JUL 28, 2026 · JOURNAL ARTICLE
Kernel density-encoded MALDI-TOF spectra with LightGBM machine learning for multiplex resistance prediction in Klebsiella pneumoniae.
Diagnostic Microbiology and Infectious Disease
Single-center proof-of-concept validation of a machine-learning classifier for antimicrobial resistance prediction using MALDI-TOF spectra, with internal hold-out testing only and no external validation, before clinical application.
Reported
Model accuracy range0.81 to 0.92
AUROC range0.88 to 0.96
Sample size424