Open access
Sep 2026
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.
U. Kolaç, Mazlum Veysel Sili, Orhan Mete Karademir et al.
· Knee (Oxford) · 0 citations