To develop a model for the prognosis of cognitive impairment in patients with type 1 diabetes mellitus based on data from proton magnetic resonance spectroscopy.Patients with type 1 diabetes mellitus and individuals without diabetes were examined (control group). All participants were evaluated for carbohydrate metabolism, underwent neuropsychological testing (MoCa test), proton magnetic resonance spectroscopy of the brain. Statistical processing of the results was performed using the IBM SPSS Statistics 20.0 program. The predictive model is calculated using discriminant analysis.Based on the data of proton magnetic resonance spectroscopy, a predictive model for the development of cognitive impairment in patients with type 1 diabetes mellitus was obtained using discriminant analysis.The method for the early diagnosis of cognitive impairment allows predicting the development of cognitive dysfunction in patients with type 1 diabetes in the early stages and can be used in clinical practice to assess the effectiveness of preventive therapy for cognitive impairment.