ABSTRACT
BACKGROUND: Pancreatic cyst fluid analysis plays an important role in distinguishing between mucinous and non-mucinous cyst lesions. We aimed to compare the diagnostic performances of cyst fluid carcinoembryonic antigen (CEA), CA 19-9, and glucose in differentiating mucinous from non-mucinous neoplastic pancreatic cystic lesions (PCLs) and determine the best cut-off levels. METHODS: Patients' data were evaluated retrospectively. 102 patients' PCLs were grouped as non-neoplastic (n = 25), non-mucinous neoplastic (n = 20), mucinous neoplastic (n = 47) and pancreatic adenocarcinomas with cystic degeneration (n = 10); and CEA, CA 19-9, and glucose levels were compared. Receiver-operating characteristic analysis was performed, and the ideal cut-off values were determined. RESULTS: Cyst fluid CEA and CA 19-9, levels were significantly higher (P < 0.001, P < 0.001, respectively) and glucose levels were significantly lower (P = 0.001) in mucinous than in non-mucinous neoplastic PCLs. Area under curve with 95% confidence interval of CEA, glucose and CEA and glucose test combination was 0.939 (95% CI = 0.885-0.993, P = 0.001), 0.809 (95% CI = 0.695-0.924, P < 0.001) and 0.937 (95% CI = 0.879-0.995), respectively. CEA cut-offs to rule-in and rule-out mucinous neoplastic were 135.1 ng/mL (sensitivity = 62%, specificity = 94.7%) and 6.12 ng/mL (sensitivity = 94.1%, specificity = 80.4%), respectively. Glucose cut-off of 2.8 mmol/L was chosen both to rule-in and rule-out mucinous neoplastic PCLs (sensitivity = 78%, specificity = 80%). Co-analysis of CEA and glucose to distinguish mucinous from non-mucinous neoplastic PCLs had sensitivity = 87.8%, specificity = 93.3%, and diagnostic accuracy = 89.3%. CONCLUSIONS: We concluded that co-analysis of cyst fluid CEA (cut-off = 135.1 ng/mL) and glucose (cut-off = 2.8 mmol/L) at novel cut-offs had the best testing performance to rule-in mucinous neoplastic PCLs. To rule-out mucinous PCLs co-analysis of CEA (cut-off = 6.12 ng/mL) and glucose (cut-off = 2.8 mmol/L) added value to prediction.