Direct Detection of Carbapenemase-Producing Klebsiella pneumoniae by MALDI-TOF Analysis of Full Spectra Applying Machine Learning

Gato, Eva; Arroyo, Manuel J.; Méndez, Gema; Candela, Ana; Rodiño-Janeiro, Bruno K.; Fernández, Javier; Rodríguez‐Sánchez, Belén; Mancera, Luis; Arca-Suárez, Jorge; Beceiro, Alejandro; Bou, Germán; Oviaño, Marina

doi:10.1128/jcm.01751-22

Cited by 9 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the identification of novel biomarkers needs a thorough understanding of their genetic context to verify their linkage to resistance genes. Another interesting approach was recently published by Gato and colleagues, who proposed the use of the full spectrum of the bacterial proteome coupled with machine learning to predict OXA-48 and KPC carriage [ 27 ]. While the results of this study need external confirmation and evaluation using a more epidemiologically diverse set of isolates, the possibility presents an exciting avenue for the application of MALDI-ToF MS for the rapid and reliable clinical detection of AMR.…”

Section: Discussionmentioning

confidence: 99%

Poor Sensitivity of the MALDI Biotyper® MBT Subtyping Module for Detection of Klebsiella pneumoniae Carbapenemase (KPC) in Klebsiella Species

Cuello,

Alvarez Otero,

Greenwood-Quaintance

et al. 2023

Antibiotics

View full text Add to dashboard Cite

Rapid detection of Klebsiella pneumoniae carbapenemase (KPC) in the Klebsiella species is desirable. The MALDI Biotyper® MBT Subtyping Module (Bruker Daltonics) uses an algorithm that detects a peak at ~11,109 m/z corresponding to a protein encoded by the p019 gene to detect KPC simultaneously with organism identification by a matrix-assisted laser desorption ionization–time-of-flight mass spectrometry (MALDI-ToF MS). Here, the subtyping module was evaluated using 795 clinical Klebsiella isolates, with whole genome sequences used to assess for blaKPC and p019. For the isolates identified as KPC positive by sequencing, the overall sensitivity of the MALDI-ToF MS subtyping module was 239/574 (42%) with 100% specificity. For the isolates harboring p019, the subtyping module showed a sensitivity of 97% (239/246) and a specificity of 100%. The subtyping module had poor sensitivity for the detection of blaKPC-positive Klebsiella isolates, albeit exhibiting excellent specificity. The poor sensitivity was a result of p019 being present in only 43% of the blaKPC-positive Klebsiella isolates.

show abstract

Section: Discussionmentioning

confidence: 99%

Poor Sensitivity of the MALDI Biotyper® MBT Subtyping Module for Detection of Klebsiella pneumoniae Carbapenemase (KPC) in Klebsiella Species

Cuello,

Alvarez Otero,

Greenwood-Quaintance

et al. 2023

Antibiotics

View full text Add to dashboard Cite

show abstract

“…Unfortunately, the current methodology is unable to detect the NDM enzyme, probably due to its inefficiency in extracting membrane-anchored proteins [ 47 ]. However, in the future, it would be valuable to explore hybrid approaches that integrate machine learning techniques [ 26 , 27 , 28 ] with our KPC peak detection method to categorize CRE isolates based on the specific type of resistance mechanism they exhibit.…”

Section: Discussionmentioning

confidence: 99%

“…Although MALDI-TOF MS hydrolysis assays have been described to detect carbapenemases, they are not commonly implemented in clinical laboratories [ 25 ]. The latest approaches in MALDI-TOF MS resistance detection involve the use of machine learning techniques to discriminate between resistant and susceptible isolates [ 26 , 27 , 28 ].…”

Section: Introductionmentioning

confidence: 99%

MALDI-TOF MS-Based KPC Direct Detection from Patients’ Positive Blood Culture Bottles, Short-Term Cultures, and Colonies at the Hospital

et al. 2023

View full text Add to dashboard Cite

Carbapenemase resistance in Enterobacterales is a global public health problem and rapid and effective methods for detecting these resistance mechanisms are needed urgently. Our aim was to evaluate the performance of a MALDI-TOF MS-based “Klebsiella pneumoniae carbapenemase” (KPC) detection protocol from patients’ positive blood cultures, short-term cultures, and colonies in healthcare settings. Bacterial identification and KPC detection were achieved after protein extraction with organic solvents and target spot loading with suitable organic matrices. The confirmation of KPC production was performed using susceptibility tests and blaKPC amplification using PCR and sequencing. The KPC direct detection (KPC peak at approximately 28.681 Da) from patients’ positive blood cultures, short-term cultures, and colonies, once bacterial identification was achieved, showed an overall sensibility and specificity of 100% (CI95: [95%, 100%] and CI95: [99%, 100%], respectively). The concordance between hospital routine bacterial identification protocol and identification using this new methodology from the same extract used for KPC detection was ≥92%. This study represents the pioneering effort to directly detect KPC using MALDI-TOF MS technology, conducted on patient-derived samples obtained from hospitals for validation purposes, in a multi-resistance global context that requires concrete actions to preserve the available therapeutic options and reduce the spread of antibiotic resistance markers.

show abstract

Machine learning and matrix-assisted laser desorption/ionization time-of-flight mass spectra for antimicrobial resistance prediction: A systematic review of recent advancements and future development

López-Cortés,

Manríquez-Troncoso,

Kandalaft-Letelier

et al. 2024

Journal of Chromatography A

View full text Add to dashboard Cite

Direct Detection of Carbapenemase-Producing Klebsiella pneumoniae by MALDI-TOF Analysis of Full Spectra Applying Machine Learning

Abstract: MALDI-TOF MS is considered to be an important tool for the future development of rapid microbiological techniques. We propose the application of MALDI-TOF MS as a dual technique for the identification of bacteria and the detection of resistance, with no extra hands-on procedures.

Cited by 9 publications

References 35 publications

Poor Sensitivity of the MALDI Biotyper® MBT Subtyping Module for Detection of Klebsiella pneumoniae Carbapenemase (KPC) in Klebsiella Species

Poor Sensitivity of the MALDI Biotyper® MBT Subtyping Module for Detection of Klebsiella pneumoniae Carbapenemase (KPC) in Klebsiella Species

MALDI-TOF MS-Based KPC Direct Detection from Patients’ Positive Blood Culture Bottles, Short-Term Cultures, and Colonies at the Hospital

Machine learning and matrix-assisted laser desorption/ionization time-of-flight mass spectra for antimicrobial resistance prediction: A systematic review of recent advancements and future development

Contact Info

Product

Resources

About