PREDICTIVE ALGORITHMS AND ANTIMICROBIAL RESISTANCE IN HEALTHCARE-ASSOCIATED INFECTIONS: PERSPECTIVES OF ARTIFICIAL INTELLIGENCE IN HEALTHCARE SECURITY

Abstract

Healthcare-Associated Infections (HAIs) remain a major challenge to patient safety, particularly due to the growing threat of antimicrobial resistance. In this scenario, artificial intelligence (AI) has emerged as a promising tool to enhance epidemiological surveillance and support clinical decision-making. This study aims to discuss the contributions of AI-based predictive algorithms to the early identification of risks associated with antimicrobial resistance in healthcare settings. A narrative literature review was conducted based on the analysis of national and international scientific publications addressing artificial intelligence, machine learning, antimicrobial resistance, and patient safety. The findings indicate that predictive algorithms can process large volumes of clinical data in real time, identify patterns of resistant microorganism spread, and assist healthcare professionals in selecting the most appropriate antimicrobial therapy. Furthermore, these technologies support the implementation of preventive measures, contributing to the reduction of hospital infections and treatment-related costs. It is concluded that the application of artificial intelligence in monitoring and preventing antimicrobial resistance has significant potential to strengthen healthcare safety. However, challenges related to data quality, technological infrastructure, and ethical considerations must be addressed to enable its broader implementation in healthcare services.