biostudies-literatureUnknown6(1)Lu JJ<h4>Motivation</h4><i>Klebsiella pneumoniae</i> is a highly virulent superbug with rising antibiotic resistance worldwide. While matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has transformed microbial identification, its application to antimicrobial resistance prediction remains underexplored, particularly for large clinical cohorts. In this study, we developed machine-learning models with feature-level interpretability using MALDI-TOF MS data to rapidly predict resistance to ciprofloxacin (CIP), cefuroxime (CXM), and ceftriaxone (CRO) in <i>K. pneumoniae</i>.<h4>Results</h4>Using more than 28 000 isolates from two hospitals, the best-performing models reached an independent test accuracy of 0.7858, with sensitivity of 0.7289 and specificity ofBioinformatics advancesvbaf303https://www.ebi.ac.uk/biostudies/studies/S-EPMC12776345biostudies-literatureAI-powered rapid detection of multidrug-resistant &lt;i&gt;Klebsiella pneumoniae&lt;/i&gt; with informative peaks of MALDI-TOF MS.PMC12776345Lu JJChiang MCWu LCLee TYHorng JTHsu JBChung CRTang YWang HYfalseAI-powered rapid detection of multidrug-resistant &lt;i&gt;Klebsiella pneumoniae&lt;/i&gt; with informative peaks of MALDI-TOF MS.<h4>Motivation</h4><i>Klebsiella pneumoniae</i> is a highly virulent superbug with rising antibiotic resistance worldwide. While matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has transformed microbial identification, its application to antimicrobial resistance prediction remains underexplored, particularly for large clinical cohorts. In this study, we developed machine-learning models with feature-level interpretability using MALDI-TOF MS data to rapidly predict resistance to ciprofloxacin (CIP), cefuroxime (CXM), and ceftriaxone (CRO) in <i>K. pneumoniae</i>.<h4>Results</h4>Using more than 28 000 isolates from two hospitals, the best-performing models reached an independent test accuracy of 0.7858, with sensitivity of 0.7289 and specificity of2026-01-01T00:00:00Z20262026-06-13T06:30:50.892Z2026-06-13T03:12:42.133ZS-EPMC127763454151002310.1093/bioadv/vbaf303