Dr. John Lee has been awarded the Harvard Catalyst K12 Training Award to develop an AI/ML-driven, video-based method for automated, continuous assessment of respiratory distress in the emergency department (ED). This work aims to transform the subjective, intermittent bedside evaluation of respiratory distress into an objective, continuously quantifiable signal, with the goal of improving early detection of respiratory deterioration and clinical decision-making in acute care settings. The project also includes a prospective feasibility study evaluating continuous video-based monitoring of high-risk patients in the ED, with the long-term goal of making the ED a safer environment for patients at risk of clinical deterioration.

Emergency departments are the front door of the health care system. Every day, ED teams are asked to recognize serious illness, identify unmet needs, catch diagnostic risk, and make high-stakes decisions for patients they may be meeting for the first time. That work is essential, but the scale is enormous. Two new studies from members of our AI Division point to a common idea: AI may be most useful in emergency care when it helps clinicians notice what is otherwise too easy to miss.

Dr. Adrian Haimovich, the Director of the BIDMC Department of Emergency Medicine’s Division of Artificial Intelligence, spoke on Artificial Intelligence in Sepsis at last week’s prestigious and 25th annual International Conference of Emergency Medicine in Hamburg, Germany. He also contributed to two AI-related panel discussions.

This first and novel course, AI in Emergency Medicine, launches December 3 and 4 with a faculty of renowned experts in Clinical AI.

In new research by Brodeur et al., the OpenAI o1 large language model was tested directly against hundreds of physicians across diagnostic and management tasks—from published vignettes to brand-new ER patients—outperforming both human physicians and older models and pointing to its potential utility in clinical care.

Dr. John H. Lee, MD, PhD, of BIDMC and Harvard Medical School has been awarded the NFEM Scholar Program 2026 to develop an AI-driven, video-based system for continuously and objectively assessing respiratory distress in the emergency department.

The AI Division announces a new International Fellowship in Emergency Medicine Artificial Intelligence, equipping clinicians with the competencies to understand, evaluate, and implement AI systems—culminating in a ready-to-implement capstone project for their home institution.