External validation of risk classification in patients with docetaxel-treated castration-resistant prostate cancer

Background: Castration-resistant prostate cancer (CRPC) patients have poor prognoses, and docetaxel (DTX) is among the few treatment options. An accurate risk classification to identify CRPC patient groups for which DTX would be effective is urgently warranted. The Armstrong risk classification (ARC), which classifies CRPC patients into 3 groups, is superior; however, its usefulness remains unclear, and further external validation is required before clinical use. This study aimed to examine the clinical significance of the ARC through external validation in DTX-treated Japanese CRPC patients. Methods: CRPC patients who received 2 or more DTX cycles were selected for this study. Patients were classified into good-, intermediate-, and poor-risk groups according to the ARC. Prostate-specific antigen (PSA) responses and overall survival (OS) were calculated and compared between the risk groups. A multivariate analysis was performed to clarify the relationship between the ARC and major patient characteristics. Results: Seventy-eight CRPC patients met the inclusion criteria. Median PSA levels at DTX initiation was 20 ng/mL. Good-, intermediate-, and poor-risk groups comprised 51 (65%), 17 (22%), and 10 (13%) patients, respectively. PSA response rates >= 30% and >= 50% were 33%, 41%, and 30%, and 18%, 41%, and 20% in the good-, intermediate-, and poor-risk groups, respectivcixely, with no significant differences (p = 0.133 and 0.797, respectively). The median OS in the good-, intermediate-, and poor-risk groups were statistically significant (p < 0.001) at 30.1, 14.2, and 5.7 months, respectively. A multivariate analysis revealed that the ARC and PSA doubling time were independent prognostic factors. Conclusions: Most of CRPC patients were classified into good-risk group according to the ARC and the ARC could predict prognosis in DTX-treated CRPC patients.