Creative Commons source reading · Machine learning for performance
Machine learning based prediction of antimicrobial resistance in Klebsiella spp.: a five-year retrospective study
Alfadhel MM; Aldawsari MF; Moglad E
Originally published in Front Public Health · 2026-07-01
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
AbstractIntroductionKlebsiella 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.MethodsA 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…
Discussion
In this study, Klebsiella species constituted a notable proportion of clinical isolates, accounting for 2,646 (13.7%) of the 18,003 microbiology reports analyzed over the five-year period. This considerable representation reflects the substantial clinical burden of Klebsiella infections in healthcare settings. The finding is consistent with previous reports that identify Klebsiella spp. as important opportunistic pathogens responsible for both community-acquired and hospital-associated infections (24–26). The relatively high prevalence observed further emphasizes the growing relevance of Klebsiella species in antimicrobial resistance surveillance and infection control efforts. Regarding patient demographic, a slightly higher proportion of isolates was obtained from female patients (48.2%) compared with male patients (38.4%), while…
Conclusion
This study underscores the substantial clinical burden of Klebsiella infections, with Klebsiella spp. accounting for 13.7% of clinical isolates over the five-year period, predominantly K. pneumoniae. Urinary tract infections represented the most common source, followed by bloodstream, wound, and respiratory infections, highlighting the opportunistic behavior and clinical significance of Klebsiella species. In addition, high resistance rates to commonly used antibiotics particularly ceftazidime along with moderate resistance to several β-lactams and fluoroquinolones, reflect the growing challenge of antimicrobial resistance. Although the last-line agents such as colistin and tigecycline remained largely effective, emerging resistance trends remain concerning. The findings demonstrate a substantial burden of carbapenem-resistant…
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
