急性胰腺炎严重程度的预测模型构建与验证

Establishment and validation of prediction model for severity of acute pancreatitis

目的构建预测急性胰腺炎严重程度的模型并进行内部验证。方法选取2020年3月至2022年3月惠州市中心人民医院诊断为急性胰腺炎的患者为研究对象,将其分为中重症和重症急性胰腺炎(MSAP+SAP)组110例和轻症急性胰腺炎(MAP)组423例。比较两组患者的临床资料,采用二元logistic回归分析MSAP和SAP的独立预测因子并构建预测模型。采用Bootstrap法重复抽样1000次进行模型的内部验证。结果二元logistic回归分析发现,胆囊结石、白细胞计数、中性粒细胞与淋巴细胞比值(NLR)、血小板计数、红细胞分布宽度(RDW)、白蛋白和血肌酐为MSAP+SAP的独立预测因子。构建的预测模型AUC值为0.817(95%CI:0.776~0.857),敏感度为73.0%,特异度为79.1%。经Bootstrap法1000次内部校准,该模型具有较高的鉴别能力(AUC值为0.825)。结论基于胆囊结石、白细胞计数、NLR、血小板计数、RDW、白蛋白和血肌酐构建的预测模型具有较好的临床实用性,但仍需更多外部数据进一步验证。

Objective To construct a model for predicting the severity of acute pancreatitis and conduct internal validation.Methods Patients diagnosed with acute pancreatitis at Huizhou Central People′s Hospital from March 2020 to March 2022 were selected as the study subjects.They were divided into the moderately severe and severe acute pancreatitis(MSAP+SAP)group with 110 cases and the mild acute pancreatitis(MAP)group with 423 cases.Clinical data of the two groups were compared,and binary logistic regression analysis was used to identify independent predictors of MSAP and SAP to construct the prediction model.The model was internally validated using the Bootstrap method with 1000 repetitions of sampling.Results Binary logistic regression analysis revealed that gallstones,white blood cell count,neutrophil-to-lymphocyte ratio(NLR),platelet count,red cell distribution width(RDW),albumin,and blood creatinine were independent predictors of MSAP+SAP.The constructed prediction model had an AUC value of 0.817(95%CI:0.776-0.857),sensitivity of 73.0%,and specificity of 79.1%.After 1000 internal calibrations using the Bootstrap method,the model showed a high discriminatory ability with an AUC value of 0.825.Conclusion The prediction model based on gallstones,white blood cell count,NLR,platelet count,RDW,albumin,and blood creatinine has good clinical utility.However,further external validation with more data is required.