Publications by authors named "Nila Kirupaharan"
Purpose: To analyze the accuracy and thoroughness of three large language models (LLMs) to produce information for providers about immune checkpoint inhibitor ocular toxicities.
Methods: Eight questions were created about the general definition of checkpoint inhibitors, their mechanism of action, ocular toxicities, and toxicity management. All were inputted into ChatGPT 4.
Article Synopsis
- The study evaluated how accurately and thoroughly three large language models (ChatGPT 4.0, Bard, and LLaMA) could generate information on ocular toxicities related to antibody-drug conjugates (ADCs).
- Twenty-two specific questions about two ADCs were tested, with responses rated by ocular toxicity experts using a 6-point scale for accuracy and completeness.
- Results showed that ChatGPT and Bard scored higher in accuracy than LLaMA, while all models demonstrated high completeness, indicating they can effectively handle specialized topics within ophthalmology.