Dataset Information

Detection of carbapenem-resistant Klebsiella pneumoniae on the basis of matrix-assisted laser desorption ionization time-of-flight mass spectrometry by using supervised machine learning approach.

ABSTRACT: BACKGROUND:Carbapenem-resistant Klebsiella pneumoniae (CRKP) is emerging as a significant pathogen causing healthcare-associated infections. Matrix-assisted laser desorption/ionisation mass spectrometry time-of-flight mass spectrometry (MALDI-TOF MS) is used by clinical microbiology laboratories to address the need for rapid, cost-effective and accurate identification of microorganisms. We evaluated application of machine learning methods for differentiation of drug resistant bacteria from susceptible ones directly using the profile spectra of whole cells MALDI-TOF MS in 46 CRKP and 49 CSKP isolates. METHODS:We developed a two-step strategy for data preprocessing consisting of peak matching and a feature selection step before supervised machine learning analysis. Subsequently, five machine learning algorithms were used for classification. RESULTS:Random forest (RF) outperformed other four algorithms. Using RF algorithm, we correctly identified 93% of the CRKP and 100% of the CSKP isolates with an overall classification accuracy rate of 97% when 80 peaks were selected as input features. CONCLUSIONS:We conclude that CRKPs can be differentiated from CSKPs through RF analysis. We used direct colony method, and only one spectrum for an isolate for analysis, without modification of current protocol. This allows the technique to be easily incorporated into clinical practice in the future.

SUBMITTER: Huang TS

PROVIDER: S-EPMC7004327 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Detection of carbapenem-resistant Klebsiella pneumoniae on the basis of matrix-assisted laser desorption ionization time-of-flight mass spectrometry by using supervised machine learning approach.

Huang Tsi-Shu TS Lee Susan Shin-Jung SS Lee Chia-Chien CC Chang Fu-Chuen FC

PloS one 20200206 2

<h4>Background</h4>Carbapenem-resistant Klebsiella pneumoniae (CRKP) is emerging as a significant pathogen causing healthcare-associated infections. Matrix-assisted laser desorption/ionisation mass spectrometry time-of-flight mass spectrometry (MALDI-TOF MS) is used by clinical microbiology laboratories to address the need for rapid, cost-effective and accurate identification of microorganisms. We evaluated application of machine learning methods for differentiation of drug resistant bacteria fr ...[more]

PMID: 32027671

Similar Datasets

Project description:Streptococcus suis, particularly S. suis serotype 2 (SS2), is an important zoonotic pathogen causing meningitis in humans worldwide. Although the proper classification of the causative and pathogenic serotype is salutary for the clinical diagnosis, cross-reactions leading to the indistinguishability of serotypes by the current serotyping methods are significant limitations. In the present study, matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF-MS) analysis of extracted peptides was developed to improve the classification of serotype of S. suis. The peptide mass fingerprint (PMFs) database of S. suis was generated from the whole-cell peptides of 32 reference strains of S. suis isolates obtained from pigs. Thirty-two human S. suis isolates from clinical cases in Thailand were used to validate this alternative serotyping method in direct comparison to the multiplex (m)PCR approach. All reference strains, representing 32 serotypes of S. suis, exhibited their individual PMFs patterns, thus allowing differentiation from one another. Highly pathogenic SS2 and SS14 were clearly differentiated from the otherwise serologically closely related SS1/2 and SS1, respectively. The developed MALDI-TOF-MS serotyping method correctly classified the serotype in 68.8% (22/32) of the same serotype isolates generated from the PMFs database; while the validity for the clinical human isolates was 62.5% (20/32). The agreement between the MALDI-TOF-MS and mPCR serotyping was moderate with a Kappa score of 0.522, considering that mPCR could correctly serotype up to 75%. The present study demonstrated that PMFs from the developed MALDI-TOF-MS-based method could successfully discriminate the previously indistinguishable highly pathogenic SS2 and SS14 from SS1/2 and SS1, respectively. Moreover, this serotyping method distinguished pathogenic SS6, and so is an alternative approach of choice to rapidly and reliably serotype clinically pathogenic S. suis isolates.

Dataset Information

Detection of carbapenem-resistant Klebsiella pneumoniae on the basis of matrix-assisted laser desorption ionization time-of-flight mass spectrometry by using supervised machine learning approach.

Publications

Detection of carbapenem-resistant Klebsiella pneumoniae on the basis of matrix-assisted laser desorption ionization time-of-flight mass spectrometry by using supervised machine learning approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets