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

Yingjie Kuang, Zhixin Cheng, Jun Zhang, Chunxu Yang and Yue Zhang

PLOS ONE, 2024, vol. 19, issue 12, 1-14

Abstract: 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.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0314862 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 14862&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0314862

DOI: 10.1371/journal.pone.0314862

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().