臨床試驗之連續性滿足點Phase II/III調適性設計

An Alternative Phase II/III Design in Clinical Trials for Continuous Endpoint

劉佳佩(Chia-Pei Liu)

指導教授 ： 蕭金福

國立交通大學/理學院/統計學研究所/碩士(2010年)

https://doi.org/10.6842/NCTU.2010.00292

摘要

醫藥研發是非常具有風險、複雜、高成本又費時的過程。其中大部分的時間和經費是用於臨床試驗。因此，我們需要更有效率且可靠的臨床試驗方法，來分析資料及評估藥物的風險和效用，以減少病人樣本數，縮短發展期間，進而降低藥物開發成本。在本文中，我們發展一個連續性滿足點的phase II / III試驗設計，在phase II試驗中評估不同劑量的試驗藥物與對照組兩兩之間比較。在phase II試驗，隨機分派病人接受一個試驗藥物劑量或對照組。如果一個或一些劑量有統計顯著的療效優於對照組，這些劑量將被選中進入phase III試驗。此外，病人在被選中的劑量組與對照組將繼續進入phase III試驗。同時也將招募新的病人，隨機分配至所選的藥物劑量組或對照組。我們會計算每階段的檢定統計量之臨界值，以確定各藥物劑量在試驗過程中是否應被淘汰或被選擇，並計算合適的樣本大小以方便招募病人。在我們的設計中，由於將傳統的phase II試驗及phase III試驗合併成單一的試驗，同時，在phase II試驗收集的資料也會進入phase III試驗做最後的分析，因此可以減少樣本數量和節省試驗時間。

關鍵字

調適設計 ； 臨床試驗 ； phase II/III設計

並列摘要

The pharmaceutical development is very risky, complex, costly, and time-consuming. Much of time and costs were spent in clinical trials. Hence, we need the methods which can be more efficient and reliable to minimize sample size, shorten the period of development duration, and thus reduce the cost for drug development. In this paper, we demonstrate the phase II/III design for continuous endpoint based on pariwise comparisons at the phase II stage when evaluating the efficacy of drugs. For the phase II stage, patients are randomly assigned to receive either one of the several doses of the test drug or to the control group. If one or some doses are declared to have a statistically significantly superior efficacy over control, these doses will be selected for the phase III trial. In addition, the patients in the selected doses and control groups will be continued to the phase III stage. Also new patients will be recruited and randomized to receive either the selected doses of the test drug or to the control group. We will find the critical value at each stage to determine whether the treatment should be dropped out or selected in the process of the trials, and compute the required sample size for facilitating recruitment of patients. In our design, since we integrate the traditional phase II and III trials into a single trial, and the data collected from phase II stage will also be included into the final analysis, sample size reduction and trial time saving may be possible.

並列關鍵字

adaptive design ； clinical trial ； phase II/III design

參考文獻

1. Bischoff W, and Miller F. Adaptive two-stage test procedures to find the best treatment in clinical trials. Biometrika. 2005;92:197-212.

2. Gupta SS. Probability integrals of multivariate normal and multivariate t. Ann. Math. Statist. 1963;34:792-828.

3. Maca J, Bhattacharya S, Dragalin V, Gallo P, and Krams M. Adaptive seamless Phase II/III designs—Background, operational aspects, and examples. Drug Information Journal. 2006;40:463-473.

4. Posch M, Koenig F, Branson M, Brannath W, Dunger-Baldauf C, and Bauer P. Testing and estimation in flexible group sequential designs with adaptive treatment selection. Stat Med. 2005;24:3697-3714.

5. Schaid DJ, Wieand S, and Therneau TM. Optimal two-stage screening designs for survival comparisons. Biometrika. 1990;77:507-13.