AI-Driven Pathways to Operational Resilience and Quality Enhancement in Emergency Departments

Recent years have seen emergency departments (EDs) face escalating pressures due to rising patient volumes, unpredictable surges, and increasing operational complexity. This landscape has intensified challenges such as overcrowding, prolonged waiting times, and resource constraints, all of which threaten the quality, safety, and resilience of emergency medicine care. Advancements in artificial intelligence (AI) and machine learning (ML) introduce new possibilities to optimize critical processes within EDs—including patient-flow management, capacity planning, and continuous monitoring—by unlocking real-time data insights that support prompt, informed response to rapidly evolving conditions. However, full realization of these technologies is hindered by barriers related to integration, scalability, data governance, and ethical deployment. Despite promising studies demonstrating the predictive power of AI tools for patient arrivals, early deterioration detection, and dynamic resource allocation, the implementation of robust, equitable, and sustainable models remains an open area of exploration.This Research Topic aims to advance knowledge on the effective integration of AI-enabled solutions into emergency medicine care systems to enhance both operational resilience and the quality of healthcare delivery. The central objective is to identify and critically assess the strategies by which AI and ML tools—including analytical decision-support platforms and process automation frameworks—can alleviate ED congestion, improve patient outcomes, and enable continuous quality improvement. Specific questions include how AI-driven measurement systems can enhance real-time monitoring, what governance and infrastructure are necessary for scaling digital tools, and what ethical considerations must be addressed to ensure fairness and transparency in clinical decision-making. The Research Topic further seeks to investigate synergies between AI applications and established process improvement methodologies such as Lean Six Sigma, to guide the creation of sustainable workflows that adapt to changing demands in emergency settings.Contributions may encompass the operational, practical, and ethical dimensions of AI adoption relevant to disaster and emergency medicine. Submissions addressing, but not limited to, the following areas are welcomed:o AI-driven patient-flow optimization and capacity management to alleviate crowding and reduce length of stay.o Development and evaluation of operational decision support systems for Eds.o Performance measurement using statistical process control and key performance indicators powered by AI.o Implementation science perspectives on integrating digital tools into emergency workflows, with attention to interoperability and sustainability.o Governance models for data stewardship, transparency, and accountable AI deployment within emergency care contexts.o Application and impact of Lean Six Sigma methodologies in conjunction with AI for driving continuous operational improvement.o Common barriers to AI adoption in EDs (cultural, professional, legal, operational, or infrastructural).o Which stakeholders should be engaged (clinical staff, nursing leadership, operational managers, IT, data governance bodies, patients/public)?.o Implementation strategies and change - management approaches that can improve trust, usability, and sustained integration into routine workflows. Topic editors: Giovanni Improta, Teresa Rea, Arianna Scala, Alfonso Maria Ponsiglione, Paolo Gargiulo, Mario Damiano Toro Source: https://www.frontiersin.org/research-topics/78110/ai-driven-pathways-to-operational-resilience-and-quality-enhancement-in-emergency-departments