Establishment and application of risk prediction model for pulmonary infection in stroke patients
Objective To construct a risk prediction model for pulmonary infection in stroke patients and verify its clinical predictive performance.Methods Using convenience sampling,750 stroke patients hos-pitalized in a tertiary hospital in Guizhou Province from January 2021 to January 2023 were selected as study subjects.They were divided into a pulmonary infection group(n=267)and a non-pulmonary infection group(n=483)based on whether pulmonary infection occurred.Comparative analysis of relevant data between the two groups was conducted.Logistic regression analysis was applied to establish a risk prediction model.The goodness-of-fit of the model was tested using the Hosmer-Lemeshow(H-L)test,and the predictive perform-ance of the model was evaluated by the area under the receiver operating characteristic curve(ROC curve).Another 145 eligible patients from February to August 2023 were selected to validate the predictive perform-ance of the model.Results Univariate and multivariate analyses revealed that dysphagia[odds ratio(OR)=10.462],coexisting pulmonary diseases(OR=6.046),hypokalemia(OR=2.266),hyponatremia(OR=3.807),low hemoglobin(OR=4.036),National Institutes of Health Stroke Scale(NIHSS)score at admis-sion(OR=38.135),Activities of Daily Living(ADL)score at admission(OR=12.942),and length of hospi-tal stay(OR=8.992)were independent risk factors for pulmonary infection in stroke patients(P＜0.05).The risk prediction model formula was:Logit(P)=-4.761+2.348 ×(dysphagia score)+1.799 X(coexisting pulmonary diseases score)+0.818 ×(hypokalemia score)+1.337 ×(hyponatremia score)+1.395 ×(low he-moglobin score)+3.641 ×(NIHSS score)+2.560 ×(ADL score)+2.196 ×(length of hospital stay score).The area under the ROC curve of the modeling group was 0.953[95％confidence interval(95％CI)0.940-0.967,P＜0.001],with a Youden index of 0.762,a sensitivity of 0.880,a specificity of 0.882,and a P value of 0.553 in the H-L test.The validation results showed that the area under the ROC curve of the validation group was 0.946(95％CI:0.927-0.987,P＜0.001),with a sensitivity of 0.898,a specificity of 0.875,an ac-curacy of 88.3％,and a P value of 0.510 in the H-L test.Conclusion The established risk prediction model for pulmonary infection in stroke patients has good predictive performance,providing a reference for clinical healthcare professionals to early identify high-risk groups for stroke induced pulmonary infection and facilita-ting the timely adoption of preventive management measures.
StrokePulmonary infectionRisk factorsRisk predictionPrediction model
万方数据
维普
