An important aspect of the drug evaluation process is to have an integrated benefit-risk assessment to determine, using some quantitative measures, whether the benefit outweighs the risk for the target population. A five-category random variable and three global scores were proposed by Chuang-Stein for benefit-risk assessment during clinical trials. When the data from multiple visits in clinical trials become available, a generalized linear mixed model based approach is proposed to model the probabilities of each subject falling into each of the five benefit-risk categories throughout the trial. Different variance-covariance structures are available to model the longitudinal trend. The estimates of the confidence intervals of the global measures are derived from Monte Carlo samples, and the decision rules can be determined based on the confidence intervals. Illustration of the methodology is provided using clinical trial data.