Multi-trajectories of BMI, waist circumference, gut microbiota, and incident dyslipidemia: a 27-year prospective study

Abstract

Evidence is insufficient to establish a longitudinal association between combined trajectories of body mass index (BMI) and waist circumference (WC) and dyslipidemia. This study investigated the associations between multi-trajectories of BMI and WC over 24 years and the subsequent risk of dyslipidemia in a large cohort of 10,678 Chinese adults from the China Health and Nutrition Survey. Utilizing a group-based trajectory model, we identified four distinct trajectories: normal, normal-increasing, overweight-increasing, and obesity-increasing. Our results indicated that ascending trajectories of BMI and WC are significantly associated with increased odds of dyslipidemia, particularly in males, with odds ratios (OR) of 2.10, 2.69, and 3.56 for the normal-increasing, overweight-increasing, and obesity-increasing groups, respectively. Among females, the normal-increasing group exhibited a significant increased risk (OR: 1.54). Furthermore, we explored the gut microbiota associated with these trajectories, identifying 3, 8, and 4 bacterial genera linked to increasing BMI and WC in males, alongside two genera in females with the normal-increasing trajectory. We identified a total of 23, 25, and 10 differential metabolites significantly associated with these genera, except for Group 2 in males. The inclusion of relevant microbiome and metabolite data improved the model's predictive capacity for the risk of dyslipidemia, with ROC values increasing from 0.655 to 0.875. Our findings underscore the critical implications of continuous weight gain on metabolic health and suggest that gut microbiota may play a pivotal role in understanding these associations.IMPORTANCEEmerging evidence suggests a close connection between the gut microbiome and both human obesity and dyslipidemia, suggesting that the gut microbiome may play an important role in the obesity-dyslipidemia relationship. In this study, we observed several characteristic genera, including Clostridium_sensu_stricto_1, Turicibacter, and CHKCI002 among males and Parabacteroides and [Eubacterium]_brachy_group among females, which were negatively associated with high-risk trajectories. They were also related to free fatty acids (FFAs) and oxidized lipid metabolites. These shared and unique gut microbial and metabolic signatures among combined trajectories of BMI and WC with a higher risk of dyslipidemia could provide important evidence for the omics mechanism pathway of long-term obesity trend leading to dyslipidemia.

Keywords: body mass index; dyslipidemia; gut microbiota; prospective study; waist circumference.

Fig 1

Multi-trajectories of BMI and WC and their associations with dyslipidemia. (A) Summary of the study population. This study utilized data from the China Health and Nutrition Survey (CHNS) spanning from 1991 to 2018. The analysis process can be summarized as follows: we first performed a multi-trajectory analysis using samples collected from 1991 to 2015 to examine the association between long-term trajectories of BMI and WC (1991–2015) and the incidence of new-onset dyslipidemia in 2018. Subsequently, we explored the relationships between these identified multi-trajectories and microbiota as well as metabolite profiles in the 2015 samples. This was followed by an in-depth investigation into the correlations between microbiota and metabolites. Finally, we conducted a conjoint analysis that integrated all key factors to provide a comprehensive understanding of the interactions among them. (B and C) Multi-trajectories of BMI and WC in the CHNS cohort (1991–2015) among males (B) and females (C) using GBTM (5,222 males and 5,456 females). The solid lines represent the average estimated BMI and WC over time. The dots represent the actual data, where we weighted each individual’s responses based on posterior probabilities of group membership. (D) Associations between multi-trajectories and dyslipidemia based on a binomial logistic regression model (841 males and 1,151 females). Both models were adjusted for age, location (urban/rural), geographical area (province), education level, smoking, drinking, household income, physical activity, and dietary energy intake.

Fig 2

Comparison of the diversity of gut microbiota in multi-trajectories of different sexes (1,434 males and 1,605 females). (A and B) Alpha-diversity analysis between males (A) and females (B). Four alpha-diversity indices were scaled: Shannon’s diversity index, observed features, Pielou’s measure of species evenness, and Faith’s phylogenetic diversity. Comparison between each risk trajectory group and the normal group using the Kruskal-Wallis test. (C–F) β-Diversity analysis between males (C–E) and females (F). Pairwise comparisons were determined by PERMANOVA analyses based on the Bray-Curtis distance. R² and P values were determined from 999 permutations.

Fig 3

Characteristic genera for those multi-trajectories with higher risk of dyslipidemia. (A–D) Discovery cohort: 1,434 males and 1,605 females. Cross-validation curves of 169 bacteria genera for screening of characteristic genera by LASSO regression (discovery cohort). Characteristic genera selection for BMI and WC normal increasing trajectory (Group 2) in male (A), BMI and WC overweight increasing trajectory (Group 3) in male (B), BMI and WC obesity increasing trajectory (Group 4) in male (C) and BMIWC normal increasing trajectory (Group 2) in female (D). (E–H) Validation cohort: 650 males and 750 females. Characteristic genera with statistical significance after validation in both the discovery cohort and validation cohort by logistic regression. Association of selected characteristic genera with BMI and WC normal increasing trajectory (Group 2) in male (E), BMIWC overweight increasing trajectory (Group 3) in male (F), BMI and WC obesity increasing trajectory (Group 4) in male (G), and BMI and WC normal increasing trajectory (Group 2) in female (H).

Fig 4

Volcanic map of differential metabolites (P < 0.05, |log2(FC) > 0.5 considered to be differential, 334 males and 438 females). Differential metabolites were found between the normal group (Group 1) and BMI and WC overweight increasing trajectory (Group 3) in male (A), BMI and WC obesity increasing trajectory (Group 4) in male (B), and BMI and WC normal increasing trajectory (Group 2) in female (C). Blue was the downregulated differential metabolite, red was the upregulated differential metabolite, and metabolites with no difference were marked as gray. The P value was further adjusted for multiple testing of pairwise comparison using the Benjamini-Hochberg method. Panels A and B show only the top 10 metabolites with significant differences, respectively, and the top 10 metabolites were sorted according to the absolute value of log2FC.

Fig 5

Spearman’s rank correlation between validated characteristic genera and differential metabolites (393 males and 553 females), and prediction models for the risk of dyslipidemia. (A) Association of validated eight characteristic genera for BMI and WC overweight increasing trajectory (Group 3) with 36 differential metabolites (between Group 3 and Group 1) in males. (B) Association of validated four characteristic genera for BMI and WC obesity increasing trajectory (Group 4) with 57 differential metabolites (between Group 4 and Group 1) in males. (C) Association of validated two characteristic genera for BMI and WC normal increasing trajectory (Group 2) with 10 differential metabolites (between Group 2 and Group 1) in females. (D) Logistic regression models to predict the risk of dyslipidemia. Model 1 included the trajectories and relevant covariates (age, gender, location [urban/rural], geographical area [province], education level, smoking, drinking, household income, physical activity, and dietary energy intake), model 2 further added the validated characteristic genera, and model 3 further added the differential metabolites.