To illustrate the importance of adjusting the estimates of cumulative incid
ence of acquired immunodeficiency syndrome (AIDS) related illnesses for com
peting risk of other causes of death, we compared unadjusted and adjusted (
for competing events) incidence estimates for four AIDS illnesses: pneumocy
stis cavinii pneumonia (PCP), mycobacterium avium complex (MAC), cytomegalo
virus (CMV), and esophageal candidiases. The study population was patients
followed by the Johns Hopkins Hospital AIDS Service between 1989 to 1995. R
atios of 4 year unadjusted incidence estimates to 4 year adjusted incidence
estimates for the four diseases ranged from 1.38 to 1.86, corresponding to
cumulative death rates of 61% to 69%. For CMV, the ratios of 4 year unadju
sted to adjusted incidence estimates for five groups of patients ranged fro
m 1.5 to 2.33, corresponding to cumulative death rates of 48% to 78%. We co
nclude that ignoring the competing risk of death can result in substantial
overestimation of disease occurrence, which may give misleading results in
estimating and comparing the occurrence of a disease of interest. (C) 2000
Elsevier Science Inc. All rights reserved.