You may want to read this article first: What is a Primary Endpoint?
What is a Composite Endpoint?A composite endpoint is an endpoint that is a combination of multiple clinical endpoints. Composite endpoints can be primary or secondary:
- Primary composite endpoints are the main measurements for a trial; They answer the most important questions in the trial. For example, if the endpoint of a study is “cure”, then a composite endpoint might be cure or remission.
- Secondary composite endpoints are the secondary objectives in the trial. For example, a drug designed to cure/put into remission a disease might also have measures of whether chronic pain and quality of life are improved.
Benefits and Risks
The benefits of composite endpoints are:
- Increased statistical efficiency and precision.
- Smaller trials (which also means lower costs).
- Faster trial completion (as you are not hanging around waiting for a significant number of rare events).
The major risk to studies with composite endpoints is bias. Studies with composite endpoints should be analyzed carefully to avoid bias because of competing risks between endpoints. For example, a study on a particular stroke medication with endpoints of death or hospitalization may see a reduction in hospitalization only because of an increase in mortality. For this reason, death should always be included in a trial that studies non-fatal events (Skali et. al).
When to Use Composite Endpoints
When a study has a fairly rare endpoint, it’s common to use a composite endpoint instead. Rare events may require a very large, expensive trial in order to get statistically significant results. Let’s say a study is investigating a new drug for anaphylaxis (a severe allergic reaction which can lead to death). If “death” is the endpoint, a trial could need about a million people to record one death(1). A composite primary endpoint might be “any non-fatal or fatal allergic reaction” — which would require much smaller numbers (thousands, or possibly hundreds).
Composite endpoints should only be used when each endpoint in the composite is meaningful, both to the trial purpose and to the patient. Each endpoint should be analyzed separately to gauge if the clinical trial has meaningful results for all members of the composite, or just some (ICOH, CPMP). For example, glycoprotein IIb/IIIa inhibitors show a statistically significant reduction for the composite endpoints of death, myocardial infarction, or refractory angina. However, death — the most important endpoint — showed no change (Freemantle et. al).
American Academy of Allergy, Asthma and Immunology. Dying from Allergies: Fatal Anaphylaxis in the United States. Retrieved March 2, 2017 from: https://www.aaaai.org/global/latest-research-summaries/Current-JACI-Research/fatal-anaphylaxis
Committee For Proprietary Medicinal Products (CPMP), “Points to Consider on Multiplicity Issues in Clinical Trials.” Retrieved June 10, 2017 from:
N. Freemantle, M. Calvert, J. Wood, J. Eastaugh, C. Griffin, “Composite Outcomes in Randomized Trials. Greater Precision but with Greater Uncertainty?” Journal of the American Medical Association, 289, 2554–2559 (2003).
International Conference on Harmonization (ICOH), Guideline E9, “Statistical Principles for Clinical Trials.” Retrieved June 10, 2017 from: http://www.ich.org/fileadmin/Public_Web_Site/ICH_Products/Guidelines/Efficacy/E9/Step4/E9_Guideline.pdf
H. Skali, S.D. Solomon, M.A. Pfeffer, “Are We Asking Too Much of Our Trials?” American Heart Journal 143, 1–3 (2002).------------------------------------------------------------------------------
Need help with a homework or test question? With Chegg Study, you can get step-by-step solutions to your questions from an expert in the field. If you'd rather get 1:1 study help, Chegg Tutors offers 30 minutes of free tutoring to new users, so you can try them out before committing to a subscription.
If you prefer an online interactive environment to learn R and statistics, this free R Tutorial by Datacamp is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try this Statistics with R track.
Comments? Need to post a correction? Please post a comment on our Facebook page.