ABSTRACT
Objective:To explore the predictive performance of machine learning model based on vascular risk factors in early prediction of vascular cognitive impairment. Methods:From April to September, 2020, 70 subjects were enrolled and collected information of the demographics and vascular risk factors. They were assessed with Montreal Cognitive Assessment (MoCA), and then divided into normal group, vascular mild cognitive impairment (VaMCI) group and dementia group. The differences of vascular risk factors among the three groups were detected with one-way ANOVA, and the significant factors were selected to establish predictive models with support vector machine (SVM) and extreme learning machine (ELM). The predictive performance of two models was compared with Receiver Operating Characteristic Curve. Results:There were 32 cases in the normal group, 23 in VaMCI group and 15 in dementia group. Systolic blood pressure, fasting blood glucose, total cholesterol, low density lipoprotein and blood uric acid were significantly different among the three groups (F > 3.318, P < 0.05). The area under curve was the most (0.911) in SVM model predicting for VaMCI (P < 0.01), and the predictive efficacy was better for SVM model. Conclusion:SVM predictive model based on vascular risk factors may be more effective for predicting VaMCI.