Abnormal composition of gut microbiota contributes to delirium-like behaviors after abdominal surgery in mice

Abstract

Aims: Anesthesia and surgery can cause delirium-like symptoms postoperatively. Increasing evidence suggests that gut microbiota is a physiological regulator of the brain. Herein, we investigated whether gut microbiota plays a role in postoperative delirium (POD).

Methods: Mice were separated into non-POD and POD phenotypes after abdominal surgery by applying hierarchical clustering analysis to behavioral tests. Fecal samples were collected, and 16S ribosomal RNA gene sequencing was performed to detect differences in gut microbiota composition among sham, non-POD, and POD mice. Fecal bacteria from non-POD and POD mice were transplanted into antibiotics-induced pseudo-germ-free mice to investigate the effects on behaviors.

Results: α-diversity and β-diversity indicated differences in gut microbiota composition between the non-POD and POD mice. At the phylum level, the non-POD mice had significantly higher levels of Tenericutes, which were not detected in the POD mice. At the class level, levels of Gammaproteobacteria were higher in the POD mice, whereas the non-POD mice had significantly higher levels of Mollicutes, which were not detected in the POD mice. A total of 20 gut bacteria differed significantly between the POD and non-POD mice. Interestingly, the pseudo-germ-free mice showed abnormal behaviors prior to transplant. The pseudo-germ-free mice that received fecal bacteria transplants from non-POD mice but not from POD mice showed improvements in behaviors.

Conclusions: Abnormal gut microbiota composition after abdominal surgery may contribute to the development of POD. A therapeutic strategy that targets gut microbiota could provide a novel alterative for POD treatment.

Keywords: abdominal surgery; gut microbiota; gut-brain axis; microbiota transplant; postoperative delirium.

Figure 1

The schedule and behavioral tests. A, The study schedule. Behavioral tests, including the open‐field test, evaluated plus maze test, and buried food test, were performed 24 h before A + S, and 6 h after it. Fresh fecal samples were collected after all behavioral tests B, Dendrogram of the hierarchical clustering analysis. After A + S, 19 mice were classified into POD, non‐POD, and undetermined groups by hierarchical clustering analysis of the results of the behavioral tests. C, Body weight (one‐way ANOVA, F _2,16 = 0.9403, P > 0.05). D, Center crossing (one‐way ANOVA, F _2,16 = 8.27, P < 0.01). E, Time spent at the center (one‐way ANOVA, F _2,16 = 14.49, P < 0.001). F, Zone crossing (one‐way ANOVA, F _2,16 = 30.88, P < 0.001). G, Entries into the open arms (one‐way ANOVA, F _2,16, P < 0.01). H, Latency to find the food pellet (one‐way ANOVA, F _2,16 = 26.95, P < 0.001). A + S, anesthesia and abdominal surgery; ANOVA, analysis of variance; NS, not significant; POD, postoperative delirium. Data are shown as mean ± SEM (n = 6 or 7). **P < 0.01, ***P < 0.001

Figure 2

Differences in gut microbiota profiles between the groups. A, A heat map of the different levels of bacteria among the groups. Y‐axis: the number of operational taxonomic units; X‐axis: groups; a: sham group; b: non‐POD group; c: POD group. B, Chao 1 index (one‐way ANOVA, F _2,17 = 10.607, P < 0.01). C, Shannon index (one‐way ANOVA, F _2,17 = 16.767, P < 0.001). D, Simpson index (one‐way ANOVA, F _2,17 = 6.621, P < 0.01). E, PD whole tree (one‐way ANOVA, F _2,17 = 5.363, P = 0.016). F, PCoA analysis of the gut bacteria data (Bray‐Curtis dissimilarity). G, PCA analysis of the gut bacteria data (Bray‐Curtis dissimilarity, one‐way ANOVA, PC1: F _2,31 = 14.909, P < 0.001). *P < 0.05, **P < 0.01 and ***P < 0.001

Figure 3

Changes in gut microbiota composition at the phylum level. A, Chart of the relative abundance of the differential levels of bacteria at the phylum level. B, Tenericutes level (Fisher's exact test, **P < 0.01)

Figure 4

Changes in gut microbiota composition at the class level. A, Chart of the relative abundance of the differential levels of bacteria at the class level. B, Gammaproteobacteria level (Fisher's exact test, **P < 0.01). C, Mollicutes level (Fisher's exact test, **P < 0.01)

Figure 5

Changes in gut microbiota composition at the order level. A, Chart of the relative abundance of the differential levels of bacteria at the order level. B, Bifidobacteriales level (Fisher's exact test, *P < 0.05). C, Anaeroplasmatales level (Fisher's exact test, *P < 0.05)

Figure 6

Changes in gut microbiota composition at the family level. A, Chart of the relative abundance of the differential levels of bacteria at the family level (top 30). B, Rikenellaceae level (one‐way ANOVA, F _2,17 = 3.796, P = 0.043). C, Clostridiaceae 1 level (Fisher's exact test, P < 0.01). D, Family XIII level (one‐way ANOVA, F _2,17 = 3.796, P = 0.038). E, Ruminococcaceae level (one‐way ANOVA, F _2,17 = 5.115, P = 0.018). F, Anaeroplasmataceae level (Fisher's exact test, P < 0.01). *P < 0.05; **P < 0.01

Figure 7

Changes in gut microbiota composition at the genus level. A, Chart of the relative abundance of the differential levels of bacteria at the genus level (top 30). B, Butyricimonas level (Fisher's exact test, P < 0.01). C, Clostridium sensu strict 1 level (Fisher's exact test, P < 0.01). D, Ruminiclostridium level (one‐way ANOVA, F _2,17 = 3.885, P = 0.041). E, Ruminococcaceae UCG 009 level (Fisher's exact test, P < 0.05). F, Ruminococcaceae UCG 014 level (one‐way ANOVA, F _2,17 = 5.132, P = 0.018). G, Desulfovibrio level (one‐way ANOVA, F _2,17 = 3.667, P = 0.047). H, Escherichia Shigella (Fisher's exact test, P < 0.05). I, Anaeroplasma level (Fisher's exact test, P < 0.01). *P < 0.05; **P < 0.01

Figure 8

Changes in gut microbiota composition at the species level. A, Chart of the relative abundance of the differential levels of bacteria at the species level. B, Uncultured Bacteroidales bacterium level (one‐way ANOVA, F _2,17 = 3.781, P = 0.044). C, Unidentified marine level (Fisher's exact test, P < 0.01). *P < 0.05; **P < 0.01

Figure 9

Effects of transplanting fecal bacteria from non‐POD and POD mice on the behavior of pseudo‐germ‐free mice. A, Schedule of fecal bacteria transplantation and behavior tests for the pseudo‐germ‐free mice. The pseudo‐germ‐free model was achieved by treating mice with large doses of antibiotic solution in their drinking water for 14 consecutive days. The mice were then orally treated with fecal bacteria from non‐POD or POD mice. The behavioral tests were performed on day 29. B, Body weight (one‐way ANOVA, F _3,41 = 25.59, P < 0.001). C, Center crossing (one‐way ANOVA, F _3,41 = 5.803, P = 0.002). D, Time spent at the center (one‐way ANOVA, F _3,41 = 6.746, P < 0.001). E, Zone crossing (one‐way ANOVA, F _3,41 = 8.143, P < 0.001). F, Entries into the open arms (one‐way ANOVA, F _3,41 = 8.442, P < 0.001). G, Latency to find the food pellet (one‐way ANOVA, F _3,41 = 5.059, P = 0.0041). ANOVA, analysis of variance; NS, not significant; PBS, phosphate‐buffered saline; POD, postoperative delirium. Data are shown as mean ± SEM (n = 11). *P < 0.05, **P < 0.01