Study on the predictive model of delirium risk after surgery for elderly hip fractures based on meta-analysis.

Abstract

Objective: To develop and validate a risk prediction model for postoperative delirium in elderly patients with hip fractures, aiming to identify high-risk patients and implement preventive measures.

Methods: A systematic search of five authoritative medical databases was conducted, retrieving a total of 1368 relevant articles. After screening, 44 high-quality studies were included in the meta-analysis, analyzing 13 potential risk factors, such as age, gender, diabetes, and history of stroke. A risk prediction model was constructed and validated in a cohort of 189 elderly hip fracture patients. The model's predictive performance was evaluated using ROC curves, with calibration assessed through the Hosmer-Lemeshow test, and clinical utility examined via Decision Curve Analysis (DCA) and Clinical Impact Curves (CIC).

Results: The meta-analysis identified the following as independent risk factors for postoperative delirium: age (≥ 70 years), male gender, diabetes, history of stroke, preoperative comorbidities (≥ 2), previous delirium, preoperative cognitive impairment, low preoperative albumin levels (≤ 40 g/L), prolonged preoperative waiting time (≥ 48 h), anemia (≤ 100 g/L), ASA classification (≥ 3), use of general anesthesia, and prolonged surgery duration (≥ 2 h). The prediction model demonstrated strong efficiency in the validation cohort, with an AUC of 0.956, sensitivity of 87.3%, specificity of 94.8%, and a Brier score of 0.144, indicating high predictive accuracy and calibration. DCA and CIC analyses showed the model to have strong clinical decision-making value and impact across most thresholds.

Conclusion: The risk prediction model developed in this study shows high predictive accuracy and clinical utility, making it valuable for identifying high-risk patients and implementing preventive measures in clinical practice. However, the study has limitations, such as potential retrospective bias, and further validation in larger, multicenter prospective studies is needed to confirm the model's broader applicability and stability.