EyeGPT for Patient Inquiries and Medical Education: Development and Validation of an Ophthalmology Large Language Model
Xiaolan Chen, Ziwei Zhao, Weiyi Zhang, Pusheng Xu, Yue Wu, Mingpu Xu, Le Gao, Yinwen Li, Xianwen Shang, Danli Shi, Mingguang He, Gunther Eysenbach, Andrew Coristine, Kai Jin, Marcel Lucas Chee, William Rojas-Carabali, Amit Saxena, Rafael Scherer · 2024
Read EyeGPT for Patient Inquiries and Medical Education: Development and Validation of an Ophthalmology Large Language Model by Xiaolan Chen, Ziwei Zhao, Weiyi Zhang, Pusheng Xu, Yue Wu, Mingpu Xu, Le Gao, Yinwen Li, Xianwen Shang, Danli Shi, Mingguang He, Gunther Eysenbach, Andrew Coristine, Kai Jin, Marcel Lucas Chee, William Rojas-Carabali, Amit Saxena, Rafael Scherer (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-11669878.txt.
Description
A large research team built EyeGPT, a language model tuned for eye care, in this 2024 study. General chat models often lack deep knowledge of a narrow field like ophthalmology, the study of the eye. EyeGPT starts from a general model called Llama2. The team reshaped it to answer patient questions and support medical teaching.
Three moves did the reshaping: role-play prompts, fine-tuning on about eighty-four thousand eye-related samples, and lookup in a medical database plus fourteen eye textbooks. Four eye doctors graded answers to one hundred twenty questions, simple and complex. They scored accuracy, clarity, trust, and empathy, and counted made-up answers. The best version beat the base model and is compared with doctors alone and doctors aided by the model.
Catalog record
| CREATOR | Xiaolan Chen, Ziwei Zhao, Weiyi Zhang, Pusheng Xu, Yue Wu, Mingpu Xu, Le Gao, Yinwen Li, Xianwen Shang, Danli Shi, Mingguang He, Gunther Eysenbach, Andrew Coristine, Kai Jin, Marcel Lucas Chee, William Rojas-Carabali, Amit Saxena, Rafael Scherer |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |