J Tradit Chin Med. 2014 Aug;34(4):504-10. doi: 10.1016/s0254-6272(15)30054-6.
Apply spectral clustering to analyze the patterns of symptoms in patients with chronic gastritis (CG).
Based on 919 CG subjects, we applied mutual information feature selection to choose the positively correlated symptoms with each pattern. Then, we used the Shi and Malik spectral clustering algorithm to select the top 20 correlated symptoms.
We ascertained the results of six patterns. There were three categories for the pattern of accumulation of damp heat in the spleen-stomach (0.00332). There were six categories for the pattern of dampness obstructing the spleen-stomach (0.02466). There were two categories for the pattern of spleen-stomach Qi deficiency (0.013 89). There were three categories for the pattern of spleen-stomach deficiency cold (0.009 15). There were five categories for the pattern of liver-Qi stagnation (0.01910). There were four categories for the pattern of stagnant heat in the liver-stomach (0.00585).
Most of the spectral clustering results of the symptoms of CG patterns were in accordance with clinical experience and Traditional Chinese Medicine theory. Most categories suggested the nature and/or location of the disease.
应用谱聚类分析方法分析慢性胃炎（CG）患者的症状模式。
基于 919 例 CG 患者，我们应用互信息特征选择方法选择与每种模式呈正相关的症状。然后，我们采用 Shi 和 Malik 谱聚类算法选择前 20 个相关症状。
确定了六种模式的结果。脾胃湿热积聚模式有三个类别（0.00332）。湿困脾胃模式有六个类别（0.02466）。脾胃气虚模式有两个类别（0.01389）。脾胃虚寒模式有三个类别（0.00915）。肝气郁结模式有五个类别（0.01910）。肝胃郁热模式有四个类别（0.00585）。
CG 症状谱聚类分析结果大多符合临床经验和中医理论。大多数类别提示了疾病的性质和/或部位。
