Dual perspectives on large language models in rheumatology: physician-rated quality and patient-centered usability of GPT-4o versus DeepSeek-V3

Puntos clave

• This research aims to evaluate the quality of large language models from both physician and patient perspectives in rheumatology.
• Comparison of GPT-4o and DeepSeek-V3 based on physician ratings and patient usability feedback.
• Evaluation of topic-aware governance for integrating LLMs in healthcare practices.
• Assessment of queries focusing on guideline compliance and context-sensitive communication.
• Identified areas where LLMs can effectively substitute human input and areas that require human oversight.
• Proposed a layered governance approach for safe integration of LLMs in patient education.

Resumen