Background Diabetic peripheral neuropathy (DPN) is one of the most serious complications of type 2 diabetes mellitus (T2DM). DPN increases the risk of ulcers, foot infections, and noninvasive amputations, ultimately leading to long-term disability.
Methods Seven hundred patients with T2DM were investigated from 2013 to 2017 in the Sanlin community by obtaining basic data from the electronic medical record system (EMRS). From September 2018 to July 2019, 681 patients (19 missing) were investigated using a questionnaire, physical examination, biochemical index test, and follow-up Toronto clinical scoring system (TCSS) test. Patients with a TCSS score ≥6 points were diagnosed with DPN. After removing missing values, 612 patients were divided into groups in a 3:1 ratio for external validation. Using different Lasso analyses (misclassification error, mean squared error, –2log-likelihood, and area under curve) and a logistic regression analysis of the training set, models A, B, C, and D were established. The receiver operating characteristic (ROC) curve, calibration plot, dynamic component analysis (DCA) measurements, net classification improvement (NRI) and integrated discrimination improvement (IDI) were used to validate discrimination and clinical practicality of the model.
Results Through data analysis, model A (containing four factors), model B (containing five factors), model C (containing seven factors), and model D (containing seven factors) were built. After calibration, ROC curve, DCA, NRI and IDI, models C and D exhibited better accuracy and greater predictive power.
Conclusion Four prediction models were established to assist with the early screening of DPN in patients with T2DM. The influencing factors in model C and D are more important factors for patients with T2DM diagnosed with DPN.
Citations
Citations to this article as recorded by
Diabetes Mellitusu Olan Bireylerde Periferal Nöropati ve Hemşirelik Bakımı Semanur BİLGİÇ, Burcu BAYRAK KAHRAMAN Akdeniz Hemşirelik Dergisi.2024; 2(3): 113. CrossRef
Risk Factors for Subclinical Diabetic Peripheral Neuropathy in Type 2 Diabetes Mellitus Li Gao, Jiexing Qin, Ying Chen, Wenqun Jiang, Desheng Zhu, Xiajun Zhou, Jie Ding, Huiying Qiu, Yan Zhou, Qing Dong, Yangtai Guan Diabetes, Metabolic Syndrome and Obesity.2024; Volume 17: 417. CrossRef
Predictive model and risk analysis for peripheral vascular disease in type 2 diabetes mellitus patients using machine learning and shapley additive explanation Lianhua Liu, Bo Bi, Li Cao, Mei Gui, Feng Ju Frontiers in Endocrinology.2024;[Epub] CrossRef
Multi‐feature, Chinese–Western medicine‐integrated prediction model for diabetic peripheral neuropathy based on machine learning and SHAP Aijuan Jiang, Jiajie Li, Lujie Wang, Wenshu Zha, Yixuan Lin, Jindong Zhao, Zhaohui Fang, Guoming Shen Diabetes/Metabolism Research and Reviews.2024;[Epub] CrossRef
Clinical significance of vascular endothelial growth factor and endothelin-1 in serum levels as novel indicators for predicting the progression of diabetic nephropathy Wei Chu, Lin-Lin Ma, Bin-Xian Li, Ming-Cheng Li European Journal of Inflammation.2023; 21: 1721727X2311515. CrossRef
Common and contrast determinants of peripheral artery disease and diabetic peripheral neuropathy in North Central Nigeria Felicia Ehusani Anumah, Yakubu Lawal, Rifkatu Mshelia-Reng, Special Odiase Omonua, Kenechukwu Odumodu, Ramatu Shuaibu, Ukamaka Dorothy Itanyi, Amina Ibrahim Abubakar, Hadijat Oluseyi kolade-Yunusa, Zumnan Songden David, Babajide Ogunlana, Andrew Clarke, O The Foot.2023; 55: 101987. CrossRef
ApoA-I and Diabetes Thomas W. King, Blake J. Cochran, Kerry-Anne Rye Arteriosclerosis, Thrombosis, and Vascular Biology.2023; 43(8): 1362. CrossRef
Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning Xiaoyang Lian, Juanzhi Qi, Mengqian Yuan, Xiaojie Li, Ming Wang, Gang Li, Tao Yang, Jingchen Zhong BMC Medical Informatics and Decision Making.2023;[Epub] CrossRef
Establishment and health management application of a prediction model for high-risk complication combination of type 2 diabetes mellitus based on data mining Xin Luo, Jijia Sun, Hong Pan, Dian Zhou, Ping Huang, Jingjing Tang, Rong Shi, Hong Ye, Ying Zhao, An Zhang, Yee Gary Ang PLOS ONE.2023; 18(8): e0289749. CrossRef
Development and validation of risk prediction model for diabetic neuropathy among diabetes mellitus patients at selected referral hospitals, in Amhara regional state Northwest Ethiopia, 2005–2021 Negalgn Byadgie Gelaw, Achenef Asmamaw Muche, Adugnaw Zeleke Alem, Nebiyu Bekele Gebi, Yazachew Moges Chekol, Tigabu Kidie Tesfie, Tsion Mulat Tebeje, Jacopo Sabbatinelli PLOS ONE.2023; 18(8): e0276472. CrossRef
Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis Kui Liu, Linyi Li, Yifei Ma, Jun Jiang, Zhenhua Liu, Zichen Ye, Shuang Liu, Chen Pu, Changsheng Chen, Yi Wan JMIR Medical Informatics.2023; 11: e47833. CrossRef
Establishment of models to predict factors influencing periodontitis in patients with type 2 diabetes mellitus Hong-Miao Xu, Xuan-Jiang Shen, Jia Liu World Journal of Diabetes.2023; 14(12): 1793. CrossRef
Impact of Nutraceuticals on Type 1 and Type 2 Diabetes Mellitus-Induced Micro- and Macrovasculopathies Philanathi Mabena, Thandi M. D. Fasemore, Pilani Nkomozepi Applied Sciences.2023; 14(1): 64. CrossRef
Prediction Model for the Risk of HIV Infection among MSM in China: Validation and Stability Yinqiao Dong, Shangbin Liu, Danni Xia, Chen Xu, Xiaoyue Yu, Hui Chen, Rongxi Wang, Yujie Liu, Jingwen Dong, Fan Hu, Yong Cai, Ying Wang International Journal of Environmental Research and Public Health.2022; 19(2): 1010. CrossRef
Management of Type II Diabetes Mellitus using Adult Autologous Adipose derived stem cells with Platelets Rich Plasma (PRP) Shahzad Anwar, Ayesha Nawaz, Zaigham Abbas Pakistan BioMedical Journal.2022; : 270. CrossRef
A Nomogram for Predicting the Possibility of Peripheral Neuropathy in Patients with Type 2 Diabetes Mellitus Wanli Zhang, Lingli Chen Brain Sciences.2022; 12(10): 1328. CrossRef