Machine learning based prediction of antimicrobial resistance in Klebsiella spp.: a five-year retrospective study
Machine-learning-basierte Vorhersage von antimikrobieller Resistenz bei Klebsiella spp.: eine fünfjährige retrospektive Studie
Frontiers in Public Health · 01.07.2026 · 14
DOI: 10.3389/fpubh.2026.1865551 ↗Auf einen Blick
Retrospektiv wurden 2.646 Klebsiella-Isolate aus 2019 bis 2024 analysiert. XGBoost sagte die Antibiotikaresistenz am besten vorher (Accuracy 0,70).
Fragestellung
Wie gut lassen sich antimikrobielle Suszeptibilität und Resistenzphänotypen bei Klebsiella spp. mit Machine-Learning-Modellen vorhersagen?
Methode
Retrospektive Analyse von Routinelabordaten aus 2019 bis 2024; Entwicklung und Test mehrerer überwachter ML-Modelle zur Vorhersage der Antibiotikaresistenz.
Ergebnisse
Klebsiella spp. machten 2.646 Isolate (13,7 %) aller klinischen Isolate aus. 57,8 % waren MDR, 1,9 % XDR, keine PDR. Bestes Modell: XGBoost mit Accuracy 0,70, Precision 0,65, Recall 0,64, F1-Score 0,64, ROC-AUC 0,74.
Schlussfolgerung der Autor:innen
Die Ergebnisse zeigen eine zunehmende klinische Belastung durch Klebsiella-Infektionen und das Potenzial von Boosting-basierten ML-Algorithmen, besonders XGBoost und LightGBM, zur Vorhersage von Antibiotikaresistenz.
Kernaussagen
- 2.646 Klebsiella-Isolate; häufigste Quelle: Harnwegsinfektionen (45,5 %)
- 57,8 % MDR, 1,9 % XDR, keine PDR-Isolate
- XGBoost war das beste Modell (ROC-AUC 0,74)
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Public Health, online erschienen am 01.07.2026. Verfasst von Munerah M Alfadhel und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmaceutics, College of Pharmacy, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia. Hauptthemen laut MEDLINE: Klebsiella, Machine Learning, Anti-Bacterial Agents, Drug Resistance, Bacterial. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Klebsiella species are well-recognized pathogens implicated in both healthcare-associated and community-acquired infections, and they contribute substantially to the global burden of antimicrobial resistance. In this study, we investigated the epidemiology, temporal resistance trends, multidrug resistance profiles, and the application of machine learning (ML) approaches to predict antimicrobial susceptibility among Klebsiella isolates in Al-Kharj, Saudi Arabia.
Methods
A retrospective analysis conducted using routine microbiology laboratory data collected between 2019 and 2024. Antimicrobial susceptibility testing included multiple agents across major antimicrobial classes, allowing classification of isolates into defined resistance phenotypes. Multidrug-resistant (MDR), extensively drug-resistant (XDR), and pan-drug-resistant (PDR) profiles were determined using standard class-based definitions. In parallel, several supervised machine learning models were developed and evaluated, including Random Forest, Support Vector Machine (SVM), Gradient Boosting, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Extra Trees Classifier, Classifier Chains (multilabel classification), Deep Neural Network (DNN), Voting Ensemble, and Convolutional Neural Network (CNN). Models were trained using the training dataset and subsequently evaluated on the testing dataset to assess predictive performance and generalizability.
Results
Over the five-year study period, Klebsiella species accounted for 2,646 isolates (13.7%) of all clinical isolates, with Klebsiella pneumoniae representing the predominant species. Urinary tract infections were the most frequent source (45.5%), followed by blood cultures (15.4%), respiratory samples (14%), and wound and soft tissue specimens (12.2%). High resistance rates were observed for ceftazidime, whereas most other antibiotics demonstrated moderate resistance levels. Tigecycline, and Ceftriaxone showed the lowest resistance rates. Among Klebsiella spp. isolates, 57.8% were classified as multidrug-resistant, 1.9% as extensively drug-resistant, and no pan-drug-resistant isolates were identified. Among the evaluated models, the best overall model was XGBoost with an accuracy of 0.70, precision of 0.65, recall of 0.64, an F1-score of 0.64, and a ROC-AUC of 0.74.
Conclusions
Collectively, these findings underscore the increasing clinical burden of Klebsiella infections and demonstrate the potential of boosting-based machine learning algorithms, particularly XGBoost and LightGBM, for accurate prediction of antibiotic resistance. Integration of these models into clinical decision-support systems and antimicrobial stewardship programs may facilitate timely and appropriate antimicrobial therapy, thereby improving patient outcomes and promoting more rational antibiotic use.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Pharmaceutics, College of Pharmacy, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia.
Zitieren
APA
Alfadhel, M. M., Aldawsari, M. F., & Moglad, E. (2026). Machine learning based prediction of antimicrobial resistance in Klebsiella spp.: a five-year retrospective study. Frontiers in Public Health, 14. https://doi.org/10.3389/fpubh.2026.1865551
Vancouver
Alfadhel MM, Aldawsari MF, Moglad E. Machine learning based prediction of antimicrobial resistance in Klebsiella spp.: a five-year retrospective study. Frontiers in Public Health. 2026;14. doi:10.3389/fpubh.2026.1865551
BibTeX
@article{Alfadhel2026,
author = {Alfadhel, Munerah M and Aldawsari, Mohammed F and Moglad, Ehssan},
title = {Machine learning based prediction of antimicrobial resistance in Klebsiella spp.: a five-year retrospective study},
journal = {Frontiers in Public Health},
year = {2026},
volume = {14},
doi = {10.3389/fpubh.2026.1865551}
}
EUVIMED