|
|||||
|
|
| 偏最小二乘法在肝炎后肝硬化中医证候分类建模中的应用 | |
| 引用本文： | 王磊,苏越,张琴,刘平,苏式兵.偏最小二乘法在肝炎后肝硬化中医证候分类建模中的应用[J].中西医结合学报,2008,6(11):1122-1128. |
| 作者姓名： | 王磊 苏越 张琴 刘平 苏式兵 |
| 作者单位： | 1. 上海中医药大学肝病研究所,上海市高校中医内科学E-研究院,肝肾疾病病证教育部重点实验室,上海,201203 2. 上海中医药大学中医复杂系统研究中心,上海,201203 3. 复旦大学上海市公共卫生临床中心中西医结合科,上海,201508 |
| 基金项目： | 国家重点基础研究发展计划(973计划)，上海市教育委员会重点学科建设基金，上海市教委资助项目，上海市教委资助项目 |
| 摘 要： | 目的：探讨偏最小二乘法（partial least-squares,PLS）在肝炎后肝硬化中医证候分类模型建立中的应用及临床价值。方法：拟定中医四诊等生物信息采集基本要求,用临床流行病学调查方法,采集278例肝炎后肝硬化患者症状、体征、舌象、脉象及临床实验室指标等生物信息;采用逐步回归方法筛选各证候相关指标,设证候类型为因变量矩阵,相关临床信息为自变量矩阵,所有变量均经列最大化处理后导入PLS程序中进行计算,采用留一法（Leave-One-Out,LOO）完成建模和样本的预测。结果：逐步回归建立的5个证候类型回归方程的决定系数R2均在0.7以上;在此基础上,基于PLS建立的肝炎后肝硬化中医证候判识模型对肝郁脾虚、肝肾阴虚、脾肾阳虚、湿热内蕴和瘀热蕴结等主证候的预测准确率分别为73.02%、68.71%、92.45%、84.17%和68.71%。结论：PLS法能提高中医临床生物信息的利用度,在中医复杂证候建模的研究中有一定的推广应用价值。 |
| 关 键 词： | 肝炎 肝硬化 证候 数学 模型 偏最小二乘法 |
Classification and modeling of traditional Chinese medicine syndromes in patients with posthepatitic cirrhosis by partial least-squares |
|
| Lei WANG,Yue SU,Qin ZHANG,Ping LIU,Shi-bing SU.Classification and modeling of traditional Chinese medicine syndromes in patients with posthepatitic cirrhosis by partial least-squares[J].Journal of Chinese Integrative Medicine,2008,6(11):1122-1128. | |
| Authors: | Lei WANG Yue SU Qin ZHANG Ping LIU Shi-bing SU |
| Institution: | Lei WANG1,Yue SU2,Qin ZHANG3,Ping LIU1,Shi-bing SU2 1.Institute of Liver Diseases,E-institute of Shanghai Traditional Chinese Medicine,Key Laboratory for Liver-Kidney Disease Pattern of Ministry of Education,Shanghai University of Traditional Chinese Medicine,Shanghai 201203,China2.Research Center for Traditional Chinese Medicine Complexity System,China3.Department of Integrated Traditional Chinese , Western Medicine,Shanghai Public Healt... |
| Abstract: | Objective:To investigate the classification and modeling of traditional Chinese medicine(TCM)syndromes in posthepatitic cirrhosis by partial least-squares(PLS)method,and to study the clinical application of PLS method in TCM research.Methods:Inclusion criteria,exclusion criteria and criteria for harvesting and inputting of the biological information such as symptoms,signs,tongue,pulse and biological parameters were established.Stepwise regression was used to analyze the clinical information,including clinic... |
| Keywords: | hepatitis liver cirrhosis symptom complex mathematics models partial least-squares |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |