Artificial intelligence across the emergency–disaster continuum: a scoping review and implications for nursing practice

Abstract Background Emergency care and disaster response are both characterised by surges in demand, time pressure and constrained resources. In this review, an emergency-disaster continuum was developed as an analytical lens for examining AI applications across routine emergency care and disaster response. Artificial intelligence (AI) has been examined in triage, risk detection, resource allocation, communication and simulation-based training. However, to our knowledge, no scoping review has mapped these applications across the continuum while explicitly considering their relevance to nursing practice. This review aimed to map current applications of AI in emergency and disaster settings through the lens of the emergency-disaster continuum and to examine their implications for nursing practice. Methods This scoping review followed the methodology recommended by the Joanna Briggs Institute (JBI) and was reported in accordance with PRISMA-ScR. Eight databases were searched from inception to 30 January 2026. Two reviewers independently screened studies and extracted data. Eligible studies examined AI applications relevant to functions commonly undertaken or influenced by nurses, including assessment, triage, communication, coordination, training, workflow and clinical decision support, in emergency or disaster contexts. Results Eighteen studies were included. Most were published in the past five years and study designs included retrospective model-development studies, simulation studies, quasi-experimental studies, one randomised controlled trial, and one conceptual framework analysis. The included AI applications were grouped into three broad functional areas: management and resource allocation; rapid triage and risk identification; and disaster training and communication. The studies involved AI-based decision-support systems, machine learning, deep learning, natural language processing, large language models, and computer vision. Conclusions Current evidence indicates that AI has mainly been examined as a means of supporting existing emergency and disaster workflows. Direct evidence concerning nurses, nursing workflows and nursing-sensitive outcomes remains limited. Future research should prioritise implementation research, nurse-involved co-design, workflow integration and validation in real-world disaster settings. Clinical trial number Not applicable.