摘要
中医治疗疾病时,首先需要把患者进行辨证分型,疾病的辨证分型标准主要是专家组通过讨论确定的,具有较强的主观性。本文介绍三种基于无标签数据建立辨证分型规则的方法:隐类分析、单步隐树分析和双步隐树分析,并基于801例肝炎肝硬化患者中医症状数据,对三种方法进行对照比较,明确它们各自的优势和不足,以便在临床研究中选择使用。这些方法的使用可以促进辨证分型的客观化,提高临床诊疗的一致性。
When using the traditional Chinese medicine to treat disease, the first step is to determine the syndrome ofpatient. Currently, the disease classification of syndrome is mainly discussed by doctor or expert group that has strongsubjectivity. In this paper, three methods for the syndrome classification based on the unlabeled data are compared andresearched: Latent class analysis, one-phase latent tree analysis and two-phase latent tree analysis. Based on the 801 hepatitis cirrhosis patients’ symptom unlabeled data, the three methods are compared and contrasted for their respectiveadvantages and disadvantages, which to choose appropriately for user in clinical research. The use of these methods canpromote the objectivity of classification syndrome; meanwhile improve the clinical diagnosis and treatment of consistency.
引文
1龚燕冰,倪青,王永炎.中医证候研究的现代方法学评述(一)-中医证候数据挖掘技术.北京中医药大学学报,2016,29(12):797-801.
2戴霞,郭伟星.中医证候诊断标准规范化研究概况.中医杂志,2011,18(2):168-171.
3王智瑜,王天芳.建立中医证候诊断标准体系思路的探讨.中华中医药杂志,2009,24(5):634-637.
4 Li Y,Aggen S,Shi S,et al.Subtypes of major depression:latent class analysis in depressed Han Chinese women.Psychol Med,44(15):3275-3288.
5 Smeden V,Naaktgeboren C A,Reitsma J B,et al.Latent class models in diagnostic studies when there is no reference standard-a systematic review.Am J Epidemiol,2014,179(4):423-431.
6张连文,袁世宏.隐结构模型与中医辨证研究(I)-隐结构法的基本思想以及隐结构分析工具.北京中医药大学学报,2006,29(6):365-369.
7王天芳,张连文,赵燕,等.隐结构模型及其在中医证候研究中的应用.北京中医药大学学报,2009,32(8):519-527.
8 Yang X S,Chong V.Identifying the Zheng in psoriatic patients based on latent class analysis of traditional Chinese medicine symptoms and signs.Chin Med,2014,9(1):1.
9蔡伟达.证候研究中常用的数据分析方法的文献研究及基于隐类的抑郁症隐变量分析.北京:北京中医药大学博士研究生学位论文,2015.
10陈丽平.基于隐结构模型的名老中医辨治慢支气管炎规律研究.南京:南京中医药大学博士研究生学位论文,2015.
11谢艳虹,许朝霞,王忆勤.隐结构模型在中医证候分类识别中的应用概况.中华中医药学刊,2015,33(2):286-289.
12张连文,许朝霞,王忆勤,等.隐结构分析与西医疾病的辨证分型(II):综合聚类.世界科学技术-中医药现代化,2012,14(2):1-6.
13张连文,傅晨,刘腾飞,等.隐结构分析与西医疾病的辨证分型(III):辨证规则的建立.世界科学技术-中医药现代化,2014,16(4):1-15.
14 Poon L K M,Liu A H,Zhang N L.UC-LTM:Unidimensional clustering using latent tree models for discrete data.International Journal of Approximate Reasoning,2018,92:392-409.
15香港科技大学计算机科学及工程学系.孔明灯隐结构分析软件(v5.0),2017,http://www.cse.ust.hk/~lzhang/ltm/softwares/Lantern.zip.
16 Zhang N L,Fu C,Liu T F,et al.A data-driven method for syndrome type identification and classification in traditional Chinese medicine.JIntegr Med,2017,15(2):110-123.
17 Schwarz G.Estimating the dimension of model.Ann Statist,1978,6(2):461-464.