论文部分内容阅读
【目的】采用决策树回顾性分析中西医结合治疗输卵管妊娠影响因子权重及预后的风险因素,为中西医治疗早期输卵管妊娠的预后提供临床证据。【方法】收集广州中医药大学第一附属医院妇科采用中西医结合治疗的住院病例350例,采用SPSS 19.0建立数据库,并导入Clementine 12.0进行统计分析,建立CART决策树模型。【结果】成功构建了决策树模型。从模型中的12个变量中共筛选出中西医治疗组的5个重要预后变量,即血人绒毛膜促性腺激素(HCG)值、首次孕酮值、月经是否规律、有无阴道流血、有无自然流产史,其权重值分别为0.388、0.236、0.125、0.125、0.125。其中血HCG值和首次孕酮值是治疗预后的最重要的因素。【结论】所构建的决策树模型符合输卵管妊娠临床诊断规律,可较准确地预测中西医结合治疗早期输卵管妊娠的预后。
【Objective】 The purpose of this study was to retrospectively analyze the risk factors of the weight and prognosis of tubal pregnancy by TCM combined with traditional Chinese and western medicine by using decision tree and provide clinical evidence for the treatment of early tubal pregnancy by TCM and WM. 【Methods】 A total of 350 inpatients with gynecology admitted by Department of Gynecology of the First Affiliated Hospital of Guangzhou University of Traditional Chinese Medicine were enrolled in this study. SPSS 19.0 was used to establish a database and imported into Clementine 12.0 for statistical analysis. The CART decision tree model was established. 【Result】 The decision tree model was constructed successfully. Five important prognostic variables of TCM-WM treatment group were screened from 12 variables in the model, namely HCG, first progesterone, regular menstruation, vaginal bleeding, presence or absence of vaginal bleeding The history of spontaneous abortion, the weight values were 0.388,0.236,0.125,0.125,0.125. The blood HCG value and the first progesterone value is the most important factor in the treatment of prognosis. 【Conclusion】 The constructed decision tree model conforms to the clinical diagnosis of tubal pregnancy, which can predict the prognosis of early tubal pregnancy more accurately.