Towards Bridging Generalists to Subspecialists With Large Language Models
Status: Recruiting
Location: See location...
Intervention Type: Other
Study Type: Interventional
Study Phase: Not Applicable
SUMMARY
This study evaluates the impact of large language models (LLMs) versus traditional decision support tools on clinical decision-making in cardiology. General cardiologists will be randomized to manage real patient cases from a cardiovascular genetic cardiomyopathy clinic, with or without AI assistance. Each case will be assessed by two cardiologists, and their responses will be graded by blinded subspecialty experts using a standardized evaluation rubric.
Eligibility
Participation Requirements
Sex: All
Minimum Age: 18
Healthy Volunteers: f
View:
• Board certified or board eligible Cardiologist.
Locations
United States
California
Stanford
RECRUITING
Palo Alto
Contact Information
Primary
Jack W O'Sullivan, MBBS, DPhil
jackos@stanford.edu
+16507367878
Backup
Euan A Ashley, BSc, MB ChB, DPhil
deptmedchair@stanford.edu
+16507367878
Time Frame
Start Date: 2025-01-10
Estimated Completion Date: 2025-12
Participants
Target number of participants: 12
Treatments
Active_comparator: Large Language Model
This group will be given access to a Large Language Model
No_intervention: Usual resources
Group will not be given access to a Large Language Model but will be encouraged to use any resources they usually use in their practice besides large language models (UpToDate, Dynamed etc).
Related Therapeutic Areas
Sponsors
Leads: Stanford University
Collaborators: Google LLC.