Publications by authors named "Maria Palwasha Khan"
Front Artif Intell
August 2024
Article Synopsis
- The study explores how effective consumer-facing large language models (LLMs) can be for helping clinicians diagnose complex clinical cases.
- Researchers compared the performance of three LLMs—Bing, Chat GPT, and Gemini—using a new grading rubric that focused on accuracy, readability, clinical interpretability, and safety.
- Findings indicate that the LLMs performed differently, with Gemini showing the best results, and the grading tool developed for this research proved to be a reliable way to evaluate the clinical output of these models.
