基于Stacking的脓毒症患者死亡风险预测模型  

Prediction Model of Mortality Risk of Sepsis Patients Based on Stacking Algorithm

作　　者：李文锦 Wenjin Li(School of Health Science and Engineering,University of Shanghai for Science and Technology,Shanghai)

机构地区：[1]上海理工大学健康科学与工程学院,上海

出　　处：《建模与仿真》2025年第3期261-269,共9页Modeling and Simulation

摘　　要：脓毒症是由感染反应失调引起的危及生命的器官功能障碍,早期识别和预测高风险群体是降低患者死亡风险的关键。本研究采用多指标评估基础分类器的可信度得分,并引入贝叶斯优化算法构建脓毒症患者死亡风险预测模型。通过AUC、准确率、召回率、精确度和F1分数等指标全面评估模型的预测效果和性能,并使用特征重要性分析对模型预测结果进行可解释性分析,以提高辅助临床决策的及时性和准确性。结果表明,构建的Stacking模型在AUC、准确率、精确率等多个评估指标上表现优异,性能表现较优。特征重要性分析表明APACHE III评分、WBC等是影响脓毒症患者死亡风险的重要因素。本研究构建的Stack-ing脓毒症患者死亡风险预测模型具有较高的预测准确性,能够有效辅助医务人员对患者进行死亡风险评估,从而及时采取干预措施,改善患者预后。Sepsis is a life-threatening organ dysfunction caused by the imbalance of infection response.Early identification and prediction of high-risk groups is the key to reduce the risk of death of patients.In this study,multiple indicators were used to evaluate the reliability score of the basic classifier,and Bayesian optimization algorithm was introduced to construct the death risk prediction model of sepsis patients.The prediction effect and performance of the model are comprehensively evaluated by AUC,accuracy,recall,accuracy and F1 score,and the predictive results of the model are interpret-able by using feature importance analysis,so as to improve the timeliness and accuracy of assisting clinical decision-making.The results show that the Stacking model has excellent performance in AUC,accuracy,precision and other evaluation indexes.Characteristic importance analysis showed that APACHE III score was an important factor affecting the death risk of sepsis patients.The mor-tality risk prediction model of Stacking sepsis patients constructed in this study has high prediction accuracy,and can effectively assist medical staff to evaluate the mortality risk of patients,so as to take timely intervention measures and improve the prognosis of patients.

关 键 词：贝叶斯优化 堆叠算法 评估函数 脓毒症 死亡风险 

分 类 号：R459.7[医药卫生—急诊医学]