摘要
目的:分析肝硬化患者的脉诊信息特征。方法:分别采集肝硬化患者的脉诊信息并与正常人对照进行分析。在对脉诊信息预处理后选取连续的多个周期的脉搏波作为研究对象,对各个周期进行12次谐波的最小二乘(LS)回归并建立数学模型,获取193个特征参数,根据上述参数对2类人群的脉诊信息进行特征分析,分别进行主成分分析和LS回归与Lasso回归的分类判决,获得肝硬化患者脉诊信息的变化特征。结果:肝硬化患者的脉诊信息与正常人比较有较明显的差异,主成分分析的判决准确率为81%,7参数拟合的回归判决准确率为98.77%,Lasso回归判决准确率为89%。结论:肝硬化患者机体的病理变化可以在桡动脉脉诊信息中得到体现并在诊脉的不同部位呈现较强的特征性,该特征经过不同的数学方法得到印证。本研究为中医"独取寸口"的诊脉方法提供了一定的科学依据,并在一定程度上为中医分寸、关、尺不同部位的诊脉方式提供了科学基础。
Objective： To study the features in the pulse waves of cirrhosis patients.Methods： To collect the pulse waves of Cirrhosis patients and compare them with normal volunteers＇.We choose continuous cycles waves with different period length and then do the LSQ regression by 12 harmonics fitting which are correspond with every cycle lengths to build mathematical model and extract 193 parameters after pretreatment,then do principal component analysis and regression for classification and identification to find the features of cirrhosis patients＇ pulse waves by EFBLS.Result： There are significant differences between cirrhosis patients＇ pulse waves and the normal volunteers＇ and the accurate is 81% to identify by principal component analysis,the accurate of LSQ regression by 7 features is 98.77% and the accurate of Lasso is 89%.Conclusion： Pathological changes of cirrhosis patients can embody in pulse waves we collected from the radial artery and the characters of the waves change regularly in special places,and the result was confirmed by 3 kinds of analysis methods.This research can offer some scientific basis for taking pulse in radial artery in TCM,also for the method of feeling different places when pulse-taking.
出处
《中华中医药杂志》
CAS
CSCD
北大核心
2011年第10期2244-2247,共4页
China Journal of Traditional Chinese Medicine and Pharmacy
基金
国家"十一五"科技支撑计划项目(No.2006BAI08B01-02)
基本科研业务费课题(No.ZZ2006043
ZZ2010009)~~
关键词
肝硬化
脉诊信息
分类判决
主成分分析
谐波拟合
回归分析
Cirrhosis
Pulse waves
Classification and identification
Principal component analysis
Harmonic fitting
Regression analysis
