Genomic and phenotypic inconsistencies in Pseudomonas aeruginosa resistome among intensive care patients

Abstract

Objective: Pseudomonas aeruginosa, a difficult-to-manage nosocomial pathogen, poses a serious threat to clinical outcomes in intensive care (ICU) patients due to its high antimicrobial resistance (AMR). To promote effective management, it is essential to investigate the genomic and phenotypic differences in AMR expression of the isolates.

Methods: A prospective observational study was conducted from July 2022 to April 2023 at Liepaja Regional Hospital in Latvia. The study included all adult patients who were admitted to the ICU and had a documented infection with P. aeruginosa, as confirmed by standard laboratory microbiological testing and short-read sequencing. Since ResFinder is the only sequencing-based database offering antibacterial susceptibility testing (AST) data for each antibiotic, we conducted a comparison of the resistance profile with the results of phenotypic testing, evaluating if ResFinder met the US Food and Drug Administration (FDA) requirements for approval as a new AMR diagnostic test. Next, to improve precision, AST data from ResFinder was compared with two other databases - AMRFinderPlus and RGI. Additionally, data was gathered from environmental samples to inform the implementation of appropriate infection control measures in real time.

Results: Our cohort consisted of 33 samples from 29 ICU patients and 34 environmental samples. The presence of P. aeruginosa infection was found to be associated with unfavourable clinical outcomes. A third of the patient samples were identified as multi-drug resistant isolates. Apart from resistance against colistin, significant discrepancies were observed when phenotypic data were compared to genotypic data. For example, the aminoglycoside resistance prediction of ResFinder yielded a major errors value of 3.03% for amikacin, which was marginally above the FDA threshold. Among the three positive environmental samples, one sample exhibited multiple AMR genes similar to the patient samples in its cluster.

Conclusion: Our findings underscore the importance of utilizing a combination of diagnostic methods for the identification of resistance mechanisms, clusters, and environmental reservoirs in ICUs.

Keywords: Pseudomonas aeruginosa; antimicrobial resistance; antimicrobial susceptibility testing; environmental reservoirs; intensive care unit; next-generation sequencing.

Figure 1

Phenotypical results from the antimicrobial susceptibility testing of the clinical isolates. Green box indicates susceptible isolate, yellow box indicates susceptibility with increased exposure isolate, and red box indicates resistant isolate. AMK, Amikacin; TOB, Tobramycin; CAZ, Ceftazidime; CIP, Ciprofloxacin; IPM, Imipenem; MEM, Meropenem; TZP, Piperacillin/Tazobactam; COL, Colistin. Antibiotic classes are as follows – 1 for aminoglycosides; 2 for cephalosporins; 3 for fluoroquinolones; 4 for carbapenems; 5 for penicillins and 6 for polymyxins. ECDC-MDR isolate (blue box) indicates Pseudomonas aeruginosa samples which are resistant to at least 1 antibiotic from a minimum of three or more antibiotic classes – thus known as multi-drug resistant.

Figure 2

The phylogenetic grape-tree showing the clusters and un-clustered isolates identified from our clinical and environmental samples. Sample ID are shown in the centre of the circles. The tree was prepared using the Grape-tree online render tool (https://achtman-lab.github.io/GrapeTree/MSTree_holder.html).

Figure 3

Heatmap demonstrating the presence of non-ubiquitous AMR genes in our 36 isolates (33 clinical and 3 environmental). Samples are grouped based on clusters within 15 allele distance.

Figure 4

Timeline of events for Cluster 14 samples (2 patient samples and 1 environmental sample).