The Development And Application Of A Risk Prediction Model For Postoperative Delirium In Patients With Hip Fracture

Objective: To establish a risk prediction model of postoperative delirium(POD)in patients with hip fracture and to explore the prediction effects of the model.Methods: A total of 200 patients with hip fracture in a tertiary hospital were selected,observation and evaluation were performed within 7 days after operationand.Group patients according to delirium criteria.Clinical data including age,gender,body mass index(BMI),education level,family economic status,history of excessive drinking,hypertension,diabetes,stroke,hemoglobin,albumin,visual analogue scale(VAS),operation duration,anesthesia mode,intraoperative hypotension,intraoperative hypoxia saturation,intraoperative blood loss,postoperative drainage tube placement and other indicators may be related to POD,indicators of POD group(n=66)and non POD group(n=134)were analyzed.Logistic regression was used to establish a risk prediction model.The area under the ROC curve was used to test the model to predict the effects.Thirty patients were selected to evaluate the model’s effects.Results: In this study,200 patients with hip fracture underwent surgical treatment,and 66 patients had POD,with a incidence rate of 33%.There were no significant differences in gender,history of excessive drinking,living conditions,economic status,sedative use history,anemia,stroke history,diabetes,hypertension,chronic renal failure,creatinine level,operation time,intraoperative blood loss and drainage tube between the two groups(P > 0.05).There were significant differences in age,BMI,education level,sleep disorder,Alzheimer’s disease,depression,VAS score,albumin level,anesthesia mode,intraoperative hypotension and intraoperative hypoxic saturation between the two groups(P < 0.05).The study finally included age(OR=1.077),preoperative visual analogue scale(VAS scale)(OR=1.882),Alzheimer’s disease(OR=10.711),depression(OR= 22.150),and intraoperative hypotension(OR=8.189)to construct the risk prediction model.The model formula was: Z=0.075 × age + 0.632 × preoperative VAS score +2.371 × Alzheimer’s disease + 3.098 × depression + 2.103 × intraoperative hypotension-12.069,the area under the ROC curve of this model was 0.848,with the sensitivity of 0.652,the specificity of 0.888,the Youden index of 0.540.The model verification results showed the sensitivity of 75%,the specificity of100%,and the accuracy of 93.3%.Conclusion: The prediction effect of the model is satisfactory.Patients can be predicted the risk of postoperative delirium after admission,which can provide basis for prevention and treatment for high risk patients.