Rapid detection of carbapenem-resistant Escherichia coli and carbapenem-resistant Klebsiella pneumoniae in positive blood cultures via MALDI-TOF MS and tree-based machine learning models

Abstract

Background: Bloodstream infection (BSI) is a systemic infection that predisposes individuals to sepsis and multiple organ dysfunction syndrome. Early identification of infectious agents and determination of drug-resistant phenotypes can help patients with BSI receive timely, effective, and targeted treatment and improve their survival. This study was based on matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), Decision Tree (DT), Random Forest (RF), Gradient Boosting Machine (GBM), eXtreme Gradient Boosting (XGBoost), and Extremely Randomized Trees (ERT) models were constructed to classify carbapenem-resistant Escherichia coli (CREC) and carbapenem-resistant Klebsiella pneumoniae (CRKP). Bacterial species were identified by MALDI-TOF MS in positive blood cultures isolated via the serum isolation gel method, and E. coli and K. pneumoniae in positive blood cultures were collected and placed into machine learning models to predict susceptibility to carbapenems. The aim of this study was to provide rapid detection of CREC and CRKP in blood cultures, to shorten the turnaround time for laboratory reporting, and to provide a basis for early clinical intervention and rational use of antibiotics.

Results: The collected MALDI-TOF MS data of 640 E. coli and 444 K. pneumoniae were analysed by machine learning algorithms. The area under the receiver operating characteristic curve (AUROC) for the diagnosis of E. coli susceptibility to carbapenems by the DT, RF, GBM, XGBoost, and ERT models were 0.95, 1.00, 0.99, 0.99, and 1.00, respectively, and the accuracy in predicting 149 E. coli-positive blood cultures were 0.89, 0.92, 0.90, 0.92, and 0.86, respectively. The AUROC for the diagnosis of K. pneumoniae susceptibility to carbapenems by the DT, RF, GBM, XGBoost, and ERT models were 0.78, 0.95, 0.93, 0.90, and 0.95, respectively, and the accuracy in predicting 127 K. pneumoniae-positive blood cultures were 0.76, 0.86, 0.81, 0.80, and 0.76, respectively.

Conclusions: Machine learning models constructed by MALDI-TOF MS were able to directly predict the susceptibility of E. coli and K. pneumoniae in positive blood cultures to carbapenems. This rapid identification of CREC and CRKP reduces detection time and contributes to early warning and response to potential antibiotic resistance problems in the clinic.

Clinical trial number: Not applicable.

Keywords: Escherichia coli; Klebsiella pneumoniae; Blood cultures; MALDI-TOF MS; Machine learning.

Fig. 1

After obtaining the MALDI-TOF MS data, the 10 Da spectra were divided into one box, and the peaks within the same box were considered as a single property. The maximum peak intensity within each box was used as a representative value. Constructing Decision Tree, Random Forest, Gradient Boosting Machine, eXtreme Gradient Boosting, Extremely Randomized Trees Models

Fig. 2

Pathogens in positive blood cultures were isolated by serum separation gels and identified by MALDI-TOF MS. The results of E. coli and K. pneumoniae identifications were analysed by machine learning models to rapidly predict susceptibility to carbapenems, thereby reducing laboratory turnaround time (this figure was produced in the biorender)

Fig. 3

This is a Beeswarm plot of the Escherichia coli RF model, where the colour of each test spectrum indicates a data point, with red indicating high eigenvalues and blue indicating low eigenvalues. The vertical axis (Y-axis) represents the top ten features that have the greatest impact on RF prediction, and the horizontal axis (X-axis) represents the distribution of Shapley values and their impact on model output. Among them, 7,870-7,879 m/z is the feature peak that has the greatest impact on carbapenem-resistant Escherichia coli detection

Fig. 4

This is a Beeswarm plot of the Klebsiella pneumoniae RF model, where the colour of each test spectrum indicates a data point, with red indicating high eigenvalues and blue indicating low eigenvalues. The vertical axis (Y-axis) represents the top ten features that have the greatest impact on RF prediction, and the horizontal axis (X-axis) represents the distribution of Shapley values and their impact on model output. Among them, 4,920-4,929 m/z is the feature peak that has the greatest impact on carbapenem-resistant Klebsiella pneumoniae detection