A national survey on the integration of traditional Chinese medicine and artificial intelligence: attitudes and perceptions from the individuals with health needs

Background: Traditional Chinese medicine (TCM) plays an indispensable role in the healthcare system. Artificial intelligence (AI) opens a new pathway for TCM modernization, while also addressing critical healthcare challenges. The present national survey was conducted to assess the attitudes and perceptions of individuals with health needs regarding the integration of TCM with AI. Methods: A cross-sectional national survey was conducted at 13 medical institutions across China. A structured, self-reported questionnaire was administered to 2587 individuals with health needs, including patients seeking TCM/Western medical treatment and individuals undergoing routine physical examinations, between June 27th and July 11th, 2025. Results: A total of 1641 (63.4 %) respondents were familiar with the TCM-AI equipment, and 61.7 % respondents were willing to try TCM diagnosis and treatment services combined with AI. 43.5 % respondents trusted the diagnosis results provided by the TCM-AI equipment. In the subgroup analysis, respondents aged 18–34, with a bachelor's degree or associate's degree as their educational background, and working as employees of state organs, showed greater acceptance and trust towards the integration of TCM and AI (P < 0.005). The top three most promising applications were the intelligent syndrome differentiation system (46.9 %), TCM four diagnostic instruments (39.9 %), and intelligent TCM formula (39.0 %). Conclusion: The integration of TCM and AI demonstrates promising acceptance among health-seeking individuals in China, with younger and educated populations who have health demands for TCM showing particularly high trust, and intelligent syndrome differentiation systems highlight a clear pathway for AI to modernize TCM practice by augmenting diagnostic accuracy and treatment personalization.

Abstract licence: CC BY-NC-ND

20 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.