Developing a prediction model for preoperative acute heart failure in elderly hip fracture patients: a retrospective analysis

Abstract Background Hip fractures in the elderly are a common traumatic injury. Due to factors such as age and underlying diseases, these patients exhibit a high incidence of acute heart failure prior to surgery, severely impacting surgical outcomes and prognosis. Objective This study aims to explore the potential risk factors for acute heart failure before surgery in elderly patients with hip fractures and to establish an effective clinical prediction model. Methods This study employed a retrospective cohort study design and collected baseline and preoperative variables of elderly patients with hip fractures. Strict inclusion and exclusion criteria were adopted to ensure sample consistency. Statistical analyses were carried out using SPSS 24.0 and R software. A prediction model was developed using least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression. The accuracy of the model was evaluated by analyzing the area under the receiver operating characteristic (ROC) curve (AUC) and a calibration curve was plotted to assess the model’s calibration. Results Between 2018 and 2019, 1962 elderly fracture patients were included in the study. After filtering, 1273 were analyzed. Approximately 25.7% of the patients experienced acute heart failure preoperatively. Through LASSO and logistic regression analyses, predictors for preoperative acute heart failure in elderly patients with hip fractures were identified as Gender was male (OR = 0.529, 95% CI: 0.381–0.734, P