A 2025 study published in npj Digital Medicine assessed the diagnostic and treatment capabilities of seven large language models (LLMs) in Traditional Chinese Medicine (TCM) using a real-world acupuncture case.
Compared with three professional acupuncturists across five areas, Western diagnosis, TCM diagnosis, acupoint selection, needling technique, and herbal medicine, LLMs showed promising results.
GPT-4o, Qwen 2.5 Max, and Doubao 1.5 Pro performed best, particularly in TCM-specific domains. The study, involving 28 expert evaluators from China, South Korea, and the U.S., highlights the potential of LLMs to bridge access gaps and support culturally grounded healthcare, especially in TCM settings.