A Case Study in Personalized Medicine: Rilpivirine Versus Efavirenz for Treatment-Naive HIV Patients
研究利用基线病毒载量和CD4细胞计数等生物标志物，开发个性化治疗方案，以最大化病毒学应答率或复合结局中位数，并在HIV试验数据中验证了优化方案可能优于统一用药。
Rilpivirine and efavirenz are two major nonnucleoside reverse transcriptase inhibitors currently available in the U.S. for treatment-naive adult patients infected with human immunodeficiency virus (HIV). Two randomized clinical trials comparing the two drugs suggested that their relative efficacy may depend on baseline viral load and CD4 cell count. This article is concerned with the potential utilities of these biomarkers in developing individualized treatment regimes that attempt to maximize the virologic response rate or the median of a composite outcome that combines virologic response with change in CD4 cell count (dCD4). Working with the median composite outcome removes the need to assign numerical values to the composite outcome, as would be necessary if we were to maximize its mean, and reduces the influence of extreme dCD4 values. To estimate the target quantities for a given treatment regime, we use G-computation, inverse probability weighting (IPW), and augmented IPW methods to deal with censoring and missing data under a monotone coarsening framework. The resulting estimates form the basis for optimization in a class of candidate regimes indexed by a small number of parameters. A cross-validation procedure is used to remove the resubstitution bias in evaluating an optimized treatment regime. Application of these methods to the HIV trial data yields candidate regimes of different forms together with cross-validated performance measure estimates, which suggest that optimized treatment regimes may be able to improve virologic response (but not the composite outcome) over uniform regimes that prescribe one drug for all patients. Supplementary materials for this article are available online.