PROGNOSIS OF INTRAVESICAL BACILLUS-CALMETTE-GUERIN THERAPY FOR SUPERFICIAL BLADDER-CANCER BY IMMUNOLOGICAL URINARY MEASUREMENTS - STATISTICALLY WEIGHTED SYNDROMES ANALYSIS

Purpose: The goal of this research was to discover new biological indi cators in urine which could be used for short-term prognosis of local Bacillus Calmette-Guerin (BCG) therapy outcome in patients with superf icial bladder cancer. Patients and Methods: We measured and statistica lly evaluated soluble immunological molecules in urine from bladder ca ncer patients (n = 34) receiving BCG intravesically. Urine was collect ed following each of 6 weekly treatments, processed and assayed. The d ata base included measurements of interleukin-1 (IL-1), IL-2, IL-4, IL -6, IL-8, IL-10, IL-12, soluble intercellular adhesion molecule-1 (sIC AM-1), tumour necrosis factor-alpha (TNF alpha), soluble CD14 (sCD14), interferon-gamma (IFN gamma), CM-CSF, volume of urine and its pH. The clinical response was evaluated by urine histology and random quadran t biopsy 3 months after the start of therapy. Patients were divided in to 2 groups, with good and poor therapeutic effect. The initial comple te response rate was 62% (21/34). The data base was analyzed using tra ditional multivariate statistical methods and a pattern recognition me thod which deals with combinatorial-statistical analysis (statisticall y weighted syndromes (SWS) method) of the gradated features. The SWS m ethod is capable of identifying robust patterns in small ''fuzzy'' set s with high dimensional objects and some missing values. Results: Only one parameter gave significant differences at p<0.05, GM-CSF at insti llation 6. Repeated measurement analysis of variance, backward stepwis e multiple logistic regression and linear discriminant analysis failed to show any significance. However, significant differences in the str ucture of correlation between features in the groups with and without therapeutic effect were observed and four highly informative variables (the masses of sICAM-1, TNF alpha, sCD14 and pH) relating to 5(th)-6( th) installations were selected by SWS. These features provided accura te individual prediction of therapeutic outcome for all our patients. Cross-validation analysis and computer simulation showed the statistic ally significant stability of the prediction. Conclusion: We have sele cted a set of urinary variables that could be considered as a perspect ive combination of indicators (syndromes) of outcome of pre-operation BCG therapy of patients with superficial bladder cancer. A larger pati ent database will provide testing and evaluation of the biological and clinical significance of selected features. The computational syndrom e-disease approach should be applicable for the solution of decision-m aking problems for management of cancer.