Abstract

Enterococcus faecium is one of the leading pathogens in the world. In this study, we proposed a strategy to rapidly and accurately distinguish vancomycin-resistant Enterococcus faecium (VREfm) and vancomycin-susceptible E. faecium (VSEfm) to help doctors correctly determine the use of vancomycin by a machine learning (ML)-based algorithm. A predictive model was developed and validated to distinguish VREfm and VSEfm by analyzing MALDI-TOF MS spectra of unique E. faecium isolates from different specimen types. Firstly, 5717 mass spectra, including 2795 VREfm and 2922 VSEfm, were used to develop the algorithm. And 2280 mass spectra of isolates, namely 1222 VREfm and 1058 VSEfm, were used to externally validate the algorithm. The random forest-based algorithm demonstrated good classification performances for overall specimens, whose mean AUROC in 5-fold cross validation, time-wise validation, and external validation was all greater than 0.84. For the detection of VREfm in blood, sterile body fluid, urinary tract, and wound, the AUROC in external validation was also greater than 0.84. The predictions with algorithms were significantly more accurate than empirical antibiotic use. The accuracy of antibiotics administration could be improved by 30%. And the algorithm could provide rapid antibiotic susceptibility results at least 24 hours ahead of routine laboratory tests. The turn-around-time of antibiotic susceptibility could be reduced by 50%. In conclusion, a ML algorithm using MALDI-TOF MS spectra obtained in routine workflow accurately differentiated VREfm from VSEfm, especially in blood and sterile body fluid, which can be applied to facilitate the clinical testing process due to its accuracy, generalizability, and rapidness.