The lower respiratory tract microbiome of critically ill patients with COVID-19

Abstract

COVID-19 infection may predispose to secondary bacterial infection which is associated with poor clinical outcome especially among critically ill patients. We aimed to characterize the lower respiratory tract bacterial microbiome of COVID-19 critically ill patients in comparison to COVID-19-negative patients. We performed a 16S rRNA profiling on bronchoalveolar lavage (BAL) samples collected between April and May 2020 from 24 COVID-19 critically ill subjects and 24 patients with non-COVID-19 pneumonia. Lung microbiome of critically ill patients with COVID-19 was characterized by a different bacterial diversity (PERMANOVA on weighted and unweighted UniFrac Pr(> F) = 0.001) compared to COVID-19-negative patients with pneumonia. Pseudomonas alcaligenes, Clostridium hiranonis, Acinetobacter schindleri, Sphingobacterium spp., Acinetobacter spp. and Enterobacteriaceae, characterized lung microbiome of COVID-19 critically ill patients (LDA score > 2), while COVID-19-negative patients showed a higher abundance of lung commensal bacteria (Haemophilus influenzae, Veillonella dispar, Granulicatella spp., Porphyromonas spp., and Streptococcus spp.). The incidence rate (IR) of infections during COVID-19 pandemic showed a significant increase of carbapenem-resistant Acinetobacter baumannii (CR-Ab) infection. In conclusion, SARS-CoV-2 infection and antibiotic pressure may predispose critically ill patients to bacterial superinfection due to opportunistic multidrug resistant pathogens.

Figure 1

(a) Boxplots with whiskers showing the comparison of alpha diversity measures between SARS-CoV-2 positive patients (n = 24) and negative patients (n = 24). No significant differences were found between the two study groups. Median, first and third quartile and outliers are shown. (b) Principal Coordinate Analysis (PCoA) on unweighted and weighted UniFrac distance metric at the OTU level calculated on COVID-19 positive (n = 24, red dots) and COVID-19 negative patients (n = 24, blue dots). Each sample is represented by a dot. Axis 1 explained 12% and 40% of the variation observed, in the left and right graph, respectively, and Axis 2 explained 8% and 16% of the variation, in the left and right graph, respectively.

Figure 2

Taxonomic profiles at the phylum (pie charts) and genus level (stacked barplot) of COVID-19 critically ill patients and negative subjects. Taxa that were present in significantly different relative abundances after SIMPER analysis are shown in the lower panel.

Figure 3

Plot from LDA LEfSE analysis. The plot was generated using the online Galaxy web platform tools at https://huttenhower.sph.harvard.edu/galaxy/. The length of the bar column represents the LDA score. The figure shows the microbial taxa with significant differences between the COVID-19 positive (red) and negative patients (green) (LDA score > 2) with their original identification codes.

Figure 4

(a) Incidence rate of ICU-acquired infection due to Carbapenem-resistant Acinetobacter baumannii (CR-Ab) per 10.000 patient-days over the same 4-months period (January–April) from 2017 to 2020. (b) Incidence rate of ICU-acquired infection due to Pseudomonas aeruginosa and (c) carbapenemase-producing Enterobacteriaceae (CPE). Abbreviations: Lower Respiratory Tract Infection, LRTI; Bloodstream Infection (BSI).