Volume 29, Issue 3 (8-2026)
J Arak Uni Med Sci 2026, 29(3): 0-0 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Akbari M, Arsalani N, Dinmohammadi M, Abbasi Niasar A, Shahbazi Miraghaei B, Mosafer H, et al . Application of Artificial Intelligence in Prevention and Control of Hospital-Acquired Infections: A Narrative Review Study. J Arak Uni Med Sci 2026; 29 (3)
URL: http://jams.arakmu.ac.ir/article-1-8235-en.html
URL: http://jams.arakmu.ac.ir/article-1-8235-en.html
Mehran Akbari1 
, Narges Arsalani2 , Mohammadreza Dinmohammadi3 , Alireza Abbasi Niasar1 , Bahareh Shahbazi Miraghaei1 , Hadis Mosafer1 , Nasim Bagheri Moheb1 , Masoud Fallahi-Khoshknab4
, Narges Arsalani2 , Mohammadreza Dinmohammadi3 , Alireza Abbasi Niasar1 , Bahareh Shahbazi Miraghaei1 , Hadis Mosafer1 , Nasim Bagheri Moheb1 , Masoud Fallahi-Khoshknab4
1- PhD Student in Nursing, Student Research Committee, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran
2- Professor, Department of Nursing, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran
3- Associate Professor of Nursing, Department of Nursing, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran
4- Professor of Nursing, Department of Nursing, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran ,fallahi@uswr.ac.ir
2- Professor, Department of Nursing, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran
3- Associate Professor of Nursing, Department of Nursing, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran
4- Professor of Nursing, Department of Nursing, University of Social Welfare and Rehabilitation Sciences, Tehran, Iran ,
Abstract: (69 Views)
Abstract
Introduction: Hospital-acquired infections (HAIs) represent the most prevalent adverse events among hospitalized patients, and although evidence-based preventive strategies offer significant potential for reducing hospital-acquired infections, the integration of innovative technologies such as artificial intelligence holds promise for transformative improvements. This review aims to critically evaluate the application of artificial intelligence in the identification, prevention, and control of hospital-acquired infections.
Method: This narrative review was undertaken to explore the utilization of artificial intelligence in addressing HAIs. A systematic search was performed using the keywords “Artificial Intelligence,” “Machine Learning,” “Hospital-Acquired Infections,” “Infection Prevention,” “Infection Control,” “Healthcare-Associated Infection,” “Intelligent Systems,” and “HAI” across prominent databases including PubMed, Scopus, ScienceDirect, and Google Scholar. The search spanned publications from 2015 to 2026. Following an initial screening and subsequent detailed review, a total of ten articles were selected for comprehensive analysis.
Results: The reviewed literature indicates that machine learning algorithms—such as Support Vector Machines (SVM), Random Forest, XGBoost, and neural networks—as well as large language models like ChatGPT, demonstrate efficacy in risk prediction and intelligent detection or surveillance of HAIs. These AI-driven tools facilitate early identification of high-risk patients, enhance diagnostic sensitivity, and alleviate the workload associated with manual infection surveillance.
Conclusion: Artificial intelligence has the potential to render infection control surveillance more intelligent, real-time, and tailored to individual patient risk profiles. The broad adoption and integration of AI-based models are imperative to mitigate the incidence of hospital-acquired infections and to advance patient safety outcomes.
Introduction: Hospital-acquired infections (HAIs) represent the most prevalent adverse events among hospitalized patients, and although evidence-based preventive strategies offer significant potential for reducing hospital-acquired infections, the integration of innovative technologies such as artificial intelligence holds promise for transformative improvements. This review aims to critically evaluate the application of artificial intelligence in the identification, prevention, and control of hospital-acquired infections.
Method: This narrative review was undertaken to explore the utilization of artificial intelligence in addressing HAIs. A systematic search was performed using the keywords “Artificial Intelligence,” “Machine Learning,” “Hospital-Acquired Infections,” “Infection Prevention,” “Infection Control,” “Healthcare-Associated Infection,” “Intelligent Systems,” and “HAI” across prominent databases including PubMed, Scopus, ScienceDirect, and Google Scholar. The search spanned publications from 2015 to 2026. Following an initial screening and subsequent detailed review, a total of ten articles were selected for comprehensive analysis.
Results: The reviewed literature indicates that machine learning algorithms—such as Support Vector Machines (SVM), Random Forest, XGBoost, and neural networks—as well as large language models like ChatGPT, demonstrate efficacy in risk prediction and intelligent detection or surveillance of HAIs. These AI-driven tools facilitate early identification of high-risk patients, enhance diagnostic sensitivity, and alleviate the workload associated with manual infection surveillance.
Conclusion: Artificial intelligence has the potential to render infection control surveillance more intelligent, real-time, and tailored to individual patient risk profiles. The broad adoption and integration of AI-based models are imperative to mitigate the incidence of hospital-acquired infections and to advance patient safety outcomes.
Keywords: Artificial intelligence, hospital-acquired infections, infection prevention, infection control
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
