Risk factors analysis and prediction model construction of Mycoplasma pneumoniae pneumonia in adults
Objective To analyze the risk factors of Mycoplasma pneumoniae pneumonia(MPP)in adults,and to construct a predictive model for its occurrence.Methods Patients with Community-Acquired Pneumonia(CAP)admitted to the Department of Respiratory and Critical Care Medicine of Lu'an People's Hospital from Janu-ary to December 2023 were selected strictly according to the inclusion and exclusion criteria,and the clinical data of the patients were analyzed.All subjects were randomly divided into training sets and validation sets by R language sample function 7∶3.Univariate and multivariate Logistic regression analysis was used to screen independent predic-tors of adult MPP,and a nomogram model was established.The receiver operating characteristic(ROC)curve,cali-bration curve,and decision curve analysis(DCA)curve were used to evaluate and verify the model.Results The nomogram constructed by 7 independent predictors of age,body temperature,chills,dry cough,CRP,NLR,and the tree-in-bud sign had high accuracy.The area under the ROC curve of the training set was AUC=0.900(95％CI:0.863,0.936),and the area under the ROC curve of the validation set was AUC=0.878(95％CI:0.812,0.944).The calibration curves of the training set and the verification set were well-fitted.The training set and the verification set were within the risk threshold probability range of 0.05 and 0.94,0.09,and 0.82,respectively,the model had a net benefit.Conclusion The nomogram prediction model constructed by seven independent predictors has certain guiding significance in predicting the occurrence of adult MPP,helping clinicians to identify high-risk pa-tients early and formulate effective diagnosis and treatment plans.
AdultMycoplasma pneumoniae pneumoniaRisk factorsPrediction model
万方数据
维普
