2023
Guerrero-López, Alejandro; Sevilla-Salcedo, Carlos; Candela, Ana; Hernández-García, Marta; Cercenado, Emilia; Olmos, Pablo M.; Cantón, Rafael; Muñoz, Patricia; Gómez-Verdejo, Vanessa; Campo, Rosa; Rodríguez-Sánchez, Belén
Automatic antibiotic resistance prediction in Klebsiella pneumoniae based on MALDI-TOF mass spectra Artículo de revista
En: Engineering Applications of Artificial Intelligence, vol. 118, pp. 105644, 2023, ISSN: 0952-1976.
Resumen | Enlaces | BibTeX | Etiquetas: Antibiotic Resistance, Bayesian model, CP, ESBL, Klebsiella pneumoniae, MALDI-TOF
@article{GUERREROLOPEZ2023105644,
title = {Automatic antibiotic resistance prediction in Klebsiella pneumoniae based on MALDI-TOF mass spectra},
author = {Alejandro Guerrero-L\'{o}pez and Carlos Sevilla-Salcedo and Ana Candela and Marta Hern\'{a}ndez-Garc\'{i}a and Emilia Cercenado and Pablo M. Olmos and Rafael Cant\'{o}n and Patricia Mu\~{n}oz and Vanessa G\'{o}mez-Verdejo and Rosa Campo and Bel\'{e}n Rodr\'{i}guez-S\'{a}nchez},
url = {https://www.sciencedirect.com/science/article/pii/S0952197622006340},
doi = {https://doi.org/10.1016/j.engappai.2022.105644},
issn = {0952-1976},
year = {2023},
date = {2023-01-01},
journal = {Engineering Applications of Artificial Intelligence},
volume = {118},
pages = {105644},
abstract = {Matrix-Assisted Laser Desorption Ionization Time-Of-Flight (MALDI-TOF) Mass Spectrometry (MS) is a reference method for microbial identification and it can be used to predict Antibiotic Resistance (AR) when combined with artificial intelligence methods. However, current solutions need time-costly preprocessing steps, are difficult to reproduce due to hyperparameter tuning, are hardly interpretable, and do not pay attention to epidemiological differences inherent to data coming from different centres, which can be critical. We propose using a multi-view heterogeneous Bayesian model (KSSHIBA) for the prediction of AR using MALDI-TOF MS data together with their epidemiological differences. KSSHIBA is the first model that removes the ad-hoc preprocessing steps that work with raw MALDI-TOF data. In addition, due to its Bayesian probabilistic nature, it does not require hyperparameter tuning, provides interpretable results, and allows exploiting local epidemiological differences between data sources. To test the proposal, we used data from 402 Klebsiella pneumoniae isolates coming from two different domains and 20 different hospitals located in Spain and Portugal. KSSHIBA outperforms current state-of-the-art approaches in antibiotic susceptibility prediction, obtaining a 0.78 AUC score in Wild Type classification and a 0.90 AUC score in Extended-Spectrum Beta-Lactamases (ESBL)+Carbapenemases (CP)-producers. The proposal consistently removes the need for ad-hoc preprocessing by working with raw MALDI-TOF data, which, in turn, reduces the time needed to obtain the results of the resistance mechanism in microbiological laboratories. The proposed model implementation as well as both data domains are publicly available.},
keywords = {Antibiotic Resistance, Bayesian model, CP, ESBL, Klebsiella pneumoniae, MALDI-TOF},
pubstate = {published},
tppubtype = {article}
}
Matrix-Assisted Laser Desorption Ionization Time-Of-Flight (MALDI-TOF) Mass Spectrometry (MS) is a reference method for microbial identification and it can be used to predict Antibiotic Resistance (AR) when combined with artificial intelligence methods. However, current solutions need time-costly preprocessing steps, are difficult to reproduce due to hyperparameter tuning, are hardly interpretable, and do not pay attention to epidemiological differences inherent to data coming from different centres, which can be critical. We propose using a multi-view heterogeneous Bayesian model (KSSHIBA) for the prediction of AR using MALDI-TOF MS data together with their epidemiological differences. KSSHIBA is the first model that removes the ad-hoc preprocessing steps that work with raw MALDI-TOF data. In addition, due to its Bayesian probabilistic nature, it does not require hyperparameter tuning, provides interpretable results, and allows exploiting local epidemiological differences between data sources. To test the proposal, we used data from 402 Klebsiella pneumoniae isolates coming from two different domains and 20 different hospitals located in Spain and Portugal. KSSHIBA outperforms current state-of-the-art approaches in antibiotic susceptibility prediction, obtaining a 0.78 AUC score in Wild Type classification and a 0.90 AUC score in Extended-Spectrum Beta-Lactamases (ESBL)+Carbapenemases (CP)-producers. The proposal consistently removes the need for ad-hoc preprocessing by working with raw MALDI-TOF data, which, in turn, reduces the time needed to obtain the results of the resistance mechanism in microbiological laboratories. The proposed model implementation as well as both data domains are publicly available.