Objective: To compare the values of BISAP, APACHE II, and Ranson’s scoring system for estimating the severity and prognosis of patients with early stage acute pancreatitis (AP). Methods: The clinical records of AP patients admitted between January 2009 and March 2014 were retrospectively analyzed. According to the first scores yielded by BISAP, APACHE II and Ranson’s score system at the time after admission, comparison was made of the area under the curve (AUC) of the receiver operating characteristic (ROC) curve of each scoring system for estimating the organ failure, pancreatic necrosis and death in AP patients as well as their sensitivity and specificity. Results: One hundred and thirty-five patients were finally enrolled according to the inclusion and exclusion criteria. Of the patients, 24 cases (17.7%) were diagnosed as severe acute pancreatitis (SAP), which included 19 cases diagnosed with organ failure, of which death occurred in 5 cases, and 20 cases were diagnosed having pancreatic necrosis. Of the BISAP, APACHE II, and Ranson’s scoring system, the AUC for organ failure estimation was 0.773, 0.821 and 0.897 (P<0.001), with sensitivity of 0.880, 0.872 and 0.740, and specificity of 0.530, 0.642 and 0.982, respectively; the AUC for pancreatic necrosis estimation was 0.819, 0.785 and 0.825 (P>0.05), with sensitivity of 0.715, 0.844 and 0.833, and specificity of 0.885, 0.630 and 0.672, respectively; the AUC for death estimation was 0.773, 0.786 and 0.889 (P>0.05), with sensitivity of 0.740, 0.843 and 0.865, and specificity of 0.830, 0.752 and 0.886, respectively. Conclusion: For AP patients, the three scoring systems have similar value in predicting pancreatic necrosis and death, and BISAP score is inferior to Ranson’s and APACHE II score in predicting organ failure, but it has the advantages of simple scoring, rapid assessment and dynamic monitoring, and is convenient to use in clinical practice.