Confirm and Explore: A Stepwise Approach to Clinical Study Designs
- PDF / 10,523,146 Bytes
- 10 Pages / 612 x 792 pts (letter) Page_size
- 75 Downloads / 289 Views
145
Confirm and Explore: A Stepwise Approach to Clinical Study Designs
Naitee ling, PhD Researchand Development, Pfizer Inc, New London, Connecticut
Key Words Phase 2 / 3 clinical study design; Dose selection; Proof of concept; Dose ranging Correspondence Address Dr. Naitee Ting, Pfizer Inc. M S 6025 -B3141, 5 0 Pequot Ave., New London, CT 06320 (email: [email protected]).
In general, the scientific learningprocess begins with exploration. scientists learn from explomtory findings, generate a new hypothesis, and then pe$orm experiments to confirm the hypothesis. After they do more explomtion,and learn more, scientistscontinuewith this process. The process is to explore first, then confirm, next explore and confirm again, and so on. The same is true for the entire drug development ProCeSS. Howeve in designing an individual phase 2 or 3 clinical trial, this thinking process needs to to be reversed because each studv is desimed w address a specific clinical quktion. This quation is fmulated as the primary objectbe of
INTRODUCTION One of the most important scientific breakthroughs in 20th-century medicine was the randomized controlled clinical trial. The foundation of modern clinical trials is randomization, which is a statistical concept. This is why the two most critical sciences involved in clinical trials are medicine and statistics. Without the close collaboration between clinicians and statisticians in the later part of the 20th century and the beginning of the 21st, there would not have been so many important drugs and biologics available to help improve human health and extend life. It should be noted that contributions of statistical science to modern medicine are not limited to statistical methods for estimating sample sizes or calculating P values or confidence intervals. In addition to these methods, the indispensable and invaluable contributions are statistical thinking and statistical concepts. Clinical trial designs and clinical development programs are all based on these concepts. One example is statistical hypothesis testing-the null hypothesis is that there is no difference between the test drug and placebo. However, unless there is
the study Clinical trials are designed to address this well-defined study objed’ve. Hence this part is a confirmatory step. After the primary objectbe is achieved, scientists then explore all available data and see what additional information can begenemtedfrom the stuQ. In this article, we discuss the thinking process of clinical trials. It is clear that the clinical trial design fdlows a stepwise approach that first considers the confirmatorystep by testing a prespecified, well-defined statistical hypothesis, and then moves to the exploratory (or learning) step. We discuss a few examples to illustratehow this thinking process can be applied in designing some of the phase 2/3 studies.
strong enough evidence to demonstrate that the test drug is significantly different from placebo, scientists would not reject the null hypothesis (that the test treatment is not
Data Loading...
