Risk factors and predictive model construction for lower extremity arterial disease in diabetic patients

Objective To understand the prevalence and associated risk factors of lower extremity arterial disease (LEAD) in Chinese diabetic patients and to construct a risk prediction model. Methods Data from the Diabetes Complications Warning Dataset of the China National Population Health Science Data Center were used. Logistic regression analysis was employed to identify related factors, and machine learning algorithms were used to construct the risk prediction model. Results The study population consisted of 3,000 patients, with 476 (15.9%) having LEAD. Multivariate regression analysis indicated that male gender, atherosclerosis, carotid artery stenosis, fatty liver, hematologic diseases, endocrine disorders, and elevated glycosylated serum proteins were independent risk factors for LEAD. The risk prediction models constructed using Logistic regression and MLP algorithms achieved moderate discrimination performance, with AUCs of 0.73 and 0.72, respectively. Conclusion Our study identified the risk factors for LEAD in Chinese diabetic patients, and the constructed risk prediction model can aid in the diagnosis of LEAD.