【Abstract】Objective: To investigate the risk factors for postoperative pulmonary complications (PPCs) in elderly diabetic patients with femoral fracture and to develop a predictive model for these complications. Methods: A retrospective cohort study was conducted to analyze the clinical data of 1057 diabetic patients aged 65～102 years [median age: 75.0 (IQR: 69.0, 83.0)], including 345 males and 712 females, who underwent femoral fracture surgery at the Second Affiliated Hospital of Army Medical University from January 2016 to December 2023. The patients were divided into a PPCs group (n=115) and a Non-PPCs group (n=942) based on the occurrence of PPCs after surgery. Logistic regression analysis was performed to identify independent risk factors for PPCs, and a nomogram was constructed to integrate these risk factors. The model was evaluated using receiver operating characteristic (ROC) curves, calibration curves, Hosmer-Lemeshow goodness-of-fit tests, and decision curve analysis (DCA). Internal validation was performed using the Bootstrap method. Results: The incidence of PPCs was 10.88%. Logistic regression analysis revealed that age, hypoalbuminemia (ALB＜35g/dl), preoperative hemoglobin level, preoperative comorbid respiratory disease, operative time, anesthesia time, anesthesia method, preoperative waiting time, and hospital stay were significant risk factors for PPCs in elderly diabetic patients with femoral fracture surgery. The odds ratios (OR) and 95% confidence interval (CI) were 2.34 (1.43-5.65), 19.93 (4.89-81.09), 3.25 (1.68-7.35), 13.49 (5.35-34.05), 3.31 (1.53-7.19), 2.15 (1.17-3.93), 3.82 (1.56-9.32), 5.23 (1.37-19.96), and 2.11 (1.12-3.96), respectively (all P0.05). The nomogram model incorporating these factors demonstrated an area under the ROC curve (AUC) of 0.91 (95% CI: 0.88-0.94) for predicting PPCs, with sensitivity and specificity of 83.7% and 81.2%, respectively. The calibration curve was a straight line with a slope close to 1. The Hosmer-Lemeshow test yieldedχ²=1.78 (P=0.314). DCA indicated a good net benefit at a potential risk threshold of 4.2%. Internal validation confirmed the good consistency of the model. Conclusion: Age, hypoalbuminemia, preoperative hemoglobin level, preoperative comorbid respiratory disease, operative time, anesthesia time, anesthesia method, preoperative waiting time, and hospital stay are risk factors for PPCs in elderly diabetic patients with femoral fracture surgery. The nomogram model developed in this study exhibits good predictive performance.