A clinical trial evaluates the safety and effectiveness of a new treatment intervention or compares the effectiveness of a new treatment to that of current best practice or other control group. Statistics contributions to clinical trials affect every man, woman, and child in some way, whether now or in the future, as this type of research determines most options available for physicians to treat a patient. Clinical trials are required for every type of drug to treat every type of disease. Now, this is an impressive arena in which to work!
A clinical trial is designed as a prospective study, which means it is thoroughly planned before any data are collected. This important, detailed design is developed in collaboration with a statistician.
A clinical trial is an effective tool in determining whether a new treatment intervention really does have the beneficial results that have been proposed. This is where a statistician's input is vital. Given the variability of human subjects and the uncertain knowledge of the course of most diseases, it would be extremely difficult or impossible to determine the effects of a specific treatment on the outcome of the disease course if a study without a clearly defined hypothesis and an appropriate design to test this hypothesis.
In many medical settings, three types of clinical trials are usually conducted. These are called Phase I, Phase II, and Phase III trials and are administered in sequence to learn more about a given treatment intervention. Several steps or phases of clinical research must occur before a large-scale Phase III study is implemented. A Phase IV trial is a post-approval study and can be a long-term follow-up of a treatment that was previously found to be effective, a post-marketing surveillance study, or a study to learn more about the treatment.
Phase I trials are the initial clinical trials in humans. The major objective of a Phase I trial is to evaluate the safety of a new treatment, including excess toxicity and side effects. The objective of a Phase II trial is to determine whether a specific treatment is effective enough to warrant further study, usually if the new treatment appears potentially better than the existing best treatment. Phase I and II trials are relatively small, involving approximately 20-50 patients, and usually all patients are given the new treatment intervention.
A Phase III trial is almost always a randomized trial (by chance alone assigning patients to a treatment group), comparing a new treatment to the current best treatment or other control group. Such a trial can be quite large, including 100 to several thousand patients, and could take place at several centers. Randomization is used to ensure that patients given the two treatments are as alike as possible (for example, in age and health), the only differences between them being the treatment they are given. The Phase III trial is much more definitive due to the larger number of patients, the randomization process, and the multiple centers participating.
Statistical thought is vital to any clinical trial. The biostatistician ensures the design of the study is appropriate for meeting the study objectives. The statistician also ensures a sufficient number of patients is included in the clinical trial to answer its primary objective, but not so many that patients might be subjected unnecessarily to an ineffective or unsafe treatment or that the study would be conducted over an unnecessarily long period of time. The statistician will describe in advance the statistical methods to be used to analyze the data, such as a binomial comparison of the proportion of responses, a t-test for comparisons of means of continuous data, or a survival analysis to compare differences in survival. When the study is completed, the statistician will analyze the data and write a report about the results.
Information about the results of clinical trials is commonly reported in the news media, including television, newspapers, and magazines. You may have seen advertisements for a specific type of person to participate in a clinical trial. What better way to have a direct effect on the health of the nation and the world than to be a statistician who designs and analyzes clinical trials?