Early antifungal resistance prediction based on MALDI-TOF mass spectrometry and machine learning

Antimicrobial resistance (AMR) is a significant global health threat. Recent studies have shown that combining MALDI-TOF mass spectrometry with machine learning algorithms can accelerate AMR determination. However, these efforts have predominantly focused on bacterial pathogens. The significant morbidity, mortality, and healthcare costs associated with fungal infections highlight the need for accurate and early detection of antifungal resistance. We developed a machine learning pipeline integrating MALDI-TOF mass spectrometry data and drug features to predict antifungal resistance and identify spectral biomarkers. By leveraging the DRIAMS dataset, we included 658 pathogen spectra linked to 3,046 phenotypic antifungal resistance results across three drug classes and seven yeast species. Models were trained using categorical phenotypic antifungal susceptibility testing results as ground truth. We systematically investigated how different dimensionality reduction methods, antifungal encodings, and model types affected predictive performance using nested cross-validation. We identified that applying principal component analysis to MALDI-TOF mass spectra, and training a multi-layer perceptron yielded the highest and most stable performance for the prediction of antifungal resistance. Our method achieved an AUPRC of 0.77 across the 10 highest-performing species-drug pairs. The model demonstrated the best performance for the species-drug combinations of Candida albicans with micafungin, Candida parapsilosis with fluconazole, and Saccharomyces cerevisiae with itraconazole and fluconazole. By comparing established species-based guidelines, susceptibility test results, and machine learning predictions, we estimated that integrating our algorithm into antifungal selection could help avoid prescriptions to likely resistant pathogens in approximately 3 out of 10 patients for whom standard guidelines recommend such treatments.