论文部分内容阅读
[目的]本课题采用传统多因素分析和基于倾向性评分的3种方法比较伽玛刀分次和单次治疗垂体腺瘤患者的疗效,证实倾向性评分可以用来平衡两个组的协变量,从而降低偏倚。[方法]采用t检验和简单线性回归方法逐个分析每一因素的作用,利用多因素回归平衡混杂因素来探讨处理方法的效果;倾向性评分方法均衡数据后采用1︰1配对、分层及分层后回归调整比较处理方法的效果。[结果]①多因素分析平衡了其他因素后处理方法仍然为术后疗效的显著影响因素。②经配对、分层后,伽玛刀分次治疗组垂体肿瘤的体积差小于对照组,差异均具有统计学意义,采用分层后回归调整处理方法后,分次伽玛刀治疗的体积增大风险是单次伽玛刀治疗的22.1%,分次伽玛刀治疗的效果要优于单次伽玛刀。③两方法结果一致,平衡了其他因素后处理方法不同术后疗效不同,分次伽玛刀治疗的效果要优于单次伽玛刀。[结论]倾向评分法能够有效地均衡各对比组间特征变量的分布和构成,并在组间均衡的基础上评价干预措施或危险因素与结果变量间的联系或作用。
[Objective] To compare the curative effect of Gamma Knife fraction and single treatment of pituitary adenoma by traditional multivariate analysis and propensity score based methods, propensity score can be used to balance the covariate of two groups , Thereby reducing bias. [Methods] The effect of each factor was analyzed one by one using t-test and simple linear regression method, and the effect of treatment method was discussed by using the multivariate regression to balance the confounding factors. After using the propensity score method to balance the data, 1: 1 matching, After the adjustment of the level of adjustment to compare the effect of treatment methods. [Results] ①Multivariate analysis balances the other factors that post-treatment methods are still significant influencing factors for postoperative efficacy. ② After paired and stratified, the volume difference of pituitary tumor in Gamma Knife divided treatment group was smaller than that in control group, and the difference was statistically significant. After stratified and regressive adjustment treatment, the volume increase of Gamma Knife treatment The big risk is 22.1% of single gamma knife treatment, sub-gamma knife treatment is better than a single gamma knife. ③ The results of the two methods are the same, balance the other factors Post-treatment Different effects after surgery, sub-gamma knife treatment is better than a single gamma knife. [Conclusion] The propensity score method can effectively balance the distribution and composition of the characteristic variables in each comparison group, and evaluate the connection or effect between interventions or risk factors and outcome variables on the basis of group balance.