Mazlum Veysel Sili

Comparative quality, accuracy, and readability of large language model responses to patient questions about robotic-assisted total knee arthroplasty.

Although Gemini 3 and DeepSeek demonstrated greater readability in selected comparisons, median responses across all models remained above recommended patient-education reading levels, and LLM-generated responses should be regarded as supplementary rather than standalone sources of patient information regarding RA-TKA.