Background Patients with acute pancreatitis often present to the emergency department (ED) and usually require hospital admission. The aim of this study was to determine predictors of prolonged hospital stays in patients with mild forms of acute pancreatitis. Methods This retrospective cohort study was conducted in patients diagnosed in the ED with mild and moderate acute pancreatitis according to the revised Atlanta classification. Patients with available data between 2007 and 2017 were included and were divided based on their admission duration. Eight days or more was considered a long hospitalization. A multivariate logistic regression model was constructed to determine the independent predictors of prolonged hospital stays. Results Of the 485 evaluated patients, 335 were included in the analysis. Baseline characteristics, determined by vital signs and laboratory parameters, were similar between the short and long hospitalization groups. However, the long hospitalization group received more intravenous crystalloid in the ED, and this group used more diuretics and more angiotensin-converting enzyme inhibitor and angiotensin-receptor blocker (ACEI/ARB) drugs than the other group. Diuretic use was present in 8 patients (4.8%) in the short hospital length of stay group and in 26 patients (15.3%) in the long hospital length of stay group. Age, gender, ACEI/ARB use, diuretic use, total amount of intravenous crystalloid administered in the ED, aPTT, BUN, creatinine, and presence of biliary pathology were included in the multivariate analysis. Regarding the final analysis, diuretic use was an independent predictor of prolonged hospitalization (odds ratio 2.89, 95% confidence interval 1.05-8.00, p = 0.041). Conclusion Diuretic use is an independent predictor of long hospitalization in patients with mild and moderate pancreatitis. Drugs affecting total volume balance may prolong hospital stays in these patients.