Abstract: BACKGROUND: With the development of the aging population, the number of elderly patients with hip fracture is getting larger and larger, and the number of delirium after surgical treatment of hip fracture is also increasing. It has become a hot spot to study the risk factors of postoperative delirium in elderly patients with hip fracture and build a prediction model.
OBJECTIVE: To explore the clinical risk factors of postoperative delirium in elderly patients with hip fracture and to establish a Nomogram prediction model of postoperative delirium in elderly patients with hip fracture. 
METHODS: The elderly patients with hip fracture aged ≥ 65 years old who were treated in the Second Department of Orthopedics, Guangdong Province Traditional Chinese Medical Hospital from January 2015 to June 2019 were found and screened, and the medical records were analyzed retrospectively. Lasso regression and multivariate Logistic regression analysis were used to screen the independent risk factors of postoperative delirium in hip fracture. R software was used to construct risk prediction nomogram and evaluate the model. 
RESULTS AND CONCLUSION: (1) Postoperative delirium occurred in 243 cases (28.1%) of 864 elderly patients with hip fracture, including 166 females and 77 males, with an average age of 83.36 years. Postoperative delirium was not observed in 621 patients, including 453 females and 168 males, with an average age of 81.71 years. (2) Lasso regression and multivariate Logistic regression analysis showed that age, preoperative waiting time, preoperative anemia, intraoperative blood loss, preoperative low albumin, diabetes, cerebrovascular disease and hypoxemia were independent risk factors for postoperative delirium in elderly patients with hip fracture. (3) Nomogram model evaluation showed that the area under the receiver operating characteristic curve was 0.773 (95%CI:0.698-0.931). The calibration curve was a straight line with a slope close to 1, indicating that the model was accurate in predicting the risk of postoperative delirium in elderly patients with hip fracture. (4) The analysis of clinical decision curve showed that the model was clinically practical. (5) It is concluded that the Nomogram prediction model of postoperative delirium in elderly patients with hip fracture can individually predict the occurrence of postoperative delirium in elderly patients with hip fracture, and provide reference for clinical early identification and intervention of postoperative delirium in elderly patients with hip fracture.

Key words: hip fracture, aged, postoperative delirium, risk factors, prediction model