Perceived stress and coping strategies in relation to body mass index: cross-sectional study of 12,045 Japanese men and women

Abstract

Background: Accumulated evidence suggests a weak positive relationship between psychosocial stress and body mass index (BMI), but little is known about stress coping strategies and BMI.

Objective: We aimed to examine if perceived stress and coping strategies are related to BMI, with any of their mutual interactions on BMI.

Methods: This cross-sectional study included 5,063 men and 6,982 women aged 40-69 years. A self-administered questionnaire ascertained perceived stress and 5 items of coping strategies (emotion expression, emotional support seeking, positive reappraisal, problem solving, and disengagement). Analyses were performed by gender with adjustment for age, socioeconomic status, and lifestyle factors.

Results: No significant associations were detected between perceived stress and BMI in either men (P(trend) = 0.09) or women (P(trend) = 0.58). In men, however, 'disengagement' showed an inverse association with BMI (P(trend) < 0.001), and 'positive reappraisal' and 'problem solving' revealed a positive association with BMI (P(trend) = 0.04 and 0.007, respectively) even after controlling for perceived stress. A possible interaction between perceived stress and 'disengagement' on BMI was found in men (P(interaction) = 0.027); the inverse association between 'disengagement' and BMI was more evident in higher levels of stress (β = -0.13, P(trend) = 0.21 in low; β = -0.22, P(trend) = 0.01 in medium; and β = -0.24, P(trend) = 0.06 in high). In men, 'disengagement' was inversely associated with overweight/obesity (odds ratio 0.79, 95% confidential interval 0.67-0.95), and "positive reappraisal" was positively associated with it (1.25, 1.02-1.54).

Conclusions: Coping strategies may have an important role in developing overweight/obesity, particularly in men.

Fig 1. Adjusted means of body mass index (BMI) by levels of selected coping strategies and by perceived stress levels in men.

β represent regression coefficients in kg/m². Adjustment was made for age, socio-economic status (occupation, working hours, and years of schooling), and lifestyle factors (drinking, smoking, physical activity level, sleeping hours, and energy intake). P values for trend were estimated from multiple linear regression analysis including in the model an ordinal variable (1–3 assigned to low, medium, and high levels, respectively) for each coping strategy. Symbols show means and error bars represent 95% confidential intervals.