Comparative Evaluation of ChatGPT, DeepSeek, and Physician-Generated Acupuncture Protocols—Multilingual Performance
COMPARISONA cross-sectional evaluation study compared ChatGPT, DeepSeek, and physician-generated acupuncture treatment protocols across Chinese and English language settings, examining both the quality of acupoint selection and the consistency of recommendations across linguistic contexts. Key Findings: - AI systems demonstrated substantial progress in encoding explicit acupuncture knowledge and performing systematic acupoint selection - Performance remained inconsistent in individualized treatment planning—the most clinically complex task - Significant variation emerged between Chinese and English outputs, suggesting language-specific training gaps in both models Challenges Identified: - Syndrome-specific reasoning (matching traditional diagnostic categories to treatment) remains underdeveloped - Bilingual or multilingual training corpora appear insufficient for consistent cross-language performance - Neither system reliably captures patient-specific factors (age, constitution, comorbidities) that inform TCM treatment individualization Implications: Enhancing AI-assisted traditional medicine systems requires investment in: - Expanded bilingual/multilingual training datasets with clinical context - Domain-specific modules for syndrome differentiation and individualization - Validation against established acupuncture protocols and clinical outcomes - Collaboration with TCM practitioners to ensure cultural and clinical authenticity ---
Subscribe to read full wiki analysis
Full wiki content — including source provenance, contradiction tracking, related pages, and analyst notes — is available to Subscriber members.
View Plans & SubscribeNew users get a 7-day trial — no credit card required.