| 2型糖尿病周围神经病变风险的列线图预测模型研究 |
| |
| 引用本文： | 李永生,张学良,李丞,封志炜,王凯. 2型糖尿病周围神经病变风险的列线图预测模型研究[J]. 中国全科医学, 2022, 25(6): 675-681. DOI: 10.12114/j.issn.1007-9572.2021.02.118 |
| |
| 作者姓名： | 李永生 张学良 李丞 封志炜 王凯 |
| |
| 作者单位： | 1．830011 新疆维吾尔自治区乌鲁木齐市，新疆医科大学公共卫生学院2．830011 新疆维吾尔自治区乌鲁木齐市，新疆医科大学医学工程技术学院3．830054 新疆维吾尔自治区乌鲁木齐市，新疆医科大学第一附属医院4．830011 新疆维吾尔自治区乌鲁木齐市，新疆医科大学继续教育学院 |
| |
| 基金项目： | 新疆维吾尔自治区自然科学基金资助项目(2019D01C215)。 |
| |
| 摘 要： | 背景2型糖尿病周围神经病变（DPN）患病率高、危害性大，目前尚无有效的治疗方法。目的探讨DPN的危险因素，旨在建立并验证一种辅助临床预测DPN患者的可视化评价工具。方法收集2010—2019年在新疆医科大学第一附属医院就诊的15 020例2型糖尿病（T2DM）患者，按照3∶1的比例将患者随机分为训练组（n =11 265）和验证组（n=3 755）。收集患者的一般资料和生化资料。通过Lasso回归分析筛选独立预测因子，在此基础上利用多因素Logistic回归分析进一步探讨并建立列线图预测模型，并由验证组评估DPN列线图预测模型的可行性。最后，分别采用受试者工作特征（ROC）曲线下面积（AUC）、校正曲线和决策曲线分析（DCA）对预测模型的鉴别能力、准确性和临床实用性进行评估。结果15 020例T2DM患者中，无DPN患者8 887例，DPN患者6 133例。Lasso回归结合多因素Logistic回归分析结果显示，年龄〔OR=1.034，95%CI（1.031，1.039）〕、糖尿病视网膜病变（DR）〔OR=11.881，95%CI（10.756，13.135）〕、糖尿病病程〔OR=1.070，95%CI（1.061，1.078）〕、糖化血红蛋白（HbA1c）〔OR=1.237，95%CI（1.209，1.266）〕、高密度脂蛋白（HDL）〔OR=0.894，95%CI（0.877，0.901）〕是T2DM患者发生DPN的影响因素（P<0.05）。利用上述变量建立列线图预测模型。训练组中列线图预测模型预测DPN发生的AUC为0.858〔95%CI（0.851，0.865）〕，验证组中列线图预测模型预测DPN发生的AUC为0.852〔95%CI（0.840，0.865）〕。Hosmer-Lemeshow拟合优度检验显示出较好的拟合度（P>0.05）。DCA显示当患者的阈值概率为0~0.9，使用列线图预测模型预测DPN风险的净收益更高。结论本研究成功建立并验证一种高精度的列线图预测模型（预测变量包括年龄、DR、糖尿病病程、HbA1c、HDL），有助于提高DPN高危患者的早期识别和筛选能力。
|
| 关 键 词： | 糖尿病 2型 糖尿病神经病变 危险因素 预测模型 |
| 收稿时间： | 2021-08-20 |
A Predictive Nomogram for the Risk of Peripheral Neuropathy in Type 2 Diabetes |
| |
| LI Yongsheng,ZHANG Xueliang,LI Cheng,FENG Zhiwei,WANG Kai. A Predictive Nomogram for the Risk of Peripheral Neuropathy in Type 2 Diabetes[J]. Chinese General Practice, 2022, 25(6): 675-681. DOI: 10.12114/j.issn.1007-9572.2021.02.118 |
| |
| Authors: | LI Yongsheng ZHANG Xueliang LI Cheng FENG Zhiwei WANG Kai |
| |
| Affiliation: | (School of Public Health,Xinjiang Medical University,Urumqi 830011,China;Department of Medical Engineering and Technology,Xinjiang Medical University,Urumqi 830011,China;The First Affiliated Hospital of Xinjiang Medical University,Urumqi 830054,China;School of Continuing Education,Xinjiang Medical University,Urumqi 830011,China) |
| |
| Abstract: | Background Effective treatment has not been worked out so far for diabetic peripheral neuropathy(DPN)in type 2 diabetes which is regarded as highly prevalent and quite harmful.Objective To screen the risk factors of DPN in type 2 diabetes,and used them to develop a predictive nomogram as a visualization tool assisting clinical diagnosis of this disease.Methods Participants(n=15020)were type 2 diabetics who were retrospectively selected from the First Affiliated Hospital of Xinjiang Medical University from 2010 to 2019,and 75%of them were randomly assigned to a training group(n=11265)and other 25%to a verification group(n=3755).Patients'basic personal information and biochemical data were collected.Independent predictors of DPN were screened by Lasso regression analysis,and further analyzed using multivariate Logistic regression analysis,then the finally determined ones were used to develop a predictive nomogram.The performance of the nomogram was verified in the verification group.Finally,the area under the ROC curve(AUC),calibration curve and decision curve analysis(DCA)were used to evaluate the identification ability,accuracy and clinical applicability of the nomogram.Results Among the 15020 cases,6133 had DPN,and other 8887 did not.The findings of Lasso regression with multivariate Logistic regression analyses showed that age〔OR=1.034,95%CI(1.031,1.039)〕,diabetic retinopathy〔OR=11.881,95%CI(10.756,13.135)〕,duration of diabetes〔OR=1.070,95%CI(1.061,1.078)〕,glycosylated hemoglobin〔OR=1.237,95%CI(1.209,1.266)〕and high-density lipoprotein〔OR=0.894,95%CI(0.877,0.901)〕were associated with DPN.The predictive nomogram was established by employing the above-mentioned variables.The AUC of the nomogram for identifying DPN in the training group was 0.858〔95%CI(0.851,0.865)〕,and in the validation group was 0.852〔95%CI(0.840,0.865)〕.The nomogram was found with a high goodness of fit by the Hosmer-Lemeshow test(P>0.05).DCA showed that when the threshold probability of patients was 0 to 0.9,using the nomogram resulted in higher net benefit of predicting the risk of DPN.Conclusion We successfully established and verified a nomogram(with above-mentioned five variables included)with a high accuracy,which may be used as a tool facilitating the improvement in early identification or screening of DPN in high-risk type 2 diabetics. |
| |
| Keywords: | Diabetes mellitus,type 2 Diabetic neuropathies Risk factors Prediction model |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《中国全科医学》浏览原始摘要信息 |
|
点击此处可从《中国全科医学》下载全文 |
|
