Construction Of Nomogram Prediction Model For The Risk Of Type 2 Diabetes Mellitus Complicated With Peripheral Neuropathy

Objective: To analyze the related risk factors of type 2 diabetes mellitus(T2DM)complicated with peripheral neuropathy,and to construct a simple and efficient nomogram prediction model for better identifying patients with high risk diabetic peripheral neuropathy(DPN)in clinical practice.Methods: A total of 500 patients with type 2 diabetes admitted to the Department of Endocrinology,the First Affiliated Hospital of Xinjiang Medical University from March 2021 to March 2022 were included and divided into 250 patients in DPN group and 250 patients in T2DM group according to whether they met the diagnostic criteria for diabetic peripheral neuropathy.The clinical and laboratory data of the patients were collected.Univariate analysis was performed to select the risk factors related to DPN,and then the statistically significant variables were included in the multivariate Logistic regression analysis to screen the independent risk factors of DPN.R software was used to construct a nomogram prediction model for the risk of type 2 diabetes mellitus complicated with peripheral neuropathy,and the receiver operating characteristic curve(ROC)and calibration curve were drawn,and the area under the ROC curve(AUC)was calculated to evaluate the discriminant ability and accuracy of the model.A P value of less than 0.05 was considered statistically significant.Results: Were selected six independent factors: age,duration of diabetes,glycated hemoglobin,triglycerides,2 hours C peptide,three iodine thyroid glycine and establish the regression model.The ROC curve area was 0.938(95%CI: 0.918～0.958),and the AUC value was greater than 75%.The calibration curve indicated that the calibration degree was good,and the model had good prediction ability and high accuracy.Conclusion: In this study,age,diabetes course,glycosylated hemoglobin,triglyceride,2-hour C-peptide and triiodothyronine were included as predictive factors to establish a line graph prediction model for the risk of type 2 diabetes complicated with peripheral neuropathy,which can identify high-risk patients who may develop DPN early.