Construction and validation of a risk prediction model for ventilator-induced diaphragm dysfunction within 24 hours in patients with severe pneumonia of mechanical ventilation
Objective To construct and validate a risk prediction model for ventilator-induced diaphragm dysfunction(VIDD)within 24 hours in patients with severe pneumonia of mechanical ventilation.Methods A total of 261 patients with severe pneumonia who received mechanical ventilation in the Department of Critical Care Medicine,Ruikang Hospital Affiliated to Guangxi University of Chinese Medicine from January 2021 to March 2024 were selected as study object,and they were divided into training set(182 cases)and validation set(79 cases)in a 7∶3 ratio.According to whether patients had VIDD or not,the patients in the training set were divided into occurrence group and non-occurrence group.The basic data of patients were collected,the influencing factors of VIDD occurrence within 24 hours in patients with severe pneumonia of mechanical ventilation were analyzed,and the risk prediction model was constructed.Receiver operating characteristic curve was used to evaluate the diagnostic value of the model,Hosmer-Lemeshow test was used to evaluate the goodness of fit of the model,and decision curve analysis was used to evaluate the applicability of the model.Results VIDD occurred in 80 patients in the training set.There were significant differences in admission acute physiology and chronic health evaluation Ⅱ(APACHE Ⅱ)score,serum albumin,days of mechanical ventilation,gender,infection,positive end-expiratory pressure(PEEP),arterial partial pressure of oxygen before treatment,and early functional exercise between occurrence group and non-occurrence groups(P＜0.05).APACHE Ⅱ score(OR=1.22),PEEP(OR=2.13),and early functional exercise(OR=2.78)were the independent risk factors for VIDD within 24 hours in patients with severe pneumonia of mechanical ventilation(P＜0.05),and serum albumin(OR=0.92)was the protective factor(P＜0.05).The area under the curve of the training set was 0.76 to predict VIDD within 24 hours in patients with severe pneumonia of mechanical ventilation,and the verification was 0.72.The model of the training set and the validation set fit well.When the threshold probability of training set was 0.18-0.90,the clinical net benefit was higher;when the validation set was between 0.05-0.60,the clinical net benefit was higher.Conclusion Admission APACHE Ⅱ score,PEEP,early functional exercise,and serum albumin are influencing factors for VIDD within 24 hours in patients with severe pneumonia of mechanical ventilation.This model has good predictability and applicability in clinic.
Severe pneumoniaMechanical ventilationVentilator-induced diaphragm dysfunction
NETL
NSTL
万方数据
