Establishment and validation of a risk line chart model for sepsis complicated with acute lung injury
Aim To establish and validate an column chart model for the risk of sepsis complicated with acute lung injury(ALI)in sepsis.Methods A total of 257 patients with sepsis were selected as the modeling group,and 110 patients with sepsis during the same period were collected as the validation group in a 7∶3 ratio.The two groups were divided into an ALI group and a non-ALI group according to whether they had concurrent ALI.Logistic regression model was applied to analyze the influencing factors of ALI in sepsis patients,R software was applied to construct a column chart model for the risk of sepsis complicated with ALI,and validation was conducted.Results The incidence rate in the modeling group was 33.85％,while the incidence rate in the valida-tion group was 31.82％.The pulmonary infection(OR=16.505),procalcitonin(PCT,OR=2.640),tumor necrosis factor-α(TNF-α,OR=1.098),oxygenation index(OR=0.867),and APACHE Ⅱ score(OR=1.750)were the influencing factors of sepsis complicated with ALI(P＜0.05).Based on the above 5 indicators,a column chart prediction model was constructed.The AUC of the column charts for predicting the risk of ALI occurrence in the modeling group and validation group were 0.858 and 0.877,respec-tively.The H-L test showed good consistency,and the predicted probability of the calibration curve was close to the actual probabili-ty,indicating that the model has good accuracy in predicting the risk of ALI occurrence.Conclusion The influencing factors of sepsis complicated with ALI include APACHE Ⅱ score,pulmonary infection,PCT,TNF-α,and oxygenation index.Based on this,the constructed column chart model for predicting the risk of ALI has good predictive value and can provide reference for individualized prevention of ALI in sepsis patients.
万方数据
维普
