摘要
目前微观辨证研究多聚焦于疾病状态下的病证之变,而对健康状态下人体常态的认识与量化不足,一定程度上限制了中医在无明显病证人群中的早期预警与客观辨识能力。基于中医状态学理论,从“以常衡变”视角出发,提出构建中医常态微观参数数据库。通过标准化采集不同性别、年龄健康人群的多维度生理指标,结合统计学分析与人工智能技术,按人群特征分组建立常态微观指标数据库,挖掘异常微观指标的中医内涵及其对状态辨识的贡献度。该方法可为无显著病证征象的患者提供早期预警和干预依据,进一步推动中医诊断向客观化、精准化与数据驱动方向发展。
Currently,research on microscopic syndrome differentiation in traditional Chinese medicine(TCM)primarily focuses on the changes of syndromes and diseases under pathological states,while the understanding and quantification of the human body's normal state under healthy conditions are insufficient.This limitation somewhat restricted TCM to provide early warnings and objective identification in populations without obvious symptoms.Based on the TCM state theory and from the perspective of"evaluating abnormalities based on normal conditions",this paper proposes the construction of database for normal microscopic parameters in TCM.By standardizing the collection of multidimensional physiological indicators from healthy individuals of different genders and ages,and combining statistical analysis with artificial intelligence technology,a database of microscopic indicators under normal condition is established.This approach also explores the significance of abnormal microscopic indicators in TCM and their contribution to the identification of health states.Such a method can provide early warnings and a basis for intervention in patients without obvious symptoms,contributing to the development of TCM diagnosis towards objectivity,precision,and data-driven approaches.
作者
唐浩博
陈启亮
黎晖
TANG Haobo;CHEN Qiliang;LI Hui(The Fourth Clinical Medical College of Guangzhou University of Chinese Medicine,Guangzhou,510006;School of Basic Medical Sciences,Guangzhou University of Chinese Medicine)
出处
《中医杂志》
北大核心
2025年第24期2544-2548,共5页
Journal of Traditional Chinese Medicine
基金
国家自然科学基金(82305068)
国家重点研发计划(2023YFC3503002)
广东省普通高校青年创新人才类项目(2023KQNCX014)
广州市科技局青年博士“启航”项目(SL2024A04J01944)。
关键词
中医状态辨识
常态微观参数
数据库
traditional Chinese medicine state identification
microscopic parameters under normal condition
database
