JAMA Network
Rebecca T. Emeny, PhD, MPH; Chiang-Hua Chang, PhD; Jonathan Skinner, PhD; A. James O’Malley, PhD; Jeremy Smith, MPH; Gouri Chakraborti, MA;Clifford J. Rosen, MD; Nancy E. Morden, MD, MPH
Choosing between competing treatment options is difficult for patients and clinicians when results from randomized and observational studies are discordant. Observational real-world studies yield more generalizable evidence for decision making than randomized clinical trials, but unmeasured confounding, especially in time-to-event analyses, can limit validity.