基于GBM倾向评分法对疏血通注射液导致谷丙转氨酶异常变化的影响分析(6)
(1.Institute of Basic Research in Clinical Medicine， China Academy of Chinese Medical Sciences， Beijing 100700， China；
2. Statistical Institute of Renmin University， Beijing 100872， China； 3.The PLA Navy General Hospital， Beijing 100048， China)
[Abstract] Objective： To estimate treatment effects of Shuxuetong injection on abnormal changes on ALT index， that is， to explore whether the Shuxuetong injection harms liver function in clinical settings and to provide clinical guidance for its safe application. Method： Clinical information of traditional Chinese medicine(TCM) injections is gathered from hospital information system (HIS) of eighteen general hospitals. This is a retrospective cohort study， using abnormal changes in ALT index as an outcome. A large number of confounding biases are taken into account through the generalized boosted models (GBM) and multiple logistic regression model (MLRM) to estimate the treatment effects of Shuxuetong injections on abnormal changes in ALT index and to explore possible influencing factors. Result： The advantages and process of application of GBM has been demonstrated with examples which eliminate the biases from most confounding variables between groups. This serves to modify the estimation of treatment effects of Shuxuetong injection on ALT index making the results more reliable. Conclusion： Based on large scale clinical observational data from HIS database， significant effects of Shuxuetong injection on abnormal changes in ALT have not been found.
[Key words] Shuxuetong injection； hospital information system safety surveillance； weighted propensity score； ALT； real world clinical research
doi：10.4268/cjcmm20131824, 百拇医药(杨伟 易丹辉 谢雁鸣 杨薇 戴翼 支英杰 庄严 杨虎)
2. Statistical Institute of Renmin University， Beijing 100872， China； 3.The PLA Navy General Hospital， Beijing 100048， China)
[Abstract] Objective： To estimate treatment effects of Shuxuetong injection on abnormal changes on ALT index， that is， to explore whether the Shuxuetong injection harms liver function in clinical settings and to provide clinical guidance for its safe application. Method： Clinical information of traditional Chinese medicine(TCM) injections is gathered from hospital information system (HIS) of eighteen general hospitals. This is a retrospective cohort study， using abnormal changes in ALT index as an outcome. A large number of confounding biases are taken into account through the generalized boosted models (GBM) and multiple logistic regression model (MLRM) to estimate the treatment effects of Shuxuetong injections on abnormal changes in ALT index and to explore possible influencing factors. Result： The advantages and process of application of GBM has been demonstrated with examples which eliminate the biases from most confounding variables between groups. This serves to modify the estimation of treatment effects of Shuxuetong injection on ALT index making the results more reliable. Conclusion： Based on large scale clinical observational data from HIS database， significant effects of Shuxuetong injection on abnormal changes in ALT have not been found.
[Key words] Shuxuetong injection； hospital information system safety surveillance； weighted propensity score； ALT； real world clinical research
doi：10.4268/cjcmm20131824, 百拇医药(杨伟 易丹辉 谢雁鸣 杨薇 戴翼 支英杰 庄严 杨虎)