医学多变量追踪数据的生长曲线模型

Multivariate growth curve model of longitudinal data in medical research

目的 研究医学追踪观测数据的多变量生长曲线模型 .方法 对两种药物治疗 12 0例患者后的舒张压和收缩压追踪观测数据用多元方差分析方法进行生长曲线模型检验 ,对模型系数作极大似然估计并进行组间比较 ,分析方法用SAS/ IML软件编程得以实现 .结果 用药后患者的舒张压和收缩压随时间的变化而变化 ,且两个药物组曲线的变化趋势是不相同的 ,第 1组的变化相对平缓 ,而第 2组起伏波动较大 ,用药后第 1组的舒张压和收缩压相对来说均较第 2组为高 .

AIM To study multivariate growth curve model of longitudinal data in medical research. METHODS Both diastolic and systolic blood pressure longitudinal data collected on 120 drug abusers after their taking two kinds of medicine were analyzed by using multivariate growth curve model. The hypothesis of specification of the model was tested by multivariate analysis of variance, model coefficients were estimatedby using maximum likelihood estimation method, and the effects across treatment groups were compared. Related analysis methods were programmed with SAS/IML code. RESULTS Both diastolic and systolic blood pressures changed with time after treatment, and the trends across treatment groups were different. Group 1 changed slowly, but group 2 had a greater curvature. Both diastolic and systolic blood pressures in group 1 were higher than those in group 2. CONCLUSION Multivariate growth curve model can be used to effectively analyze the dynamic change trend of multivariate longitudinal data in medical research, and make comparative studies across groups.