Interpretable machine learning of clinical MALDI-TOF spectra discriminates carbapenem-resistant Klebsiella pneumoniae while revealing phylogenetic heterogeneity that limits model generalizability
This study developed models to classify KPC, NDM, and CSKP strains using MALDI-TOF MS combined with machine learning. KPC strains were effectively classified across platforms, whereas NDM and CSKP strains showed limited differentiation due to their close evolutionary relationship. Effective classification requires consideration of regional strain variation and periodic model updates informed by local epidemiology.
Authors
- Peibo Yuan (ORCID: https://orcid.org/0000-0001-5061-0331)
- Mingyuan Zou (ORCID: https://orcid.org/0000-0001-6140-981X)
- Mingxiao Chen (ORCID: https://orcid.org/0009-0007-6358-767X)
- Hongwei Zhou (ORCID: https://orcid.org/0000-0002-9478-4023)
- Zhencheng Fang (ORCID: https://orcid.org/0000-0002-0137-4683)
- Dingqiang Chen (ORCID: https://orcid.org/0000-0001-8717-1651)
- Nianyi Zeng
- Lan‐Lan Zhong (ORCID: https://orcid.org/0009-0005-3311-5829)
- Chuang-Ye Cai
Institutions
- Sun Yat-sen University (CN)
- Second Affiliated Hospital of Guangzhou Medical University (CN)
- Zhujiang Hospital (CN)
- Southern Medical University Shenzhen Hospital (CN)
- Guangdong Provincial Center for Disease Control and Prevention (CN)
- Guangdong Provincial People's Hospital (CN)
- Detection Limit (United States) (US)
- Southern Medical University (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Journal of Mass Spectrometry and Advances in the Clinical Lab
- Published
- 2025-11-09
- DOI
- https://doi.org/10.1016/j.jmsacl.2025.11.003
- Primary Topic
- Bacterial Identification and Susceptibility Testing
- Type
- article
- Field-Weighted Citation Impact
- 0.00