摘要：The rising prevalence of overweight and obesity is partly due to nutrition transition. The reported association between dietary patterns and overweight/obesity has been controversial because of inconsistent results and weak observed associations. Although it has been hypothesized that an unhealthy diet can increase obesity risk, none of the previous studies have examined the dose–response association using nonlinear dose–response analyses. This study aimed to examine the dose–response association between major dietary patterns and overweight/obesity. This was a cross-sectional study involving teachers selected through stratified multistage sampling from public schools in three Malaysian states. Dietary intake was assessed using a food frequency questionnaire, and two major dietary patterns (Western and Prudent diet) were extracted using factor analysis. Logistic regression followed by trend analysis was used to test the difference in odds of overweight and obesity in each quintile of diet score. A further analysis using restricted cubic spline models was performed to examine the dose–response associations of dietary patterns with odds of overweight/obesity. The logistic regression analysis showed that participants with the highest quintile of Western diet score were 1.4 times more likely to be overweight/obese compared to those in the lowest quintile (95% CI: 1.11, 1.83, p-trend < 0.001). The odds of overweight/obesity showed a significant increasing trend across quintiles of Western diet among both men and women (p-trend < 0.001). In the dose–response analysis, a positive linear association (Pnonlinearity = 0.6139) was observed where overweight/obesity was more likely to occur among participants with a Western diet score greater than a mean score of zero. There was an inverse trend of odds of overweight/obesity across quintiles of Prudent diet score, significant only for men (p for trend < 0.001). Linear association was found between Prudent diet score and odds of overweight/obesity among both men (Pnonlinearity = 0.6685) and women (Pnonlinearity = 0.3684) in the dose–response analysis. No threshold at the level of adherence to Prudent diet was linked to odds of overweight/obesity. Dose–response analysis indicated that women with a Western diet score greater than zero were more likely to be overweight or obese among women. In men, higher adherence to Western diet was associated with increased odds of overweight/obesity, while greater adherence to Prudent diet decreased the odds of overweight/obesity. Promoting and enhancing the consumption of Prudent diet and limit in Western diet may be used to guide the development of evidence-based diet interventions to curb overweight and obesity.
