Background Mild cognitive impairment (MCI) is a transitional stage of cognitive function between normal aging and dementia. Substantial variations in the prevalence of MCI in different countries have been studied including China. In this study, we established a prediction system to assess the risk of MCI among the elderly in China. Methods The Rothman-Keller model was conducted on the basis of the risk factors of MCI obtained by the combined results of a meta-analysis. The accuracy of the model was verified using actual population data. Results A total of 1826 subjects as a verification set were enrolled in this study in February 2019. There were statistically significant differences in the combined results of 10 risk factors including hypertension, diabetes, educational level, hyperlipidemia, smoking, physical exercise, living alone, stroke, drinking and heart disease (P<0.05). The area under the curve (AUC) of the actual data and the predictive results of this model was 0.859 (95%CI: 0.812-0.906, P<0.05), the sensitivity was 86.6% and the specificity was 76.5%. Conclusions This model performs an effective prediction that may be applied to the primary prevention for patients with MCI, helping to reduce the risk of MCI.