基于SII构建及评价预测ARDS住院死亡率的在线临床风险模型  

Construction and evaluation of an online clinical risk model for predicting in-hospital mortality in patients with ARDS based on SII

作　　者：孙丽娜 白红艳 牛宗格 张福帅 曲仪庆[1] SUN Lina;BAI Hongyan;NIU Zongge;ZHANG Fushuai;QU Yiqing(Department of Pulmonary and Critical Care Medicine,Qilu Hospital of Shandong University,Jinan 250012,Shandong,China)

机构地区：[1]山东大学齐鲁医院呼吸与危重症医学科,山东济南250012

出　　处：《山东大学学报（医学版）》2024年第7期10-20,共11页Journal of Shandong University:Health Sciences

基　　金：国家自然科学基金重大项目(72293582);山东大学临床医学研究中心ECCM项目(2021SDUCRCB001)。

摘　　要：目的基于全身免疫炎症指数(systemic immune inflammation index,SII)探讨影响急性呼吸窘迫综合征(acute respiratory distress syndrome,ARDS)患者住院死亡率的危险因素,并建立预后预测模型。方法选取山东大学齐鲁医院2022年12月至2023年9月符合ARDS诊断标准的219例患者的资料,按3∶1的比例随机分为训练组(165例)和验证组(54例)。采用受试者工作特征(receiver operating characteristic,ROC)曲线探究SII对ARDS患者住院死亡率的预测价值,利用多因素Logistic回归分析得出的独立危险因素绘制预测ARDS患者住院死亡率的列线图,通过ROC曲线下面积(area under curve,AUC)、校准曲线、决策曲线分析(decision curve analysis,DCA)评估列线图的预测效能。结果相对于血小板与淋巴细胞的比值(platelet-to-lymphocyte ratio,PLR)、单核细胞与淋巴细胞的比值(monocyte-to-lymphocyte ratio,MLR)、C反应蛋白与白蛋白的比值(C-reactive protein-to-albumin ratio,CAR)、乳酸脱氢酶与白蛋白的比值(lactate dehydrogenase-to-albumin ratio,LAR)等其他新型炎症指标,SII曲线下面积最大(AUC=0.79),最佳截断值为3096.60×10^(9)/L,其灵敏度和特异度分别为73.70%和76.40%;多因素Logistic回归分析发现,SII、年龄、C反应蛋白(C-reactive protein,CRP)、慢性肝脏疾病和慢性肾脏疾病是影响ARDS患者住院死亡率的独立危险因素(P均<0.05)。列线图模型在训练组和验证组的AUC分别为0.876、0.848,校准曲线、DCA证实,该模型临床预测效果良好。结论入院时高SII水平与ARDS患者住院死亡风险增加相关,基于SII构建在线列线图可早期预测ARDS患者的住院死亡率,具有较高的区分度、准确性及临床实用性。Objective To explore the risk factors of in-hospital mortality in patients with acute respiratory distress syndrome(ARDS)based on systemic immune inflammation index(SII),and to develop a prognostic prediction model.Methods The data of 219 patients who met the diagnostic criteria of ARDS in Qilu Hospital of Shandong University from December 2022 to September 2023 were collected and randomly divided into a training group(n=165)and a verification group(n=54)in a ratio of 3∶1.The receiver operating characteristic(ROC)curve was used to explore the predictive value of SII for in-hospital mortality in patients with ARDS.A nomogram model predicting the risk of in-hospital death in patients with ARDS using independent risk factors derived from multifactorial Logistic regression analysis was constructed.The prediction efficiency of the nomogram was evaluated by ROC area under the curve(AUC),calibration curve and decision curve analysis(DCA).Results Compared with novel inflammatory indexes such as platelet-to-lymphocyte ratio(PLR),monocyte-to-lymphocyte ratio(MLR),C-reactive protein-to-albumin ratio(CAR)and lactate dehydrogenase-to-albumin ratio(LAR),the AUC of SII was the most prominent(AUC=0.79).When the optimal cutoff value was 3096.60×10^(9)/L,the sensitivity and specificity of SII in predicting in-hospital mortality in patients with ARDS were 73.70%and 76.40%,respectively.Multivariate Logistic regression analysis showed that SII,age,CRP,chronic liver disease and chronic kidney disease were independent risk factors for in-hospital mortality in patients with ARDS(all P<0.05).The AUC of the nomogram model in the training group and the verification group were 0.876 and 0.848,respectively.The calibration curve and DCA confirmed that the model exhibited a satisfactory degree of clinical predictive efficacy.Conclusion The high levels of SII on admission are associated with increased risk of in-hospital death in patients with ARDS.The online nomogram constructed based on SII can early predict the in-hospital mortality of pa

关 键 词：急性呼吸窘迫综合征 全身免疫炎症指数 列线图 住院死亡率 预测模型 

分 类 号：R563.9[医药卫生—呼吸系统]