Developing a nomogram for postoperative delirium in elderly patients with hip fractures

Area of Science:

• Geriatric Medicine
• Surgical Complications
• Data Science in Healthcare

Background:

• Postoperative delirium (POD) is a common complication in elderly patients with hip fractures (HFs).
• POD significantly impacts patient recovery, hospital stay duration, healthcare expenses, and long-term health outcomes.
• Existing research on POD risk factors is limited by single-factor analyses and small sample sizes.

Purpose of the Study:

• To determine the incidence of POD in elderly patients undergoing hip fracture surgery.
• To identify independent risk factors associated with POD development.
• To develop and validate a predictive nomogram model for early POD risk assessment.

Main Methods:

• Retrospective analysis of 532 elderly patients with hip fractures from April 2018 to April 2022.
• Patients were divided into training (70%) and validation (30%) cohorts.
• Logistic multivariate analysis and machine learning techniques (Lasso regression, SVM, random forest) were used to identify risk factors and build the nomogram.

Main Results:

• Overall POD incidence was 14.85%.
• Independent risk factors identified include cognitive impairment history, American Society of Anesthesiologists grade > 2, RBC transfusion of ≥ 2 units, postoperative ICU care, and preoperative hemoglobin levels.
• The nomogram demonstrated excellent predictive accuracy (AUC 0.833 in training, 0.850 in validation) and clinical utility.

Conclusions:

• Cognitive impairment history, ASA grade, RBC transfusion, ICU care, and preoperative hemoglobin are key independent risk factors for POD in elderly hip fracture patients.
• The developed nomogram is accurate and stable for predicting POD risk.
• Clinical application of the nomogram is recommended to optimize management and reduce delirium incidence.