潜在类别模型在围绝经期综合征中医证候研究中的应用

Application of latent class model in the classification of perimenopausal TCM syndrome

目的对围绝经期综合征中医症状、体征进行分类,探讨潜在类别模型在中医证候分类识别中的应用。方法自行设计调查问卷收集2014—2015年期间533例围绝经期综合征妇女的中医症状和体征信息,运用潜在类别模型对其中医证候进行识别。结果结合AIC、BIC等模型评价指标,结果显示含4个类别的潜在类别模型为最佳模型,依据症状和体征将533例围绝经期患者潜在类别分析分为4种中医证候:肝郁型(75人)、肾阳虚型(129人)、肾阴虚型(179人)、肾阴阳虚型(151人)。结论潜在类别分析(LCA)在统计推断方面更具有客观性,可以为中医证候分类及证候的标准化研究提供一种新的统计方法。

Objective To assess the application of latent class model（ LCA） in the classification of traditional Chinese medicine（ TCM） syndrome of perimenopausal syndrome in term of symptoms and physical signs. Methods Data of TCM symptoms and physical signs of 533 perimenopausal syndrome patients were collected and analyzed by LCA. Results Based on the standard of AIC and BIC, LCA identified the optimal model including four latent classes. The four types of TCM syndromes were stagnation of liver-qi syndrom,kidney yang deficiency type,kidney yin deficiency type and deficiency of kidney yin and yang. Conclusion LCA can be used as a powerful tool to provide a new method for establishing TCM syndrome criteria.