Cutaneous Microbiome Profiles Following Chlorhexidine Treatment in a 72-Hour Daily Follow-Up Paired Design: a Pilot Study

Abstract

Venous catheter-related bloodstream infections represent a significant problem in the United States. Our objective was to determine daily changes in skin microbiome profiles up to 72h postchlorhexidine treatment. Left and right forearm skin swab samples were obtained from 10 healthy volunteers over 72h at 24h intervals. Dorsal surface of left arm was treated with chlorohexidine gluconate (CHG) at initial time point (T = 0), while the right arm remained untreated (control). Swab samples were obtained shortly before (T = 0) and after CHG treatment (T = 24-48-72h). Bacterial DNA extraction, 16S rRNA gene V1-V3 sequencing and taxonomic annotation were performed using ZymoBIOMICS pipeline. PERMANOVA, linear discriminant and bacterial interaction network analyses were performed. A total of 13 total phyla, 273 genera, and 950 total species were detected across all time points, CHG-treated or CHG-untreated. Most abundant species included Cutibacterium acnes, Staphylococcus epidermidis, and Rothia Mucilaginosa. Low biomass-related inconsistent taxa detection was observed. PERMANOVA suggested a marginal difference between CHG-treated and CHG-untreated microbiome profiles (Genera: P(perm) = 0.0531; Species: P(perm) = 0.0450). Bacterial interaction network guided PERMANOVA analyses detected a microbiome change over time, suggesting a consistent CHG treatment-specific change. LEfSe identified Finegoldia magna, Bacillus pumilus, Bacillus thermoamylovorans as the only distinctive species. These species were more abundant and/or present post-CHG treatment in the CHG-treated group. These findings suggest that the skin microbiome was not significantly different 24, 48, or 72h after CHG treatment. Previous culture-based studies have found similar results after 24h. Future studies will be needed to determine the mechanisms of bacterial regrowth after CHG treatment. IMPORTANCE Annually, over 80,000 central line infections occur in the United States. Understanding the pathogenesis of these infections is crucial. Chlorhexidine is the most commonly used skin preparation before line placement. We hypothesized that the use of chlorhexidine and dressings will alter the normal arm skin microbiome over a period of 72h. We used 16S-rRNA gene next generation sequencing (NGS) to determine the forearm skin microbiome of volunteers. The left arm was swabbed with chlorhexidine and the right arm served as control. The skin microbiome returned to normal after 24h. Our NGS results confirm findings of two previous culture-based studies. Relative abundance of Bacillus spp. in the chlorhexidine-treated samples was increased, consistent with one previous study. Based on the results of this pilot study, we will need to measure viable bacteria during a 24h time course following chlorhexidine treatment to understand the source of skin microbiome replenishment.

Keywords: 16S rRNA gene sequencing; bloodstream infections; chlorhexidine; skin microbiome.

FIG 1

Analytical design of multivariate analysis of chlorhexidine effect on skin microbiome. Multivariate analyses were performed for (i) all species/genera detected in left arm (chlorhexidine treated) of all nine Healthy Volunteers (HVs), (ii) species detected in at least 10% of samples across all time points in both arms, i.e., 4 of 35 samples per each arm, (iii) species detected in at least 10% of HVs per either time point, i.e., 1 of 9 HVs in either arm. Groups were Chlorhexidine (CHG) treated and untreated; MIND_v1.01 program is Microbial Interaction Network Database (http://www.microbialnet.org/mind.html); LEfSe stands for Linear discriminant analysis (LDA) effect size.

FIG 2

LEfSe analysis CHG-Treated versus CHG-Untreated, all time points (T₀ versus T₁, T₂, T₃), all species identified (n = 950). (a) CHG-Tr_0,1,2,3 versus CHG-Un_0,1,2,3. (b) CHG-Tr_pre/CHG-Tr_post versus CHG-Un_pre/CHG-Un_post. LEfSe analysis was performed with an input of all 950 species detected across time points. Group was used as “class” and patient was used as “subject.” Strategy was set to “one-against-all” strategy for multiclass analysis, the factorial Kruskal–Wallis test and pairwise Wilcoxon signed rank tests were set at a Monte-Carlo significance level α = 0.05 to calculate LDA scores. The log LDA score was set at a threshold >0. (a) Comparison in which LEfSe data input consisted of “Group”, i.e., CHG-Treated (CHG-Tr) versus CHG-Untreated (CHG-Un) all time points for the input option “Class” and “HV” for the LEfSe input option “Subject.” (b) Data input consisted of “Group”, i.e., CHG-Tr_pre (before treatment), CHG-Tr_post (after treatment) versus CHG-Un_pre (before treatment), CHG-Un_post (after treatment) and “HV” (healthy volunteers) for the LEfSe input option “Subject”. Histograms of significant distinctive features are shown in (a) for CHG-Treated (red bars) and (b) for CHG-Treated and CHG-Untreated arm (red: CHG-Tr_pre; blue CHG-Un_pre; and green: CHG-Un_post, no feature for CHG-Tr_post).