Objectives: The World Health Organization has identified Klebsiella pneumoniae (KP) and Pseudomonas aeruginosa (PA) as significant public health threats owing to high antibiotic resistance. Traditional antibiotic susceptibility testing (AST) methods, crucial for determining the most suitable treatment regimen, typically require approximately 48-96 h (2-4 days) to yield results, including bacterial culture, rapid identification via matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS), and subsequent AST, which is too long for urgent clinical decisions. Here, we developed an artificial intelligence-clinical decision support system (AI-CDSS) utilizing machine learning to analyze MALDI-TOF MS data for antibiotic resistance prediction for these pathogens.
Methods: From 165,299 bacterial specimens, we selected 12,967 KP and 9,429 PA cases. Predictive models, the core of the AI-CDSS, were built using advanced machine learning algorithms, such as the random forest classifier (RFC) and light gradient boosting machine (LGBM), with GridSearchCV and 5-fold cross-validation optimization and robustness.
Results: Both the RFC and LGBM models demonstrated strong predictive performance, with area under the curve values predominantly ranging from 0.91 to 0.95. Sensitivity, specificity, positive predictive value, and negative predictive value primarily exceeded 80 %, ensuring reliable detection of resistance patterns. The AI-CDSS was designed to provide real-time, clinically actionable recommendations, enabling targeted antibiotic selection up to one day faster than conventional AST.
Conclusions: Integrating MALDI-TOF MS with machine learning in AI-CDSS significantly enhanced clinical decision-making, representing a major advancement in the rapid management of infectious diseases and antimicrobial stewardship.
Keywords: AI-CDSS; Klebsiella pneumoniae; MALDI-TOF MS; Machine Learning; Pseudomonas aeruginosa.
Copyright © 2025 The Author(s). Published by Elsevier B.V. All rights reserved.