Total ascitic fluid leukocyte count for reliable exclusion of spontaneous bacterial peritonitis in patients with ascites

Background and aims The diagnosis of spontaneous bacterial peritonitis (SBP) in patients with ascites is established by definition with a polymorphonuclear (PMN) cell count in the ascitic fluid greater than 0.250 g/l determined via cytological (microscopic) examination. In this study, we correlated the automatically assessed total ascitic nucleated cell count with PMN and determined its predictive value for diagnosis of SBP. Methods Six hundred and eleven consecutive paracenteses of 179 patients with ascites of various aetiologies (liver cirrhosis, hepatocellular carcinoma, peritoneal carcinomatosis, and ascites of other aetiology) were studied retrospectively. Results The most reliable diagnostic cut-off level was determined for differentiation between SBP and non-SBP via receiver operating characteristics analysis. A total ascitic nucleated cell count less than 1.0 g/l is unlikely to represent SBP (negative predictive value, 95.5%). Conclusions If ascitic fluid samples with machine-made total ascitic nucleated cell count below 1.0 g/l are not followed by additional laboratory tests, the risk of missing the diagnosis of SBP is low. Applying these criteria we would have classified 51 samples of 611 samples (20 of 179 patients) wrongly using the cut-off value of 1 g/l. On the other hand we would have spared cytologic evaluation in about 63% of paracentesis performed in our hospital. Nevertheless, to insure patient safety, standard laboratory analysis is recommended in circumstances of clinical uncertainty. Thus, patients with first manifestation of ascites should always receive cytologic examination and full diagnostic investigation to exclude other causes of ascites.