6th Edition of World Nursing Science Conference 2026

Abstract

Background: Healthcare systems contribute significantly to global carbon emissions, with clinical decision-making accounting for a substantial proportion of resource consumption and environmental impact. Nurses, as the largest group of healthcare professionals and key decision-makers in patient care, play a critical yet underexplored role in promoting environmentally sustainable practice. However, current nursing education and clinical frameworks rarely incorporate environmental impact into real-time clinical decision-making. There is a lack of structured tools that enable nurses to understand the carbon consequences of routine clinical choices, representing an important gap in sustainable healthcare practice.
Aim: This study aims to develop and evaluate an AI-supported simulation system that provides real-time carbon footprint feedback to inform nursing clinical decision-making and promote environmentally sustainable care practices.
Methods: A mixed-methods simulation-based study design was employed. A generative AI-enhanced clinical decision support system was developed to integrate carbon footprint data into nursing care scenarios. The system provided real-time feedback on estimated carbon emissions associated with common clinical actions (e.g., diagnostic testing, treatment selection, infection control strategies) and suggested lower-carbon alternatives where clinically appropriate. Nursing students and registered nurses participated in standardized simulation scenarios involving acute and chronic care situations. Participants were randomly assigned to either an AI-supported carbon feedback group or a standard simulation group. Quantitative outcomes included clinical decision patterns, selection of high- vs low-carbon interventions, and sustainability awareness scores. Qualitative data were collected through reflective debriefing interviews focusing on decision-making processes and perceived feasibility of integrating environmental considerations into clinical practice.

Results: Preliminary findings indicate that participants receiving real-time carbon feedback demonstrated increased awareness of environmental impact in clinical decision-making. The intervention group showed a higher tendency to select low-carbon alternatives when clinical outcomes were equivalent. Participants reported that AI-generated feedback prompted critical reflection on resource use and enhanced understanding of the environmental consequences of routine nursing actions. Importantly, nurses emphasized the importance of balancing patient safety, clinical effectiveness, and environmental sustainability, highlighting the need for structured decision support tools.
Conclusion: Integrating real-time carbon footprint feedback into nursing decision-making represents a novel and feasible approach to embedding environmental sustainability within clinical practice. This AI-supported innovation extends traditional nursing judgement frameworks by incorporating environmental impact as a complementary dimension of care. The approach has the potential to empower nurses as active contributors to climate-conscious healthcare systems while maintaining high standards of patient safety and care quality. Further research is needed to evaluate long-term behavioural change and scalability in real clinical environments.