Dietary patterns explaining differences in bone mineral density and hip structure in the elderly: the Rotterdam Study

Abstract

Background: Evidence on the association between dietary patterns, measures of hip bone geometry, and subsequent fracture risk are scarce.

Objective: The objective of this study was to evaluate whether dietary patterns that explain most variation in bone mineral density (BMD) and hip bone geometry are associated with fracture risk.

Design: We included 4028 subjects aged ≥55 y from the Rotterdam study. Intake of 28 food groups was assessed with the use of food-frequency questionnaires. BMD, bone width, section modulus (SM; reflecting bending strength) and cortical buckling ratio (BR; reflecting bone instability) were measured with the use of dual-energy X-ray absorptiometry. BMD and geometry-specific dietary patterns were identified with the use of reduced rank regression. Fracture data were reported by general practitioners (median follow-up 14.8 y).

Results: We identified 4 dietary patterns. Of the 4, we named 2 patterns "fruit, vegetables, and dairy" and "sweets, animal fat, and low meat," respectively. These 2 patterns were used for further analysis. Independently of confounders, adherence to the fruit, vegetables, and dairy pattern was associated with high BMD, high SM, low BR, and low risk of fractures [HR (95% CI) for osteoporotic fractures: 0.90 (0.83, 0.96); for hip fractures: 0.85 (0.81, 0.89) per z score of dietary pattern adherence]. Adherence to the sweets, animal fat, and low meat pattern was associated with high bone width, high SM, high BR, and high risk of fractures [HR (95% CI) for osteoporotic fractures: 1.08 (1.00, 1.06); for hip fractures: 1.06 (1.02, 1.12) per z score].

Conclusion: The fruit, vegetables, and dairy pattern might be associated with lower fracture risk because of high BMD, high bending strength, and more stable bones. The sweets, animal fat, and low meat pattern might be associated with higher fracture risk because of widened, unstable bones, independently of BMD. Dietary recommendations associated with bone geometry in addition to BMD might influence risk of fractures.

Keywords: dietary patterns; elderly; fractures; hip bone macro geometry; reduced rank regression.