Aaron Kornblith, MD

Associate Professor

Kornblith Data Science Lab: https://kornblithdatalab.ucsf.edu

Dr. Aaron Kornblith is an Associate Professor of Emergency Medicine and Pediatrics at the University of California, San Francisco. He is the research lead for the Division of Pediatric Emergency Medicine, co-HEDA PI for the Pediatric Emergency Care Applied Research Network (PECARN), and an affiliated faculty member of the UCSF Bakar Computational Health Sciences Institute & Center for Intelligent Imaging.

Dr. Kornblith's research program, funded by the NIH, NSF, the Pediatric Device Consortium, and the University of California, is dedicated to enhancing the diagnostic evaluation of sick and injured children through advanced data analytics and rigorous clinical trial validation. His research mission is to advance and deliver timely, expert-level emergency care for injured children, integrating safe, fair, and accurate AI-enhanced diagnostic strategies—driving precision medicine forward and improving care equity across all healthcare settings.

Publications

Analyzing patient perspectives with large language models: a cross-sectional study of sentiment and thematic classification on exception from informed consent.

Fast Interpretable Greedy-Tree Sums.

Reliability of Physician Estimation of Pelvic Free Fluid Volume on the Pediatric Focused Assessment with Sonography for Trauma.

Piloting a Diagnostic Foot and Ankle Fracture Sonographic Algorithm with Rural and Adolescent Patients.

Race, Neighborhood Disadvantage, and Prehospital Law Enforcement Handcuffing in Children With Behavioral Health Emergencies.

Evaluating the use of large language models to provide clinical recommendations in the Emergency Department.

Enhancing emergency department charting: Using Generative Pre-trained Transformer-4 (GPT-4) to identify laceration repairs.

Understanding a community's needs for an emergency department-based childhood injury prevention programme: a mixed-methods study.

Early Cold Stored Platelet Transfusion Following Severe Injury: A Randomized Clinical Trial.

Use of a Large Language Model to Assess Clinical Acuity of Adults in the Emergency Department.

Evaluating Large Language Models for Drafting Emergency Department Discharge Summaries.

ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance