|
Artificial intelligence and antimicrobial resistance in Bacteria
|
Monireh Rahimkhani1    , Maryam Gilani2 , Arya Daneshvar3 |
1- Department of Lab Medical Sciences, Faculty of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran , rrahimkhani@sina.tums.ac.ir
2- Faculty of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran
3- Department of Civil and Environmental Engineering, Amirkabir University of Technology, Tehran, Iran |
|
|
Abstract: (401 Views) |
Background and Aim: Antimicrobial resistance (AMR) represents a major global health challenge, requiring novel approaches to improve diagnosis, prediction, and clinical decision-making. In recent years, machine learning (ML), as a subset of artificial intelligence (AI), has been increasingly explored for predicting antibiotic resistance, accelerating AMR diagnostics, and supporting antibiotic prescribing decisions. This study aims to provide a critical review of current evidence on the application of ML in AMR, with a particular focus on algorithmic performance, clinical applicability, and practical limitations.
Materials and Methods: This narrative review was conducted utilizing a structured literature search of major scientific databases, including studies that applied ML-based approaches to resistance prediction, rapid AMR detection, or clinical decision support.
Results: The reviewed evidence indicates that while certain ML models demonstrate acceptable performance in specific, context-dependent settings, robust and consistent superiority over conventional statistical methods has not been established. Moreover, key limitations, such as limited generalizability, reliance on single-center data, the need for periodic model retraining, data quality and bias in electronic health records, and the inability of some models to prioritize narrow-spectrum antibiotics, remain substantial barriers to real-world clinical implementation.
Conclusion: Overall, current evidence suggests that ML should be viewed as a decision-support tool rather than a standalone solution in AMR management, and that its definitive impact on hard clinical outcomes will require further real-world evaluations and interventional studies. |
|
| Keywords: Antimicrobial resistance, Artificial intelligence, Machine learning |
|
|
Full-Text [PDF 800 kb]
(52 Downloads)
|
Type of Study: Review |
Subject:
Microbiology
Received: 2024/12/22 | Accepted: 2026/08/5 | Published: 2026/09/8
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
