2型糖尿病周围神经病变临床预测模型的构建

Development of a clinical prediction model for diabetic peripheral neuropathy with type 2 diabetes mellitus

目的分析2型糖尿病周围神经病变(DPN)发生的危险因素,构建DPN临床预测模型。方法回顾性收集2020年09月至2023年11月期间就诊于长春中医药大学附属医院内分泌代谢病科的2型糖尿病患者581例,并按是否并发周围神经病变分为:不伴有糖尿病周围神经病变NDPN组(296例)和伴有糖尿病周围神经病变DPN组(285例)。收集患者临床资料,进行单因素分析,将P<0.05的变量进行多因素Logistic回归分析,筛选出独立危险因素。采用R软件绘制列线图,绘制受试者工作特征曲线(ROC)并计算截断值,模型的区分度用ROC曲线下面积(AUC)值来表示,同时绘制模型的校准图,使用Hosmer-Lemeshow检验结合校准曲线评价模型预测准确性。结果筛选出7个危险因素:年龄、病程、吸烟史、糖化血红蛋白(HbA1c)、总胆固醇(TC)、三酰甘油(TG)、低密度脂蛋白胆固醇(LDL)。基于上述危险因素初步建立预测模型,ROC曲线下面积AUC值为0.722(95%CI:0.673~0.771),截断值为0.477(0.620,0.729),提示模型对DPN具有一定的预测能力和准确性。Hosmer-Lemeshow检验结果:卡方值10.683,P=0.220,表示模型拟合度较好。校准图结果显示预测曲线与校准曲线重合度较好,说明该模型准确度较好。结论2型糖尿病患者并发周围神经病变的危险因素有年龄、病程、吸烟史、HbA1c、TC、TG、LDL,基于以上因素构建的临床预测模型可为临床DPN患者早筛选、早识别提供参考。

Objective To analyze the risk factors of type 2 diabetic peripheral neuropathy(DPN)and to construct a clinical prediction model for DPN.Methods A retrospective review covered 581 patients with type 2 diabetes treated in the Department of Endocrinology and Metabolism Diseases of Changchun University of Traditional Chinese Medicine from September 2020 to November 2023;296 patients without diabetic kidney disease were classified as NDPD group and 285 patients with diabetic kidney disease were classified as DPN group.The clinical data of patients were collected;univariate analysis was performed followed by multivariate Logistic regression analysis to identify the variables with statistically significant differences to find independent risk factors.R software was used to construct a nomogram,and plot the receiver operating characteristic(ROC)curve and then calculated the cut-off value,and the discrimination of the model was represented by the area under curve(AUC)value.The calibration diagram of the model was drawn,and the Hosmer-Lemeshow test combined with the calibration curve was used to evaluate the prediction accuracy of the model.Results Seven risk factors were selected as age,disease duration,smoking history,hemoglobinA1c(HbA1c),total cholesterol(TC),triglyceride(TG),low density lipo-protein-cholesterol(LDL)and a prediction model was preliminarily established based on the above risk factors.The AUC value of the area under the ROC curve was 0.722(95%CI:0.673-0.771),and the cut-off value was 0.477(0.620,0.729)indicating that the model had certain predictive capacity and accuracy for DPN.The results of Hosmer-Lemeshow test showed thatχ2=10.683,P=0.220,indicating that the model fit was good.The results of the calibration chart showed that the prediction curve and the calibration curve had a good degree of coincidence,indicating that the accuracy of the model was good.Conclusions The risk factors for peripheral neuropathy in patients with type 2 diabetes mellitus include age,course of disease,smoking history,HbA1c,TC,TG,LDL.The clinical prediction model based on these factors can provide a reference for early clinical screening and early identification of DPN patients.