Artificial Intelligence in Bacterial Infections Control: A Scoping Review.

Area of Science:

• Medical Informatics
• Infectious Disease Control
• Artificial Intelligence in Healthcare

Background:

• Artificial intelligence (AI) is increasingly utilized across healthcare for diagnosis, treatment, and disease prevention.
• Despite AI's widespread adoption, its specific role and effectiveness in infection control lack clear clinical consensus.
• Bacterial infection control presents a critical area where AI applications warrant detailed examination.

Purpose of the Study:

• To conduct a scoping review of artificial intelligence applications in bacterial infection control.
• To characterize the current landscape of AI in preventing and controlling bacterial infections.
• To identify common AI techniques, applications, advantages, and limitations in this field.

Main Methods:

• A scoping review methodology based on the Arksey and O'Malley framework was employed.
• A comprehensive literature search was performed across PubMed, Embase, and Web of Science databases.
• Data from 54 eligible studies were extracted, mapped, and synthesized into thematic scopes.

Main Results:

• The majority of AI applications in infection control originate from high-income countries, particularly the USA.
• Machine learning is the most frequently used AI type, with pathogen identification and infection risk assessment being primary aims.
• Predictive modeling and risk assessment are key reported advantages, while model generalizability is a common limitation.

Conclusions:

• AI applications for bacterial infection control are predominantly reported from high-income nations, highlighting a gap in low-income country utilization.
• Further investment is needed in developing and validating AI models proven effective for infection control.
• Addressing challenges such as model generalizability is crucial for maximizing AI's impact on bacterial infection prevention and control.