摘要
目的:建立小儿咳喘中医复诊医案疗效评价模型,识别和控制某些因素对结局的作用。方法:从现代数据库中获取符合纳入标准的中医复诊医案,对其信息进行提取、规范和量化处理,采用计算机Logistic回归分析及临床医生手工筛选的方法,选择合适的症状进行建模。结果:本数据共入选医案196例,其中实验组124例,对照组72例。医案共包含301个症状。通过计算机筛选及临床医生人工筛选,最后进入模型的变量为喉中痰鸣、咳嗽、喘、短气、咳痰、红舌、鼻塞对应的变量。患者确诊小儿咳喘病症的概率P=1/1+e-Z,其中z=1.20209x1+0.7436362x2+1.548785x3+0.897351x4+0.9337164x5-0.5829916x6+1.149407x7-1.602013。讨论:在之前研究的基础上,本研究认为建模时应充分挖掘复诊症状对于临床疗效评价的价值。
Objective： To establish the TCM referral medical effect evaluation model for pediatric cough, in order to i- dentify and control some effects of some factors on outcome. Methods： TCM medical records in accordance with the inclusion criteria were obtained from the modem database, then according to the extraction, specification and quantification, the appre- pilate symptoms were selected to establish model with Logistic regression analysis and bandselected. Results： The data were included in 196 cases, including 124 cases in the experimental group and the control group of 72 cases. There were 301symptoms. The corresponding variable of wheezing due to retention of phlegm in throat, cough, asthma, shortness of breath, expectoration, red tongue and rhinobyon were select into the model by computer and clinicians manual screening. The diagno- sis probability of cough and asthma in children is P=l/l＋e-z, z=l.20209xl＋0.7436362x2＋l.548785x3＋0.897351x4＋0.9337164xs- 0.5829916x6＋1.149407x7-1.602013. Conclusion： On the basis of the previous studies, this study considers modeling should fully excavate referral symptoms for clinical evaluation of value.
出处
《中医药导报》
2014年第2期17-18,21,共3页
Guiding Journal of Traditional Chinese Medicine and Pharmacy
基金
中国中医科学院第七批自主选题项目:中医药治疗咳嗽变异型哮喘疗效证据采集与分析(ZZ070310)
关键词
中医
复诊医案
疗效评价
数学模型
LOGISTIC回归
TCM
Referral medical record
Evaluation of efficacy
Mathematical model
Logistic regression
