Abstract: Objective To investigate the risk factors of Alzheimer’s disease (AD) in the elderly and to develop a nomogram model for risk prediction. Methods The data of 2968 elderly cases were extracted from the National Alzheimer’s Coordinating Center (NACC), a public database in USA, including sociodemographic information, lifestyle, mental health, sleep patterns, disease history and medication usage. The subjects were randomly divided into a modeling group and an internal validation group at a ratio of 7∶3. Multivariable Logistic regression model was employed to identify the risk factors of AD in the elderly, and a nomogram prediction model was constructed based on these variables. The model’s discriminative ability and calibration were assessed by the area under the receiver operating characteristic (ROC) curve and calibration plots. The clinical value of the model was evaluated with clinical impact curves. Results The multivariable Logistic regression analysis showed that gender, educational level, systolic blood pressure, depression, anxiety, rapid eye movement sleep behavior disorder, age, history of traumatic brain injury and the number of medications were influencing factors of AD in the elderly (P<0.05). A risk prediction nomogram was established based on these nine factors. The area under the ROC curve and calibration plots showed good discriminative ability and accuracy of the model. The clinical impact curves demonstrated that the model had practical clinical utility within a substantial range of threshold values. Conclusions The nomogram prediction model for AD constructed in this study demonstrates good predictive performance and can provide a reference for the early identification of the elderly with high risk of AD.

Key words: Alzheimer’s disease, nomogram, prediction, influencing factor, aged