Innovative Strategies Against Superbugs: Developing an AI-CDSS for Precise Stenotrophomonas maltophilia Treatment

Abstract

ObjectivesThe World Health Organization named Stenotrophomonas maltophilia a critical multi-drug resistant threat, necessitating rapid diagnostic strategies. Traditional culturing methods require up to 96 hours, including 72 hours for bacterial growth, identification with matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) through protein profile analysis, and 24 hours for antibiotic susceptibility testing. In this study, we aimed at developing an artificial intelligence-clinical decision support system (AI-CDSS) by integrating MALDI-TOF MS and machine learning to quickly identify levofloxacin and trimethoprim/sulfamethoxazole resistance in S. maltophilia, optimizing treatment decisions. MethodsWe selected 8,662 S. maltophilia from 165,299 MALDI-TOF MS-analyzed bacterial specimens, collected from a major medical center and four secondary hospitals. We exported mass-to-charge values and intensity spectral profiles from MALDI-TOF MS .mzML files to predict antibiotic susceptibility testing results, obtained with the VITEK-2 system using machine learning algorithms. We optimized the models with GridSearchCV and 5-fold cross-validation. ResultsWe identified distinct spectral differences between resistant and susceptible S. maltophilia strains, demonstrating crucial resistance features. The machine learning models, including random forest, light-gradient boosting machine, and XGBoost, exhibited high accuracy. We established an AI-CDSS to offer healthcare professionals swift, data-driven advice on antibiotic use. ConclusionsMALDI-TOF MS and machine learning integration into an AI-CDSS significantly improved rapid S. maltophilia resistance detection. This system reduced the identification time of resistant strains from 24 hours to minutes after MALDI-TOF MS identification, providing timely and data-driven guidance. Combining MALDI-TOF MS with machine learning could enhance clinical decision-making and improve S. maltophilia infection treatment outcomes.