Artificial Intelligence in Emergency Medicine at Stanford
Stanford Emergency Medicine leads applied research and clinical projects in artificial intelligence (AI) for emergency medicine.
Our faculty develop and deploy machine learning, natural language processing (NLP), and large language model (LLM) tools to support emergency department operations, clinical decision-making, risk stratification, and digital care delivery.
Current AI projects span real-time data analytics, predictive modeling, equity-focused AI, telehealth, and generative AI, with an emphasis on integrating these technologies into emergency department workflows to improve patient outcomes, efficiency, and care delivery at scale.
Select Stanford Faculty Research in AI and Emergency Medicine (2024-2025)
The Role of Large Language Models in Transforming Emergency Medicine: Scoping Review
Reviews how large language models are being applied across emergency medicine, including clinical decision support, documentation, education, and operational workflows.
Read the study
Is Artificial Intelligence Ready to Take Over Triage?
Examines the readiness, limitations, and clinical implications of AI-driven triage tools in emergency department settings.
Read the study
Using Machine Learning to Discover Traumatic Brain Injury Patient Phenotypes: National Concussion Surveillance System Pilot
Applies machine learning methods to identify distinct patient phenotypes in traumatic brain injury using large-scale surveillance data.
Read the study
Learning From the EHR to Implement AI in Healthcare
Explores how electronic health record data can be leveraged to develop, evaluate, and implement AI tools in clinical care.
Read the study
AI Passed the Test, but Can It Make the Rounds?
Evaluates the gap between AI model performance and real-world clinical integration in healthcare environments.
Read the study
Hospitalization Prediction From the Emergency Department Using Computer Vision AI With Short Patient Video Clips
Uses computer vision and video-based AI to predict hospitalization risk from brief patient recordings in the emergency department.
Read the study
Deceptively Simple Yet Profoundly Impactful: Text Messaging Interventions to Support Health
Examines scalable, data-driven digital interventions, including automated messaging, to support patient health behaviors.
Read the study
Closing the Gaps in Alcohol Behavior Change: A Real-World Study of a Digital Intervention
Evaluates a real-world digital intervention using analytic methods to support behavior change after emergency department encounters.
Read the study