In clinical research and development, interim monitoring is critical for better decision‐making and minimizing the risk of exposing patients to possible ineffective therapies. For interim futility or efficacy monitoring, predictive probability methods are widely adopted in practice. Those methods have been well studied for univariate variables. However, for longitudinal studies, predictive probability methods using univariate information from only completers may not be most efficient, and data from on‐going subjects can be utilized to improve efficiency. On the other hand, leveraging information from on‐going subjects could allow an interim analysis to be potentially conducted once a sufficient number of subjects reach an earlier time point. For longitudinal outcomes, we derive closed‐form formulas for predictive probabilities, including Bayesian predictive probability, predictive power, and conditional power and also give closed‐form solutions for predictive probability of success in a future trial and the predictive probability of success of the best dose. When predictive probabilities are used for interim monitoring, we study their distributions and discuss their analytical cutoff values or stopping boundaries that have desired operating characteristics. We show that predictive probabilities utilizing all longitudinal information are more efficient for interim monitoring than that using information from completers only. To illustrate their practical application for longitudinal data, we analyze 2 real data examples from clinical trials.

BACKGROUND AND OBJECTIVES:Renal transplant recipients with pre-existing diabetes (PD) have reduced graft survival and increased risk of mortality and ischemic heart disease compared with nondiabetic transplant recipients. To assess the effect of belatacept in this high-risk group, we evaluated outcomes of the subpopulation with PD from previously published BENEFIT and BENEFIT-EXT trials. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS:A post hoc analysis evaluated pooled data from BENEFIT (living donors or standard criteria donors) and BENEFIT-EXT (extended criteria donors). Patients were randomized to receive cyclosporine or a more intensive (MI) or less intensive (LI) belatacept regimen. RESULTS:Of 1209 intent-to-treat patients, 336 had PD. At 12 months, the belatacept LI arm demonstrated a numerically higher rate of patients surviving with a functioning graft (90.4% MI [103 of 114], 92.8% LI [90 of 97], and 80.8% cyclosporine [101 of 125]), and fewer serious adverse events than cyclosporine or MI patients. Three cases of posttransplant lymphoproliferative disorder were reported in LI patients, one involving the central nervous system. Higher rates (% [95% confidence interval]: 22.8% MI [15.1 to 30.5]; 20.6% LI [12.6 to 28.7]; 14.4% cyclosporine (8.2 to 20.6]) and grades of acute rejection were observed with belatacept. Measured GFR (ml/min per 1.73 m(2), 59.8 MI; 62.5 LI; 45.4 cyclosporine), and cardiovascular risk profile were better for belatacept versus cyclosporine. CONCLUSIONS:In post hoc analysis of patients with PD, patient/graft survival and renal function at 12 months were numerically higher with belatacept versus cyclosporine, but not statistically significant. Further study is necessary to confirm the benefits belatacept may provide in these patients.

Florman, S.; Durrbach, A.; Larsen, C.; Pestana, J. M.; Vanrenterghem, Y.; Vincenti, F.; Block, A.; Garg, P.; Copley, B.; Duan, T.; Grinyó, J. M. Author Information