Development and validation of a nomogram for predicting in-hospital mortality in elderly hip fracture patients with atrial fibrillation: A retrospective study

Zhenli Li¹Jing He²Tiezhu Yao¹Guang Liu¹Jing Liu¹ling guo¹mengjia li¹zhengkun guan¹Ruolian Gao¹Jingtao Ma^1*

• ¹Fourth Hospital of Hebei Medical University, Shijiazhuang, China
• ²Beijing Anzhen Hospital, Capital Medical University, Chaoyang District, Beijing, China

Background: Hip fracture is prevalent among elderly patients that often results in intensive care unit (ICU) admission. When complicated with atrial fibrillation (AF), elderly patients with hip fracture were observed to own a high short-term mortality. However, few studies have focused specifically on such cohort. The aim of this study is to develop and validate a nomogram to evaluate the in-hospital mortality risk of such group in ICU. Methods: We enrolled elderly patients with hip fractures complicated by AF in Medical Information Mart for Intensive Care Database(MIMIC). Logistic regression (LR) and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms were employed to screen features. We further used Extreme Gradient Boosting (XGBoost) based on features selected by LR and LASSO algorithms to assist identifying the final model-established features. eICU Collaborative Research Database (eICU-CRD) was utilized for external validation. The area under curves (AUC), calibration curves, Delong test, decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were performed to evaluate the prediction performance. Ultimately, a visualized nomogram was constructed to provide convenient access for clinicians to evaluate the mortality risk. Results: A total of 308 patients were enrolled. We employed LR and LASSO algorithms to initially screen out 15 and 20 features respectively. Next, 10 features, which were the intersection of features selected by the above methods, were further ultilized to develop a XGBoost model to obtain the rank of feature importance. Finally, 8 features were ultimately selected to develop a nomogram by comparing the AUCs of LR models originating from a "feature-adding by the feature rank" strategy. The nomogram exhibited superior predictive performance (AUC:0.834) than conventional scoring systems in the training set, with an AUC of 0.715 in external validation. Conclusion: Our study constructed a predictive model based on features, selected by machine learning approaches, to evaluate the in-hospital mortality risk of critically ill patients with hip fractures combined with AF. And the accessible nomogram was offered to facilitate clinical decision-making.