ChatGPT Health, the new platform from OpenAI, was developed with the help of 260 physicians from across the world.
Many of those same physicians participated in HealthBench, OpenAI’s tool that evaluates how well its large language models perform on real-world healthcare tasks and how they get better over time, a company spokesperson told Becker’s in response to an inquiry Jan. 9.
Here are the health system-affiliated physicians who assisted with that project, according to a May 2025 HealthBench report:
— Albert Danso Osei, MD: UPMC (Pittsburgh)
— Ashwin Amurthur, MD: Mass General Brigham (Somerville, Mass.)
— Benjamin Briggs, MD, PhD: University of Rochester (N.Y.) Medical Center
— Bethel Mieso, MD: Stanford Medicine Children’s Health (Palo Alto, Calif.)
— Brian Han, MD: Stanford Health Care (Palo Alto, Calif.)
— Caroline Cherston, MD: NewYork-Presbyterian (New York City)
— Dania Lindenberg, MD: Scripps Health (San Diego)
— Nadine Kamel Jawad, MD: Henry Ford Health (Detroit)
— Emil Cohen, MD: MedStar Health (Columbia, Md.)
— Ethan Abbott, DO: Mount Sinai Health System (New York City)
— Manjiree Karandikar, MD: UCSF Health (San Francisco)
— Travis Zack, MD, PhD: UCSF Health (San Francisco)
— Uzair Ghori, MD: Froedtert Health (Milwaukee)
