Papillary renal cell carcinoma (PRCC) is a histologically, radiologically, and cytogenetically distinctive variant of renal cell carcinoma (RCC). Some investigators have shown that PRCC has a more favorable clinical outcome when compared to conventional RCC, but others have reported data to the contrary. In the light of these conflicting data, we analyzed 28 PRCC, defined as tumors histologically composed of papillary structures comprising at least 50% of sampled tumor, and correlated the patients' outcome with Fuhrman's nuclear grade, pathologic stage, and proliferative activity assessed by immunohistochemistry using PCNA (clone PC10; DAK0, Carpinteria, CA, U.S.A.) and Ki-67 (clone MIB-1; AMAC Inc., Westbrook, ME, U.S.A.) on formalin-fixed paraffin-embedded tissue. An immunohistochemically derived tumor proliferation index (TPI) was obtained by visual quantitative evaluation of 500 neoplastic cells by each of two independent observers; the average value was expressed as percentage of positively staining tumor nuclei. Clinical follow-up was available in all patients with a mean follow-up of 36.4 months. Based on Cox proportional regresssion, stage was the most significant independent predictor of survival (p = 0.001, hazard ratio = 45.51). At 1-75 months following surgery, all patients with Stage I-II tumors had no evidence of disease (mean, 38.4 months) and four of five with Stage III-IV were dead of disease (mean, 15.5 months). chi(2) analysis showed that Fuhrman's nuclear grade did not correlate with stage (p = 0.39) or outcome (p = 0.63). Although PCNA and MIB-1 TPI weakly correlated with each other (Spearman rank analysis, r = 0.39, p = 0.07), PCNA and MIB-1 TPI did not correlate with either nuclear grade (p = 0.11 and p = 0.69) or pathologic stage (p = 0.37 and p = 0.38, Kruskal-Wallis). PCNA TPI was also found to be another statistically significant independent prognostic variable, but its contribution was of negligible magnitude (p = 0.003, hazard ratio = 0.95). Based on our experience with PRCC, we conclude that (a) neither the morphologic nuclear grade nor the proliferative activity assessed by immunohistochemistry are useful in predicting the outcome in PRCC, (b) like conventional RCC, stage of the tumor is the most significant independent predictor of survival, and therefore (c) the validity of PRCC as a prognostically significant histologic subtype is in question.
