Infection and Drug Resistance (Apr 2023)
Development of a Nomogram for Predicting Mortality Risk in Sepsis Patients During Hospitalization: A Retrospective Study
Abstract
Bin Lu,1 Xinling Pan,2 Bin Wang,3 Chenyuan Jin,1 Chenxin Liu,1 Mengqi Wang,4 Yunzhen Shi1 1Department of Infectious Diseases, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, Zhejiang Province, People’s Republic of China; 2Department of Biomedical Sciences Laboratory, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, People’s Republic of China; 3Department of Emergency, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, Zhejiang Province, People’s Republic of China; 4Department of Neurology, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, Zhejiang Province, People’s Republic of ChinaCorrespondence: Yunzhen Shi, Department of Infectious Diseases, Affiliated Dongyang Hospital of Wenzhou Medical University, No. 60 Wuningxi Road, Dongyang, People’s Republic of China, Email [email protected]: We attempted to establish a model for predicting the mortality risk of sepsis patients during hospitalization.Patients and Methods: Data on patients with sepsis were collected from a clinical record mining database, who were hospitalized at the Affiliated Dongyang Hospital of Wenzhou Medical University between January 2013 and August 2022. These included patients were divided into modeling and validation groups. In the modeling group, the independent risk factors of death during hospitalization were determined using univariate and multi-variate regression analyses. After stepwise regression analysis (both directions), a nomogram was drawn. The discrimination ability of the model was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, and the GiViTI calibration chart assessed the model calibration. The Decline Curve Analysis (DCA) was performed to evaluate the clinical effectiveness of the prediction model. Among the validation group, the logistic regression model was compared to the models established by the SOFA scoring system, random forest method, and stacking method.Results: A total of 1740 subjects were included in this study, 1218 in the modeling population and 522 in the validation population. The results revealed that serum cholinesterase, total bilirubin, respiratory failure, lactic acid, creatinine, and pro-brain natriuretic peptide were the independent risk factors of death. The AUC values in the modeling group and validation group were 0.847 and 0.826. The P values of calibration charts in the two population sets were 0.838 and 0.771. The DCA curves were above the two extreme curves. Moreover, the AUC values of the models established by the SOFA scoring system, random forest method, and stacking method in the validation group were 0.777, 0.827, and 0.832, respectively.Conclusion: The nomogram model established by combining multiple risk factors could effectively predict the mortality risk of sepsis patients during hospitalization.Keywords: severe sepsis, mortality risk prediction, nomogram, SOFA, random forest, stacking
