Predicting Multi-Drug Resistance in Bacterial Isolates Through Performance Comparison and LIME-based Interpretation of Classification Models

TL;DR

This study develops an interpretable machine learning framework using ensemble models and LIME explanations to predict multi-drug resistance in bacteria, aiding clinical decision-making and antimicrobial stewardship.

Contribution

It introduces a combined approach of high-performing ensemble classifiers and local interpretability for predicting MDR with clinical insights.

Findings

Ensemble models like XGBoost and LightGBM outperform others in MDR prediction.

LIME explanations align with known resistance mechanisms.

Framework enables earlier and more transparent MDR detection.

Abstract

The rise of Antimicrobial Resistance, particularly Multi-Drug Resistance (MDR), presents a critical challenge for clinical decision-making due to limited treatment options and delays in conventional susceptibility testing. This study proposes an interpretable machine learning framework to predict MDR in bacterial isolates using clinical features and antibiotic susceptibility patterns. Five classification models were evaluated, including Logistic Regression, Random Forest, AdaBoost, XGBoost, and LightGBM. The models were trained on a curated dataset of 9,714 isolates, with resistance encoded at the antibiotic family level to capture cross-class resistance patterns consistent with MDR definitions. Performance assessment included accuracy, F1-score, AUC-ROC, and Matthews Correlation Coefficient. Ensemble models, particularly XGBoost and LightGBM, demonstrated superior predictive capability across all metrics. To address the clinical transparency gap, Local Interpretable Model-agnostic Explanations (LIME) was applied to generate instance-level explanations. LIME identified resistance to quinolones, Co-trimoxazole, Colistin, aminoglycosides, and Furanes as the strongest contributors to MDR predictions, aligning with known biological mechanisms. The results show that combining high-performing models with local interpretability provides both accuracy and actionable insights for antimicrobial stewardship. This framework supports earlier MDR identification and enhances trust in machine learning-assisted clinical decision support.