Development and Validation of a Prediction Model for In-hospital Mortality in Patients with Coronary Artery Disease Aged 75 Years and Older
LIU Cheng
LIU Sen
JIN Menglong
LIU Ziyang
FU Zhenyan
MA Yitong
Abstract：Objective: To construct and validate a predictive model for the risk of in-hospital mortality in patients aged ≥75 years with coronary artery atherosclerotic heart disease (CAD). Methods: A total of 2,190 patients diagnosed with CAD and aged ≥75 years who were hospitalized at The First Affiliated Hospital of Xinjiang Medical University between May 2012 and September 2023 were enrolled as the study population. Clinical data were collected and randomly divided into a training set (1,533 cases) and a validation set (657 cases) in a 7:3 ratio. Binary logistic regression analysis was used to identify independent risk factors for in-hospital mortality in elderly CAD patients, and a receiver operating characteristic (ROC) curve, calibration curve, decision curve (DCA), and nomogram prediction model were constructed. The model was then validated using the validation set. Results: Multivariate logistic regression analysis showed that increasing age, presence of diabetes and hypertension, elevated neutrophil percentage, increased transaminase levels, decreased serum albumin, increased body mass index (BMI), and reduced left ventricular ejection fraction (LVEF) were independent risk factors for in-hospital mortality in elderly CAD patients (P < 0.05). A nomogram prediction model was built using these eight indicators, and the effectiveness of the model was evaluated by drawing a calibration curve (χ² = 14.52, P = 0.07). The area under the ROC curve (AUC) of the model in the training set was 0.761, with a sensitivity of 52.38% and a specificity of 87.09%. The DCA curve showed that the model had clinical utility within a certain range. Further evaluation using the validation set showed an AUC of 0.828, a sensitivity of 74.63%, and a specificity of 83.34%, with a calibration curve χ² = 7.31, P = 0.50. Conclusion: The model has a high level of discrimination and effectiveness, good clinical practicality, and can serve as an effective tool for predicting in-hospital mortality in patients aged ≥75 years with CAD.
Keywords：coronary artery diseasethe elderlyin-hospital mortalityinfluencing factornomogramprediction model
Publication Date：2025-08-25
Online Publishing Date：2025-09-10(First online date of this platform, not the publication date of the document)
Pages：7( 2499-2505 )