a subsample. We measured general obesity using the body mass index (BMI), whereas waist circumference and A Body Shape Index were used as measures of abdominal obesity. The annual weight change was calculated for cases with two weight assessments. The association with overall mortality and BC-specific mortality were based on a multivariable Cox and Fine and Gray models, respectively. We performed Mendelian randomization (MR) analysis to investigate the potential causal association. Five-unit higher BMI prediagnosis was associated with a 10% (95% confidence interval: 5-15%) increase in overall mortality and 7% (0-15%) increase in dying from BC. Women with abdominal obesity demonstrated a 23% (11-37%) increase in overall mortality, independent of the association of BMI. Results related to weight change postdiagnosis suggested a U-shaped relationship with BC-specific mortality, with higher risk associated with losing weight or gaining > 2% of the weight annually. MR analyses were consistent with the identified associations. Our results support the detrimental association of excess body fatness on the survival of women with BC. Substantial weight changes postdiagnosis may be associated with poorer survival.

Keywords: Body fatness; Breast cancer survivors; Breast cancer-specific mortality; Mortality; Prospective study; Weight change.

Fig. 1

Non parametric estimates of the cumulative incidence curves for overall mortality (a) and breast cancer-specific mortality (b)

Fig. 2

Restricted cubic spline models for post-diagnosis annual percentage of weight change. Footnote: a Hazard Ratios from the multivariable restricted cubic spline Cox regression model further adjusted by pre-diagnosis Body Mass Index and time from diagnosis to second weight assessment. b Subdistribution Hazard Ratios from the multivariable restricted cubic spline Fine and Gray regression model further adjusted by Body Mass Index and time from diagnosis to second weight assessment. Knot locations were based on Harrell’s recommended percentiles (P10, P50, P90)