MIXED-EFFECTS REGRESSION-MODELS FOR STUDYING THE NATURAL-HISTORY OF PROSTATE DISEASE

Although prostate cancer and benign prostatic hyperplasia are major he alth problems in U.S. men, little is known about the early stages of t he natural history of prostate disease. A molecular biomarker called p rostate specific antigen (PSA), together with a unique longitudinal ba nk of frozen serum, now allows a historic prospective study of changes in PSA levels for decades prior to the diagnosis of prostate disease. Linear mixed-effects regression models were used to test whether rate s of change in PSA were different in men with and without prostate dis ease. In addition, since the prostate cancer cases developed their tum ours at different (and unknown) times during their periods of follow-u p, a piece-wise non-linear mixed-effects regression model was used to estimate the time when rapid increases in PSA were first observable be yond the background level of PSA change. These methods have a wide ran ge of applications in biomedical research utilizing repeated measures data such as pharmacokinetic studies, crossover trials, growth and dev elopment studies, aging studies, and disease detection.