Atrial fibrillation (AF) is a rapid and unorganized beating of the upper chambers of the heart. It is generally not life-threatening in the short term, but it dramatically impacts how a patient feels, and it can have bad consequences in the long term. One of those “bad consequences” is stroke, caused by blood clots that can form in the atria when they are “fibrillating” for long periods of time, and the clots subsequently flow to the brain. We are now planning a study to see whether a new therapy (perhaps cryoablation plus a new drug) is better than a control therapy (perhaps cryotherapy plus an old drug) at preventing stroke or death. Our primary endpoint will be a composite of stroke or all-cause mortality, and we will structure this as a time-to-event analysis. We think the new therapy will lead to a reduction in risk of 40% (that is, a hazard ratio of 0.60). How many events must we observe (combined across both therapy groups) in order to have 95% power to detect a reduction of this magnitude? (You may assume alpha = 0.05 and a 1:1 allocation ratio.) At the end of 5 years of follow-up we expect that 20% of our patient population (combined across treatment groups) will have died or had a stroke. How many subjects should we plan to enroll?

Human Anatomy & Physiology (11th Edition)

11th Edition

ISBN:9780134580999

Author:Elaine N. Marieb, Katja N. Hoehn

Publisher:Elaine N. Marieb, Katja N. Hoehn

Chapter1: The Human Body: An Orientation

Section: Chapter Questions

Problem 1RQ: The correct sequence of levels forming the structural hierarchy is A. (a) organ, organ system,...

See similar textbooks

Related questions

Question

Atrial fibrillation (AF) is a rapid and unorganized beating of the upper chambers of the heart. It is generally not life-threatening in the short term, but it dramatically impacts how a patient feels, and it can have bad consequences in the long term. One of those “bad consequences” is stroke, caused by blood clots that can form in the atria when they are “fibrillating” for long periods of time, and the clots subsequently flow to the brain. We are now planning a study to see whether a new therapy (perhaps cryoablation plus a new drug) is better than a control therapy (perhaps cryotherapy plus an old drug) at preventing stroke or death. Our primary endpoint will be a composite of stroke or all-cause mortality, and we will structure this as a time-to-event analysis.

We think the new therapy will lead to a reduction in risk of 40% (that is, a hazard ratio of 0.60). How many events must we observe (combined across both therapy groups) in order to have 95% power to detect a reduction of this magnitude? (You may assume alpha = 0.05 and a 1:1 allocation ratio.)
At the end of 5 years of follow-up we expect that 20% of our patient population (combined across treatment groups) will have died or had a stroke. How many subjects should we plan to enroll?

Expert Solution

Trending now

This is a popular solution!

Step by step

Solved in 2 steps

SEE SOLUTION Check out a sample Q&A here

Knowledge Booster

Learn more about

Need a deep-dive on the concept behind this application? Look no further. Learn more about this topic, biology and related others by exploring similar questions and additional content below.

Similar questions