Rapid detection of Klebsiella pneumoniae producing extended spectrum β lactamase enzymes by infrared microspectroscopy and machine learning algorithms

Antimicrobial drugs have played an indispensable role in decreasing morbidity and mortality associated with infectious diseases. However, the resistance of bacteria to a broad spectrum of commonly-used antibiotics has grown to the point of being a global health-care problem. One of the most important classes of multi-drug resistant bacteria is Extended Spectrum Beta-Lactamase-producing (ESBL+) bacteria. This increase in bacterial resistance to antibiotics is mainly due to the long time (about 48 h) that it takes to obtain lab results of detecting ESBL-producing bacteria. Thus, rapid detection of ESBL+ bacteria is highly important for efficient treatment of bacterial infections. In this study, we evaluated the potential of infrared microspectroscopy in tandem with machine learning algorithms for rapid detection of ESBL-producing Klebsiella pneumoniae (K. pneumoniae) obtained from samples of patients with urinary tract infections. 285 ESBL+ and 365 ESBL-K. pneumoniae samples, gathered from cultured colonies, were examined. Our results show that it is possible to determine that K. pneumoniae is ESBL+ with similar to 89% accuracy, similar to 88% sensitivity and similar to 89% specificity, in a time span of similar to 20 minutes following the initial culture.

Automated summary

Rapid detection of ESBL+ bacteria is crucial for efficient treatment of bacterial infections. Results from the study demonstrate the possibility of accurately identifying ESBL+ Klebsiella pneumoniae within about 20 minutes, with approximately 89% accuracy, sensitivity, and specificity.