Leung D H, Wang Y
Department of Epidemiology and Biostatistics, Memorial Sloan-Kettering Cancer Center, 1275 York Avenue, New York, NY 10021, USA.
Control Clin Trials. 2001 Apr;22(2):126-38. doi: 10.1016/s0197-2456(00)00132-x.
The purpose of a phase I trial in cancer is to determine the level (dose) of the treatment under study that has an acceptable level of adverse effects. Although substantial progress has recently been made in this area using parametric approaches, the method that is widely used is based on treating small cohorts of patients at escalating doses until the frequency of toxicities seen at a dose exceeds a predefined tolerable toxicity rate. This method is popular because of its simplicity and freedom from parametric assumptions. In this paper, we consider cases in which it is undesirable to assume a parametric dose-toxicity relationship. We propose a simple model-free approach by modifying the method that is in common use. The approach assumes toxicity is nondecreasing with dose and fits an isotonic regression to accumulated data. At any point in a trial, the dose given is that with estimated toxicity deemed closest to the maximum tolerable toxicity. Simulations indicate that this approach performs substantially better than the commonly used method and it compares favorably with other phase I designs. Control Clin Trials 2001;22:126-138
癌症一期试验的目的是确定所研究治疗方法的剂量水平，使其产生的不良反应在可接受范围内。尽管最近在这一领域采用参数方法取得了重大进展，但广泛使用的方法是对一小群患者按递增剂量进行治疗，直到某一剂量出现的毒性频率超过预先设定的可耐受毒性率。这种方法很受欢迎，因为它简单且无需参数假设。在本文中，我们考虑了不宜假设参数剂量-毒性关系的情况。我们通过修改常用方法提出了一种简单的无模型方法。该方法假定毒性随剂量增加，对累积数据进行等渗回归拟合。在试验的任何时刻，给予的剂量是估计毒性被认为最接近最大耐受毒性的剂量。模拟表明，这种方法的表现明显优于常用方法，并且与其他一期试验设计相比也更具优势。《控制临床试验》2001年；22:126 - 138
