Purpose Investigate the clinical characteristics of splenomegaly secondary to acute pancreatitis (SSAP) and construct a nomogram prediction model based on Lasso-Logistic regression. Methods A retrospective case-control study was conducted to analyze the laboratory parameters and computed tomography (CT) imaging of acute pancreatitis (AP) patients recruited at Xuanwu Hospital from December 2014 to December 2021. Lasso regression was used to identify risk factors, and a novel nomogram was developed. The performance of the nomogram in discrimination, calibration, and clinical usefulness was evaluated through internal validation. Results The prevalence of SSAP was 9.2% (88/950), with the first detection occurring 65(30, 125) days after AP onset. Compared with the control group, the SSAP group exhibited a higher frequency of persistent respiratory failure, persistent renal failure, infected pancreatic necrosis, and severe AP, along with an increased need for surgery and longer hospital stay (P < 0.05 for all). There were 185 and 79 patients in the training and internal validation cohorts, respectively. Variables screened by Lasso regression, including platelet count, white blood cell (WBC) count, local complications, and modified CT severity index (mCTSI), were incorporated into the Logistic model. Multivariate analysis showed that WBC count <= 9.71 x 10(9)/L, platelet count <= 140 x 10(9)/L, mCTSI >= 8, and the presence of local complications were independently associated with the occurrence of SSAP. The area under the receiver operating characteristic curve was 0.790. The Hosmer-Lemeshow test showed that the model had good fitness (P = 0.954). Additionally, the nomogram performed well in the internal validation cohorts. Conclusions SSAP is relatively common, and patients with this condition often have a worse clinical prognosis. Patients with low WBC and platelet counts, high mCTSI, and local complications in the early stages of the illness are at a higher risk for SSAP. A simple nomogram tool can be helpful for early prediction of SSAP.