Multi-label classification to predict antibiotic resistance from raw clinical MALDI-TOF mass spectrometry data.

Autor: Astudillo CA; Computer Science Department, Engineering Faculty, Universidad de Talca, Talca, Chile., López-Cortés XA; Department of Computer Sciences and Industries, Universidad Católica del Maule, Talca, Chile. xlopez@ucm.cl.; Centro de Innovación en Ingeniería Aplicada (CIIA), Universidad Católica del Maule, Talca, Chile. xlopez@ucm.cl., Ocque E; Computer Science Department, Engineering Faculty, Universidad de Talca, Talca, Chile., Manríquez-Troncoso JM; Department of Computer Sciences and Industries, Universidad Católica del Maule, Talca, Chile.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Dec 28; Vol. 14 (1), pp. 31283. Date of Electronic Publication: 2024 Dec 28.
DOI: 10.1038/s41598-024-82697-w
Abstrakt: Antimicrobial resistance (AMR) poses a significant global health challenge, necessitating advanced predictive models to support clinical decision-making. In this study, we explore multi-label classification as a novel approach to predict antibiotic resistance across four clinically relevant bacteria: E. coli, S. aureus, K. pneumoniae, and P. aeruginosa. Using multiple datasets from the DRIAMS repository, we evaluated the performance of four algorithms - Multi-Layer Perceptron, Support Vector Classifier, Random Forest, and Extreme Gradient Boosting - under both single-label and multi-label frameworks. Our results demonstrate that the multi-label approach delivers competitive performance compared to traditional single-label models, with no statistically significant differences in most cases. The multi-label framework naturally captures the complex, interconnected nature of AMR data, reflecting real-world scenarios more accurately. We further validated the models on external datasets (DRIAMS B and C), confirming their generalizability and robustness. Additionally, we investigated the impact of oversampling techniques and provided a reproducible methodology for handling MALDI-TOF data, ensuring scalability for future studies. These findings underscore the potential of multi-label classification to enhance predictive accuracy in AMR research, offering valuable insights for developing diagnostic tools and guiding clinical interventions.
Competing Interests: Declarations. Competing interests: The authors declare no competing interests.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: