INTEGRATING AI INTO NURSING WORKFLOWS FOR INFECTION CONTROL: OPPORTUNITIES AND CHALLENGES

Author Name: 1. Jenifer Singh 2. Dr. Rahul Tiwari 3. Harshada Joshi Inamadar 4. R.Saranya 5. Priyanak Jigar Bhatt 6.Rajnish Pathak 7. Rojln Tigga

Volume/Issue: 07/05

Country: India

DOI NO.: 08.2020-25662434 DOI Link: https://doi-ds.org/doilink/10.2026-96549758/UIJIR

Affiliation:

1. Training officer & Independent Researcher, India
2. Associate Professor, Mandsaur University, Mandsaur, Madhya Pradesh
3. Nursing Tutor, MGM College of Nursing, Vashi, Navi Mumbai
4. Assistant Professor, The Oxford college of nursing ,Bangalore, Karnataka
5. Associate Professor , Bhagwan Mahavir School of Nursing, Bhagwan Mahavir University, Surat, Gujarat
6. Assistant Professor, Bhagwan Mahavir School of Nursing, Bhagwan Mahavir University, Surat, Gujarat
7. Associate Professor, Krishna School of Nursing, KPGU, Vadodara, Gujarat

ABSTRACT

Background: Healthcare-associated infections (HAIs) remain a major challenge to patient safety and healthcare quality. Nurses are central to infection prevention and control (IPC), performing hand hygiene, personal protective equipment (PPE) use, catheter and wound care, environmental safety practices, surveillance, documentation, patient education, and early recognition of infection. At the same time, increasing clinical workloads, fragmented documentation, staffing pressures, and the growing volume of health data create opportunities for artificial intelligence (AI) to support nursing workflows. Aim: This review examines the opportunities, challenges, and implementation considerations associated with integrating artificial intelligence into nursing workflows for infection prevention and control. Methods: An integrative narrative review was developed using recent peer-reviewed literature and authoritative guidance concerning AI in nursing, healthcare-associated infection surveillance, hand-hygiene monitoring, clinical decision support, PPE assessment, antimicrobial stewardship, data governance, and ethical implementation. Evidence from PubMed-indexed literature, systematic and scoping reviews, and international health organizations was synthesized thematically. Results: AI can potentially strengthen nursing-led infection control through automated surveillance, early identification of infection risk, hand-hygiene monitoring, PPE training and compliance assessment, clinical decision support, antimicrobial stewardship, automated documentation, environmental monitoring, and outbreak detection. Recent evidence indicates that AI models can perform well in HAI detection and prediction; however, translation into routine clinical practice remains limited. Major barriers include data quality, interoperability, algorithmic bias, privacy and cybersecurity risks, alert fatigue, inadequate AI literacy, workflow disruption, unclear accountability, implementation costs, and the risk of excessive reliance on automated recommendations. Conclusion: AI should be implemented as a nurse-supportive technology rather than a replacement for professional nursing judgment. Successful integration requires participatory design involving nurses, robust data governance, and interoperability with electronic health records, transparent algorithms, appropriate validation, AI literacy, continuous monitoring, and clearly defined human oversight. Future research should move beyond model accuracy toward prospective evaluation of patient outcomes, infection rates, nursing workload, cost-effectiveness, usability, equity, and sustainability.

Key words: Artificial intelligence; nursing; infection prevention and control; healthcare-associated infections; machine learning; hand hygiene.