A Low Glycemic Index Mediterranean Diet Combined with Aerobic Physical Activity Rearranges the Gut Microbiota Signature in NAFLD Patients

Abstract

Non-alcoholic fatty liver disease (NAFLD) is the most common liver disease, and its prevalence worldwide is increasing. Several studies support the pathophysiological role of the gut-liver axis, where specific signal pathways are finely tuned by intestinal microbiota both in the onset and progression of NAFLD. In the present study, we investigate the impact of different lifestyle interventions on the gut microbiota composition in 109 NAFLD patients randomly allocated to six lifestyle intervention groups: Low Glycemic Index Mediterranean Diet (LGIMD), aerobic activity program (ATFIS_1), combined activity program (ATFIS_2), LGIMD plus ATFIS_1 or ATFIS2 and Control Diet based on CREA-AN (INRAN). The relative abundances of microbial taxa at all taxonomic levels were explored in all the intervention groups and used to cluster samples based on a statistical approach, relying both on the discriminant analysis of principal components (DAPCs) and on a linear regression model. Our analyses reveal important differences when physical activity and the Mediterranean diet are merged as treatment and allow us to identify the most statistically significant taxa linked with liver protection. These findings agree with the decreased 'controlled attenuation parameter' (CAP) detected in the LGIMD-ATFIS_1 group, measured using FibroScan^®. In conclusion, our study demonstrates the synergistic effect of lifestyle interventions (diet and/or physical activity programs) on the gut microbiota composition in NAFLD patients.

Keywords: Mediterranean diet; NAFLD; gut microbiota; lifestyle intervention; physical activity.

Figure 1

DAPC analysis based on the adegenet R package: (A) DAPC plot obtained by superimposing samples on the prior group assignment with the screeplot of used discriminant analysis (DA) eigenvalues (two out of five in grey colour) reported in the bottom right of the panel; (B) proportions of successful reassignments: heat colors represent membership probabilities (red = 1, white = 0, orange/yellow = non completely succeeded reassignment) and blue crosses represent the DAPC prior cluster; and (C) loading DAPC plot reporting the genera that best highlighted the cluster separation. The variables that contributed the most to the DAPC loading plot are over the 0.01 threshold.

Figure 2

Maaslin2 associations in the single versus combined intervention groups. Aerobic physical activity (ATFIS_1), Mediterranean diet (LGIMD), and the combined LGIMD-ATFIS_1 intervention groups were compared by means of the linear regression model (Maaslin2), determining the multivariable associations between the phenotypes. Taxa relative abundances were reported on the Y axis.

Figure 3

Maaslin2 model, single versus combined groups. Grouped single (ATFIS_1 and LGIMD) interventions were compared with the combined (LGIMD-ATFIS_1) group, setting the allocation to each of the three groups as the random effect in the linear model.