Improved sensitivity of fuzzy logic based tumor marker profiles for diagnosis of pancreatic carcinoma versus benign pancreatic disease

Background. The definite diagnosis of pancreatic tumors of unknown origin r emains a clinical challenge. Imaging techniques may fail to differentiate m alignant tumors from inflammation, especially in chronic pancreatitis. In c onsiderable number of cases the definitive diagnosis needs laparotomy. Sing le tumor markers as CA 19-9 or CEA are of limited value in these cases beca use of their limited sensitivity and specificity. This study was performed to find out whether a classification method based on fuzzy logic analysis o f tumor marker profiles is feasible in patients with pancreatic carcinoma a nd benign pancreatic disease. Patients and Methods. Tumor markers and other clinical and laboratory parameters of 74 consecutive patients, either with histologically proved pancreatic carcinoma (n = 43) or presented benign pa ncreatic disease (n = 31) assessed by ultrasound endoscopic retrograde panc reatography, ol computed tomography were analysed in order to detect their diagnostic value in the multi-dimensional approach of fuzzy logic analysis. Results. Given a specificity of 95%, sensitivity was consider ably increas ed by the fuzzy logic method (83%) compared with the best single tumor mark er CA 19-9 (65%). CA 19-9, CYFRA 21-1 and CA 15-3 gave the most consider ab le contributions to the classification system, whereas CEA, CA 125, CA 72-4 , RFP, liver enzymes, lipase, amylase, bilirubin, and ferritin were of no o r little value. Conclusions. Tumor marker profiles analysed with the fuzzy logic method may have an improved sensitivity compared with single standard tumor markets. The diagnostic efficacy should be proved in patients with p ancreatic tumors of unknown origin.