|
Activity Number:
|
97
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2003 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #302251 |
|
Title:
|
Missing Values Strategies in Medical Device Clinical Trials
|
|
Author(s):
|
Sarah J. Kogut*+
|
|
Companies:
|
Medtronic Neurological
|
|
Address:
|
4200 7th St., NE, Minneapolis, MN, 55421,
|
|
Keywords:
|
therapeutic medical device ; intent-to-treat ; simple imputation ; ignorable ; sensitivity analysis ; clinical trials
|
|
Abstract:
|
It is often thought to be conservative to analyze patients in a medical device randomized clinical trial according to an "intent-to-treat" (ITT) strategy. In this analysis, a patient's data is analyzed according to the group to which they were randomized, no matter how their clinical course of treatment has progressed during the treatment phase of the trial. The FDA guideline encourages the use of ITT analysis. In medical device clinical trials, patients are often selected among those who have tried and failed the standard treatments for their condition. They may be especially ill or in weakened physical condition. It can be expected that some patients are not be able to be assessed on physical function by the end of the trial; and there may be some who have died during the course of the trial. This leads to the concern that missing data are not missing at random (ignorable). In this situation it is useful to perform sensitivity analyses based on simple imputation methods in addition to the primary ITT analysis. Some examples of sensitivity analyses for therapeutic medical device studies will be presented and their advantages and disadvantages will be discussed.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2003 program |
