Abstract: Objective To identify the relevant risk factors of mild cognitive impairment (MCI) in the elderly and to establish a nomogram of MCI risk, so as to provide references for early clinical identification and intervention. 
Methods A total of 322 elderly people who underwent physical examination in the community of Shijiazhuang City from September 2021 to July 2022 were selected as the research subjects, and the general information, clinical detection indicators, and status of daily leisure activities were collected. Univariate analysis and multivariate Logistic regression analysis were used to determine the independent risk factors of MCI risk in the elderly. The nomogram prediction model was established and the discrimination and calibration of the nomogram model were evaluated by the receiver operating characteristic (ROC) curve, Hosmer-Lemeshow (H-L) test, and calibration curve. 
Results Multivariate Logistic regression analysis showed that advanced age, low education level, low cognitive activity participation, and Apolipoprotein E (ApoE) ε4 risk gene were independent risk factors for MCI. A nomogram predictive model was established and the area under the ROC curve (AUC) was 0.887 (95%CI: 0.834-0.939, P＜0.001), and the P value of the H-L test was 0.675. The Brier value of the calibration curve was 0.078, the absolute error was 0.013, and the calibration curve was very close to the ideal reference line. 
Conclusion The nomogram model based on the four risk factors, including age, education level, cognitive activity index, and ApoE ε4 risk gene, can effectively predict the risk of MCI in the elderly in Shijiazhuang City, and further external verification research can be carried out. 

Key words: cognitive dysfunction, proportional hazards models, risk factors