Establishment of nomogram model to predict the risks for cognitive dysfunction in type 2 diabetes mellitus patients
Objective:To investigate the risk factors of cognitive dysfunction in type 2 diabetes mellitus(T2DM)and develop a nomogram model.Methods:The clinical data were retrospectively analyzed in 193 T2DM patients treated in our hospital between January 2021 and December 2022.The patients were divided into complicated group and non-complicated group based on cognitive dysfunction.Multivariate logistic regression analysis was used to analyze the influencing factors of cognitive dysfunction in T2DM patients.A risk prediction nomogram model was then developed using R 3.5.3 software,and its discrimination and predictive accuracy was assessed.Results:The incidence rate of cognitive dysfunction in T2DM patients was 38.86%(75/193).Age≥65 years,disease duration≥10 years,diabetic retinopathy,glycosylated hemoglobin(HbA1c)≥8%,and high sensitivity-C reactive protein(hs-CRP)≥10 mg/L were independent risk factors for cognitive dysfunction in T2DM patients(P<0.05),and a risk prediction nomogram model was developed based on the above five risk factors.The consistency index obtained from Bootstrap self-sampling validation was 0.834.The calibration curve showed that the calibration curve fitted well with the standard curve.The receiver operating characteristic curve showed that the sensitivity,specificity,and area under the curve predicted by the nomogram model were 82.67%,86.44%,and 0.859,respectively.Conclusion:Age≥65 years,disease duration≥10 years,diabetic retinopathy,HbA1c≥8%,and hs-CRP≥10 mg/L are independent risk factors for cognitive dysfunction in T2DM patients.The risk prediction nomogram model based on these factors has good consistency and prediction efficiency.
type 2 diabetes mellituscognitive dysfunctioninfluencing factornomogram model
万方数据
维普
