Objective To investigate the correlation between mild cognitive impairment (MCI) and motor ability in elderly patients with coronary heart disease (CHD) and atrial fibrillation (AF). Methods A total of 116 elderly patients with CHD and AF admitted to the First Affiliated Hospital of Xinjiang Medical University from January 2024 to January 2025 were enrolled. Cognitive function was assessed using the mini-mental state examination (MMSE) and Montreal cognitive assessment (MoCA). Patients were divided into a MCI group and a control group according to the assessment results. All patients underwent grip strength, walking speed, and timed up-and-go (TUG) tests to evaluate and compare muscle mass, mobility, and dynamic balance ability between the MCI group and the control group. SPSS 27.0 was used for data analysis. According to data type, independent samples t test or Chi-square test was used for comparison between two groups. Binary logistic regression model was used to analyze the factors associated with MCI in elderly patients with CHD and AF, and receiver operating characteristic (ROC) curves were plotted to analyze the value of the logistic regression model in predicting MCI. Results Of the 116 elderly patients with CHD and AF, 110 (94.83%) completed the study, among whom 33 were diagnosed with MCI, with a detection rate of 30.00%. Patients in the MCI group had a longer TUG time, and lower walking speed and grip strength than the control group, with statistically significant differences (all P<0.05). Using the occurrence of MCI in elderly patients with CHD and AF as the dependent variable, logistic regression analysis showed that age (70-80 years) (OR=3.766,95%CI 1.709-8.297; P=0.001), diabetes mellitus (OR=1.943,95%CI 1.295-2.915; P=0.001), smoking history (OR=1.418,95%CI 1.202-1.671; P<0.001), hyperuricemia (OR=1.508,95%CI 1.009-2.254; P=0.046), Gensini score≥64 points (OR=1.721,95%CI 1.246-2.378; P=0.001), and TUG test results (OR=2.115,95%CI 1.399-3.198; P<0.001) were risk factors, while junior college education or above (OR=0.621,95%CI 0.479-0.806; P<0.001) was a protective factor. ROC curve analysis showed an area under curve of 0.919 (95%CI 0.850-0.988) for the prediction model, and the Hosmer-Lemeshow goodness-of-fit test indicated good reliability of the model. Conclusion The incidence of MCI is high in elderly patients with CHD and AF, and those with MCI have decreased motor ability. Age, educational level, diabetes mellitus, smoking history, hyperuricemia, Gensini score, and TUG test results are influencing factors for MCI. The prediction model constructed based on these factors shows good value in predicting MCI in elderly patients with CHD and AF.