Rapid Screening of Methicillin-Resistant Staphylococcus aureus Using MALDI-TOF MS and Machine Learning: A Randomized,...

Area of Science:

• Clinical microbiology
• Infectious diseases
• Machine learning applications in healthcare

Background:

• Methicillin-resistant Staphylococcus aureus (MRSA) is a significant cause of healthcare-associated infections.
• Current MRSA detection methods are time-consuming, labor-intensive, and costly, delaying treatment.
• Rapid MRSA detection is crucial for effective patient management and improved outcomes.

Purpose of the Study:

• To evaluate the clinical utility of AMRQuest software for rapid MRSA screening.
• To assess the accuracy of AMRQuest software compared to the cefoxitin disk diffusion test.
• To determine the potential of AMRQuest for simultaneous bacterial identification and MRSA screening.

Main Methods:

• Development of AMRQuest software using logistic regression-based machine learning and MALDI-TOF spectra.
• Validation of AMRQuest software against the cefoxitin disk diffusion test as a reference method.
• Analysis of 537 Staphylococcus aureus isolates (231 MRSA, 306 MSSA) from three tertiary-care hospitals.

Main Results:

• AMRQuest software demonstrated high analytical sensitivity, specificity, and percent agreement with the cefoxitin disk diffusion test.
• The software accurately screened MRSA and identified bacterial species simultaneously.
• Results indicated that AMRQuest is a powerful tool for rapid MRSA detection.

Conclusions:

• AMRQuest software can be successfully implemented in clinical microbiology laboratories for efficient MRSA screening.
• The software provides a rapid and accurate alternative to traditional, time-consuming MRSA testing methods.
• AMRQuest facilitates faster clinical decisions for patients with suspected MRSA infections.