AI-Enhanced POCUS in Emergency Care

Point-of-care ultrasound (POCUS) is an essential component of emergency medicine, enabling rapid bedside assessment across a wide spectrum of acute conditions. Its effectiveness, however, remains constrained by operator dependency, variable image quality, and time-critical decision-making. Recent advances in artificial intelligence (AI) offer opportunities to augment POCUS by supporting image acquisition, interpretation, and quantitative analysis. This narrative review synthesizes current evidence on AI-enhanced POCUS applications in emergency care, encompassing trauma, non-traumatic emergencies, integrated workflows, resource-limited settings, and education and training. Across trauma settings, AI-assisted POCUS has demonstrated promising performance for automated detection of pneumothorax, hemothorax, and free intraperitoneal fluid, supporting standardized eFAST examinations and rapid triage. In non-traumatic emergencies, AI-enabled cardiovascular, pulmonary, and abdominal applications provide automated measurements and pattern recognition that can approach expert-level performance when image quality is adequate. Integrated AI-POCUS systems and educational tools further highlight the potential to expand ultrasound access, support non-expert users, and standardize training. Nevertheless, important limitations persist, including limited generalizability, dataset bias, device heterogeneity, and uncertain impact on clinical decision-making and patient outcomes. In conclusion, AI-enhanced POCUS is transitioning from proof-of-concept toward early clinical integration in emergency medicine. While current evidence supports its role as a decision-support tool that may enhance consistency and efficiency, widespread adoption will require prospective multicentre validation, development of representative POCUS-specific datasets, vendor-agnostic solutions, and alignment with clinical, ethical, and regulatory frameworks.