Abstract
W p p 3 m t d a e s d n this issue of The Annals of Thoracic Surgery, Dr Brevig and colleagues [1] describe their program to reduce lood transfusions in cardiac surgery. Their analysis of he changes in operative mortality during this process ses the risk-adjusted cumulative sum (CUSUM) of oberved minus expected deaths. We previously discussed his method [2], but the “bullet-shaped” prediction limits hat we used, which give rise to an expanding interval ver time, raised some concern. Recently a statistically ophisticated cardiac surgeon asked, “Why do these ntervals get wider, rather than narrower, as the number
Full Text
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call