Evaluation of prostate cancer patients receiving multiple staging tests, including ProstaScint (R) scintiscans

BACKGROUND. Multiple serum tests were performed on archival samples from pa tients who participated in trials to assess the ProstaScint((R)) scan stagi ng ability. Traditional statistical analysis as well as artificial neural n etwork (ANN) analysis were employed to evaluate individual patients and the group as a whole. The results were evaluated so that each factor was teste d for prognostic value. METHODS. Data obtained from serum tests, bone scans, and ProstaScint((R)) s cans were evaluated by traditional statistical methods and ANN to determine the individual value in clinical staging of prostate cancer. RESULTS. Two hundred seventy-five patients (180 postprostatectomy, 95 intac t prostate) with prostate cancer (14 with distant metastases) were availabl e for analysis. Data available included: clinical state (remission or progr ession), most recent clinical TNM stage, bone scan, and ProstaScint((R)) sc an. Serum was tested for prostate-specific membrane antigen(PSMA), prostate -specific antigen(PSA), free PSA (fPSA), and complexed PSA (cPSA). Addition al calculations included percent free PSA, and percent complexed PSA. Spear man individual statistical assessment for traditional group evaluation reve aled no significant factors for T-stage. The free PSA and complex PSA had a significant association with node N-status. The distant metastases (M) sta ge correlated well with the bone scan and clinical stage. ANN analysis reve aled no significant T-stage factors. N-stage factors showed a 95% sensitivi ty and 49% specificity. These factors included the presence or absence of a prostate, PSA serum levels, bone scan, and ProstaScint((R)) scans as major associated indicators. ANN analysis of the important variables for M-stage included ProstaScint" scan score, and PSA levels (total, percent complexed , percent free, and fPSA). These factors were associated with a 95% sensiti vity and 15% specificity level. CONCLUSIONS. Two hundred seventy-five patients receiving treatment for pros tate cancer were evaluated by ANN and traditional statistical analysis for factors related to stage of disease. ANN revealed that PSA levels, determin ed by a variety of ways, ProstaScint((R)) scan, and bone scan, were signifi cant variables that had prognostic value in determining the likelihood of n odal disease, or distant disease in prostate cancer patients. (C) 2000 Wile y-Liss, Inc.