Recently, men with intermediate-risk prostate cancer (PC) were classified into favorable and unfavorable categories; however, whether the risk of PC-specific mortality (PCSM) among men with high-risk PC versus unfavorable intermediate-risk PC is increased is unknown. In a prospective, randomized trial conducted between 1995 and 2001, 206 men with intermediate-risk or high-risk PC were randomized to receive 70 Gy with or without 6 months of androgen-suppression therapy (AST). The subgroup of 197 patients with information available on the percentage of positive biopsies formed the cohort. Fine and Gray regression analysis was used to assess whether men with high-risk PC versus unfavorable intermediate-risk PC had an increased risk of PCSM. After a median follow-up of 14.3 years, there were 127 deaths (64.5%), including 22 deaths (17.3%) from PC. There were no PC deaths in the favorable intermediate-risk group. There was an increase in the risk of PCSM among men with high-risk PC versus unfavorable intermediate-risk PC, but the difference was not significant (adjusted hazard ratio, 1.59; 95% confidence interval, 0.66-3.83; P = .30) after adjusting for age, randomized treatment arm, and comorbidity. The lack of PC deaths among men with favorable intermediate-risk PC suggests that adding AST may not reduce their risk of PCSM; whereas many men with unfavorable intermediate-risk PC are at risk for harboring occult PC with Gleason scores from 8 to 10 and, if proven, would benefit from long-term AST. Multiparametric magnetic resonance imaging and targeted biopsy of suspicious lesions should be considered to identify PC with Gleason scores from 8 to 10 in these men. © 2014 American Cancer Society.