What question did this study set out to answer?

This research aims to develop predictive models for antimicrobial resistance using machine learning based on historical data.

February 12, 2026Frontiers in PharmacologyOpen Access

Predictive modelling of the dynamics of antimicrobial resistance: creation of a bank of renewable models based on machine learning

View Full Paper

Ask AI

Bookmark

Authors

Mathematical modelling predicts antimicrobial resistance trends, indicating control strategies for AMR.

This research aims to develop predictive models for antimicrobial resistance using machine learning based on historical data.
Analyzed antimicrobial consumption and resistance data from 2008-2022 across 82 regions.
Employed standardization and moving averages for data processing.
Utilized principal component analysis for dimensionality reduction.
Tested various machine learning algorithms including LightGBM and SVM.
Applied cross-validation to calibrate hyperparameters and assess model performance.
LightGBM model achieved 67.5% training precision and 66.6% validation precision for E. coli - cefotaxime.
Key predictors of resistance include moving averages of historical resistance and infection types.
COBYLA optimization predicted a 15-20% reduction in AMR over ten years.
ETS models forecasted a potential 5-10% increase in AMR.

Arepyeva et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

February 12, 2026Frontiers in PharmacologyOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Mathematical modelling predicts antimicrobial resistance trends, indicating control strategies for AMR.

This research aims to develop predictive models for antimicrobial resistance using machine learning based on historical data.
Analyzed antimicrobial consumption and resistance data from 2008-2022 across 82 regions.
Employed standardization and moving averages for data processing.
Utilized principal component analysis for dimensionality reduction.
Tested various machine learning algorithms including LightGBM and SVM.
Applied cross-validation to calibrate hyperparameters and assess model performance.
LightGBM model achieved 67.5% training precision and 66.6% validation precision for E. coli - cefotaxime.
Key predictors of resistance include moving averages of historical resistance and infection types.
COBYLA optimization predicted a 15-20% reduction in AMR over ten years.
ETS models forecasted a potential 5-10% increase in AMR.

Arepyeva et al. (2026) studied this question.

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark