冠心病患者痰热互结证CHAID决策树识别模式的研究
|
摘要
目的:建立冠心病不稳定性心绞痛患者临床常规检测指标对痰热互结证的识别模式。方法:选取2010年4月至2011年4月多中心收集的冠心病不稳定性心绞痛患者411例的基本资料、中医四诊信息及临床常规检测指标进行归一化处理后,采用CHAID决策树方法从90个临床常规检测指标中自动提取痰热互结证的识别规律。对其中212例患者进行痰热互结证识别模式的外验证。结果:Cl离子、缩短分数、RDW-CV、血常规RBC、D-Ⅱ聚体、CK-MB、PTA和BUN共8个属性指标经筛选后进入决策树识别模型。该模型对411例患者的测试结果显示:敏感度为75.0%,特异度为86.9%,检验准确率为86.1%。外验证模型缺失RDW-CV,模型识别准确率为85.8%,敏感度为89.5%,特异度为85.5%。结论:临床常规检测指标经CHAID决策树方法筛选后,可以直观、清晰的进行冠心病不稳定性心绞痛患者痰热互结证的识别,自动归纳识别规律,在中医证型-生物学指标对应模式的数据挖掘中具备一定的优势。
Objective: To build a recognition mode of phlegm-heat stasis syndrome according to indexes of clinical routine examinations of patients with unstable angina( UA). Methods: From April 2010 to April 2011,the clinical basic data,TCM four-diagnosis information and clinical routine examination indexes of 411 patients with UA were collected and normalized,and the recognition rules of phlegm-heat stasis syndrome was automatically extracted from 90 clinical examination indexes by applying CHAID decision tree method. The verification of recognition mode of phlegm-heat stasis syndrome in 212 patients was conducted. Results: A total of8 indicators,including Cl ion,shortening fraction,RDW-CV,blood RBC,D-II mer,CK-MB,PTA and BUN were indexed into the decision tree model. The test results of 411 patients of the model showed that the sensitivity was 75. 0%,the specificity was86. 9%,and the correct rate was 86. 1%. The verification of association patterns lacked RDW-CV,and its correct rate was 85. 8%.The sensitivity was 89. 5%,and the specificity was 85. 5%. Conclusion: The CHAID decision tree model can clearly and directly conduct recognition of phlegm-heat stasis syndrome with the basis of clinical routine examination indexes,and automatically summarize recognition rules,which has certain advantages in data mining of syndrome-physiochemistry model.
Objective: To build a recognition mode of phlegm-heat stasis syndrome according to indexes of clinical routine examinations of patients with unstable angina( UA). Methods: From April 2010 to April 2011,the clinical basic data,TCM four-diagnosis information and clinical routine examination indexes of 411 patients with UA were collected and normalized,and the recognition rules of phlegm-heat stasis syndrome was automatically extracted from 90 clinical examination indexes by applying CHAID decision tree method. The verification of recognition mode of phlegm-heat stasis syndrome in 212 patients was conducted. Results: A total of8 indicators,including Cl ion,shortening fraction,RDW-CV,blood RBC,D-II mer,CK-MB,PTA and BUN were indexed into the decision tree model. The test results of 411 patients of the model showed that the sensitivity was 75. 0%,the specificity was86. 9%,and the correct rate was 86. 1%. The verification of association patterns lacked RDW-CV,and its correct rate was 85. 8%.The sensitivity was 89. 5%,and the specificity was 85. 5%. Conclusion: The CHAID decision tree model can clearly and directly conduct recognition of phlegm-heat stasis syndrome with the basis of clinical routine examination indexes,and automatically summarize recognition rules,which has certain advantages in data mining of syndrome-physiochemistry model.
引文
[1]姚美村,袁月梅,艾路,等.数据挖掘及其在中医药现代化研究中的应用[J].北京中医药大学学报,2002,9(5):20-23.
[2]罗林英,陈金雄.基于决策树的外科手术信息挖掘与研究[J].医学信息,2008,21(11):1936-1939.
[3]吕爱平,李梢,王永炎.从主观症状的客观规律探索中医证候分类的科学基础[J].中医杂志,2005,46(1):5-7.
[4]Zhao HH,Guo S,Chen J,et al.Characteristic Pattern Study of Coronary Heart Disease with Blood Stasis Syndrome Based on Decision Tree[J].International Conference on Bioinformatics&Biom,2010,4(4):1-3.
[5]Gibbons RJ,Chatterjee K,Dale J,et al.ACC/AHA/ACP-ASIM guidelines for the management of patients with chronic stable angina[J].J Am Coll Cardiol,1999,33(7):2092-2197.
[6]中华医学会心血管病学分会.不稳定性心绞痛诊断和治疗建议[J].中华心血管病杂志,2000,28(6):409-412.
[7]朱文峰,王永炎.中医临床诊疗术语-证候部分[M].北京:中国标准出版社,1997:17-20.
[8]国家食品药品监督管理局.中药新药临床研究指导原则[M].北京:中国医药科技出版社,2002:41.
[9]周景想,唐明,李洁,等.2029例冠心病心绞痛中医证候特点及组合规律分析[J].中国中西医结合杂志,2011,31(6):753-755.
[10]王阶,汤艳莉,何庆勇.冠心病心绞痛患者证候要素与生存质量的相关性[J].中医杂志,2010,51(2):154-163.
[11]王振裕,时亮,陈嘉兴.冠心病患者中医证候与冠状动脉造影相关性研究[J].中华中医药杂志,2009,24(9):1194-1197.
[12]徐蕾,贺佳,孟虹,等.决策树技术及其在医学中的应用[J].数理医药学杂志,2004,17(2):161-164.
[13]李锋刚.数据挖掘技术在新安医学研究中的应用[J].安徽中医学院学报,2005,24(6):12-14.
[14]李梢,张宁波,李志红,等.慢性乙型肝炎患者肝胆湿热证和肝郁脾虚证的决策树诊断模型初探[J].中国中西医结合杂志,2009,29(11):993-996.
[15]Kass GV.An exploratory technique for investigating large quantities of categorical data[J].Journal of the Royal Statistical Society,1980,29(2):119-127.
[16]石玲,王燕.婴幼儿死亡危险因素的研究——兼论CHAID方法的原理及应用[J].中国卫生统计,2002,19(5):283-285.
[17]赵琛,王敏,范茜,等.老年冠心病慢性心力衰竭并发电解质紊乱的临床特点[J].齐鲁医学杂志,2008,23(5):398-402.
[18]杜柏,商秀洋,胡元会,等.冠心病心力衰竭患者中医证型与心率变异性、醛固酮及心功能关系的研究[J].中西医结合心脑血管病杂志,2010,8(8):906-908.
[19]其其格,李耀扬,张鹏,等.冠心病不稳定性心绞痛气虚血瘀证与血清理化指标间相关性研究[J].中华中医药杂志,2011,26(2):380-383.
[20]Salomaa V,Stinson V,Kark JD,et al.Association of fibrionlytic parameters with early ather osclerosis The ARIC study.Therosis Risk in Communities Study[J].Circulation,1995,91(2):284-290.
[21]董琦,牛凡,杨涓.D-二聚体、纤维蛋白原与冠状动脉病变程度及左心功能的关系[J].中国医疗前沿,2011,6(2):3-4.
[22]何德化,李卫华,谢强,等.冠心病患者分泌型磷脂酶A2与高敏C反应蛋白、肌酸激酶的检测及其临床价值[J].医学临床研究,2008,25(3):515-517.
[23]金春梅,金基永.血清白蛋白尿素氮肌酐水平与冠心病的相关性初探[J].现代医药卫生,2010,26(19):2912-2914.
[24]陈克龙,樊永平.数据挖掘中的分类算法及其在中医证候学中的应用[J].中华中医药杂志,2011,26(3):469-473.
[25]史琦,王伟,陈建新,等.基于决策树的冠心病痰瘀互阻证识别模式研究[J].中华中医药杂志,2013,28(12):3523-3526.
[26]史琦,陈建新,赵慧辉,等.冠心病病人血瘀证的决策树模型研究[J].中西医结合心脑血管病杂志,2013,11(8):897-900.
[27]Shi Q,Zhao HH,Chen JX,et al.Study on Qi Deficiency Syndrome Identification Modes of Coronary Heart Disease Based on Metabolomic Biomarkers[J].Evidence-Based Complementary and Alternative Medicine,2014,2014(3):281829.
[2]罗林英,陈金雄.基于决策树的外科手术信息挖掘与研究[J].医学信息,2008,21(11):1936-1939.
[3]吕爱平,李梢,王永炎.从主观症状的客观规律探索中医证候分类的科学基础[J].中医杂志,2005,46(1):5-7.
[4]Zhao HH,Guo S,Chen J,et al.Characteristic Pattern Study of Coronary Heart Disease with Blood Stasis Syndrome Based on Decision Tree[J].International Conference on Bioinformatics&Biom,2010,4(4):1-3.
[5]Gibbons RJ,Chatterjee K,Dale J,et al.ACC/AHA/ACP-ASIM guidelines for the management of patients with chronic stable angina[J].J Am Coll Cardiol,1999,33(7):2092-2197.
[6]中华医学会心血管病学分会.不稳定性心绞痛诊断和治疗建议[J].中华心血管病杂志,2000,28(6):409-412.
[7]朱文峰,王永炎.中医临床诊疗术语-证候部分[M].北京:中国标准出版社,1997:17-20.
[8]国家食品药品监督管理局.中药新药临床研究指导原则[M].北京:中国医药科技出版社,2002:41.
[9]周景想,唐明,李洁,等.2029例冠心病心绞痛中医证候特点及组合规律分析[J].中国中西医结合杂志,2011,31(6):753-755.
[10]王阶,汤艳莉,何庆勇.冠心病心绞痛患者证候要素与生存质量的相关性[J].中医杂志,2010,51(2):154-163.
[11]王振裕,时亮,陈嘉兴.冠心病患者中医证候与冠状动脉造影相关性研究[J].中华中医药杂志,2009,24(9):1194-1197.
[12]徐蕾,贺佳,孟虹,等.决策树技术及其在医学中的应用[J].数理医药学杂志,2004,17(2):161-164.
[13]李锋刚.数据挖掘技术在新安医学研究中的应用[J].安徽中医学院学报,2005,24(6):12-14.
[14]李梢,张宁波,李志红,等.慢性乙型肝炎患者肝胆湿热证和肝郁脾虚证的决策树诊断模型初探[J].中国中西医结合杂志,2009,29(11):993-996.
[15]Kass GV.An exploratory technique for investigating large quantities of categorical data[J].Journal of the Royal Statistical Society,1980,29(2):119-127.
[16]石玲,王燕.婴幼儿死亡危险因素的研究——兼论CHAID方法的原理及应用[J].中国卫生统计,2002,19(5):283-285.
[17]赵琛,王敏,范茜,等.老年冠心病慢性心力衰竭并发电解质紊乱的临床特点[J].齐鲁医学杂志,2008,23(5):398-402.
[18]杜柏,商秀洋,胡元会,等.冠心病心力衰竭患者中医证型与心率变异性、醛固酮及心功能关系的研究[J].中西医结合心脑血管病杂志,2010,8(8):906-908.
[19]其其格,李耀扬,张鹏,等.冠心病不稳定性心绞痛气虚血瘀证与血清理化指标间相关性研究[J].中华中医药杂志,2011,26(2):380-383.
[20]Salomaa V,Stinson V,Kark JD,et al.Association of fibrionlytic parameters with early ather osclerosis The ARIC study.Therosis Risk in Communities Study[J].Circulation,1995,91(2):284-290.
[21]董琦,牛凡,杨涓.D-二聚体、纤维蛋白原与冠状动脉病变程度及左心功能的关系[J].中国医疗前沿,2011,6(2):3-4.
[22]何德化,李卫华,谢强,等.冠心病患者分泌型磷脂酶A2与高敏C反应蛋白、肌酸激酶的检测及其临床价值[J].医学临床研究,2008,25(3):515-517.
[23]金春梅,金基永.血清白蛋白尿素氮肌酐水平与冠心病的相关性初探[J].现代医药卫生,2010,26(19):2912-2914.
[24]陈克龙,樊永平.数据挖掘中的分类算法及其在中医证候学中的应用[J].中华中医药杂志,2011,26(3):469-473.
[25]史琦,王伟,陈建新,等.基于决策树的冠心病痰瘀互阻证识别模式研究[J].中华中医药杂志,2013,28(12):3523-3526.
[26]史琦,陈建新,赵慧辉,等.冠心病病人血瘀证的决策树模型研究[J].中西医结合心脑血管病杂志,2013,11(8):897-900.
[27]Shi Q,Zhao HH,Chen JX,et al.Study on Qi Deficiency Syndrome Identification Modes of Coronary Heart Disease Based on Metabolomic Biomarkers[J].Evidence-Based Complementary and Alternative Medicine,2014,2014(3):281829.