Perspectives on artificial intelligence in clinical microbiology

Czech version

Authors: Jakub Hurych; Pavel Dřevínek
Authors‘ workplace: Ústav lékařské mikrobiologie, Fakultní nemocnice v Motole, 2. lékařská fakulta Univerzity Karlovy, Praha
Published in: Čes-slov Pediat 2025; 80 (5): 231-234.
Category:
doi: https://doi.org/10.55095/cspediatrie2025/044

Overview

Hurych J, Dřevínek P. Perspectives on artificial intelligence in clinical microbiology

Artificial intelligence (AI) has recently emerged as a revolutionary tool with the potential to fundamentally transform the operation of clinical microbiology laboratories. With its ability to automate routine tasks, analyze complex data sets, and recognize patterns often missed by the human eye, AI can significantly contribute to greater efficiency, standardization, and accuracy in laboratory diagnostics.

One of the key application areas is image data analysis—whether it involves interpreting microscopic smears (e.g., Gram staining) or digital reading of culture plates, where algorithms identify colonies, estimate their number, color, and morphology, thus supporting timely pathogen detection. AI also enhances workflows in molecular microbiology, for example, by evaluating PCR amplification curves or sequencing data. Increasingly, AI is being integrated into automated laboratory systems that combine robotic sample handling with digital imaging and algorithmic interpretation.

In the context of antimicrobial resistance (AMR), AI is used to analyze large datasets of antibiograms and genomic data to identify resistance patterns, predict clinical outcomes, and support decision-making regarding antibiotic therapy. Clinical decision support systems (CDSS) integrate laboratory results with clinical information, offering a more personalized approach to antimicrobial treatment.

However, the implementation of AI comes with several challenges—including the need for standardized training datasets, algorithm validation, and ensuring explainability for end-users. A key benefit remains the ability of AI to relieve microbiologists from repetitive manual work, enabling them to focus more on expert interpretation and consultative activities—precisely where their expertise delivers the highest added value.

Keywords:

artificial intelligence – Microbiology – Automation

Sources

1. Smith KP, Kirby JE. Image analysis and artificial intelligence in infectious disease diagnostics. Clin Microbiol Infect 2020; 26 : 1318–1323.

2. Tsitou VM, Rallis D, Tsekova M, Yanev N. Microbiology in the era of artificial intelligence: transforming medical and pharmaceutical microbiology. Biotechnology Biotechnological Equipment 2024; 38.

3. Dien Bard J, Prinzi AM, Larkin PM, et al. Proceedings of the Clinical Microbiology Open 2024: artificial intelligence applications in clinical microbiology. J Clin Microbiol 2025; 63: e0180424.

4. Smith KP, Wang H, Durant TJS, et al. Applications of artificial intelligence in clinical microbiology diagnostic testing. Clin Microbiol Newsletter 2020; 42 : 61.

5. Wensel CR, Pluznick JL, Salzberg SL, et al. Next-generation sequencing: insights to advance clinical investigations of the microbiome. J Clin Invest 2022; 132.

6. Alsulimani A, Akhter N, Jameela F, et al. The impact of artificial intelligence on microbial diagnosis. Microorganisms 2024; 12.

7. Hamprecht A, Muhsal L, van Dijk CC, et al. CarbaDetector: a machine learning model for detecting carbapenemase-producing enterobacterales from disk diffusion tests. Research Square (preprint platform): Carl von Ossietzky University Oldenburg 2025.

8. Peiffer-Smadja N, Delliere S, Rodriguez C, et al. Machine learning in the clinical microbiology laboratory: has the time come for routine practice? Clin Microbiol Infect 2020; 26 : 1300–1309.