A comparative study of GPT-4o and human ophthalmologists in glaucoma diagnosis
Junxiu Zhang, Yao Ma, Rong Zhang, Yanhua Chen, Mengyao Xu, Su Rina, Ke Ma · 2024
Read A comparative study of GPT-4o and human ophthalmologists in glaucoma diagnosis by Junxiu Zhang, Yao Ma, Rong Zhang, Yanhua Chen, Mengyao Xu, Su Rina, Ke Ma (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11621452.txt.
Description
Junxiu Zhang and co-authors compared a leading AI chatbot with eye doctors at finding glaucoma in a 2024 study. The disease harms the optic nerve and can blind if missed. The team wanted to know whether the model could stand in for doctors or only help them.
Twenty-six cases, drawn from public stores and hospital records, were judged by the model and by three doctors of varied experience. The model scored well below the doctors on the main diagnosis and on how full its answers were. On listing other possible diseases, it matched the doctors and gave the fullest lists. The authors say the model is not ready to diagnose alone. They see it as a helper for hard cases while human skill stays in charge.
Catalog record
| CREATOR | Junxiu Zhang, Yao Ma, Rong Zhang, Yanhua Chen, Mengyao Xu, Su Rina, Ke Ma |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 25 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |