Evaluation of a prognostic model for risk of relapse in stage I seminoma surveillance

A prognostic model for relapse risk in stage I seminoma managed by surveillance after orchiectomy has been developed but has not been independently validated. Individual data on 685 stage I seminoma surveillance patients managed between 1998 and 2005 at three cancer centers were retrospectively analyzed. Variables including age and pathology of the primary tumor: small vessel invasion, tumor size, and invasion of rete testis were analyzed. Specifically median tumor size and rete testis invasion was tested to evaluate the performance of the published model. Median follow-up was 3.85 years (0.1-10.29), 88 patients relapsed and 5-year relapse-free rate was 85%. In univariate analysis, median tumor size (< 3 cm vs. >= 3 cm) was associated with increased risk of relapse but rete testis invasion was not, nor was age and small vessel invasion. In multivariable analysis, tumor size above median (cutpoint of 3 cm) was a predictor for relapse, HR 1.87 (95% CI 1.15, 3.06), whereas rete testis invasion HR 1.36, (95% CI 0.81, 2.28) was not statistically significant. The 3-year relapse risk based on the primary tumor size alone increased from 9% for 1 cm primary tumor to 26% for 8 cm tumor. A clinically useful, highly discriminating prognostic model remains elusive in stage I seminoma surveillance as we were unable to validate the previously developed model. However, primary tumor size retained prognostic importance and a scale of relapse risk based on the unit increment of tumor size was developed to help guide patients and clinicians in decision making.