Construction and evaluation of an online clinical risk model for predicting in-hospital mortality in patients with ARDS based on SII
Objective To explore the risk factors of in-hospital mortality in patients with acute respiratory distress syn-drome(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 veri-fication 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-hos-pital 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),cali-bration curve and decision curve analysis(DCA).Results Compared with novel inflammatory indexes such as plate-let-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 3 096.60×109/L,the sensitivity and specificity of SII in predicting in-hospital mortality in pa-tients 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 pa-tients 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 patients with ARDS,with high differentiation,accuracy and clinical practicability.
Acute respiratory distress syndromeSystemic immune inflammation indexNomogramIn-hospital mortalityPrediction model
NETL
NSTL
万方数据
