Observational Study
Copyright ©The Author(s) 2022. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Diabetes. Nov 15, 2022; 13(11): 986-1000
Published online Nov 15, 2022. doi: 10.4239/wjd.v13.i11.986
Risk factor analysis and clinical decision tree model construction for diabetic retinopathy in Western China
Yuan-Yuan Zhou, Tai-Cheng Zhou, Nan Chen, Guo-Zhong Zhou, Hong-Jian Zhou, Xing-Dong Li, Jin-Rui Wang, Chao-Fang Bai, Rong Long, Yu-Xin Xiong, Ying Yang
Yuan-Yuan Zhou, Hong-Jian Zhou, Xing-Dong Li, Department of Endocrinology and Metabolism, The Sixth Affiliated Hospital of Kunming Medical University, The People’s Hospital of Yuxi City, Yuxi 653100, Yunnan Province, China
Tai-Cheng Zhou, Jin-Rui Wang, Chao-Fang Bai, Rong Long, Yu-Xin Xiong, Ying Yang, Department of Endocrinology and Metabolism, Affiliated Hospital of Yunnan University, The Second People’s Hospital of Yunnan Province, Kunming 650021, Yunnan Province, China
Nan Chen, Guo-Zhong Zhou, Department of Endocrinology and Metabolism, The Frist People’s Hospital of Anning City, Anning City 650300, Yunnan Province, China
Author contributions: Zhou YY contributed to the conception and design, acquisition of data or analysis and interpretation of data, and drafting the article or revising it critically for important intellectual content; Yang Y and Zhou TC were responsible for supervision, project administration, and funding acquisition; Chen N and Zhou GZ were responsible for literature and formal analysis; Wang JR, Bai CF, Long R, Xiong YX, Zhou HJ, and Li XD were responsible for patient recruitment and clinical data curation; all authors gave final approval of the version to be published.
Supported by the Natural Science Foundation of China, No. 82160159; Natural Science Foundation of Yunnan Province, No. 202101AY070001-199; Scientific Research Fund of Yunnan Education Department, No. 2021J0303; and Postgraduate Innovation Fund of Kunming Medical University, No. 2020D009.
Institutional review board statement: The study was reviewed and approved by the Ethics Committee of Affiliated Hospital of Yunnan University (Approval No. 2021062).
Informed consent statement: Written informed consent was obtained from all participants.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: No additional data are available.
STROBE statement: The authors have read the STROBE Statement—checklist of items, and the manuscript was prepared and revised according to the STROBE Statement—checklist of items.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Ying Yang, PhD, Chief Doctor, Professor, Department of Endocrinology and Metabolism, Affiliated Hospital of Yunnan University, The Second People’s Hospital of Yunnan Province, No. 176 Qingnian Road, Kunming 650021, Yunnan Province, China. yangying2072@126.com
Received: June 13, 2022
Peer-review started: June 13, 2022
First decision: August 1, 2022
Revised: August 20, 2022
Accepted: October 27, 2022
Article in press: October 27, 2022
Published online: November 15, 2022
Research background

Yunnan province has a high prevalence of diabetic retinopathy (DR). Accordingly, it is of great significance to explore the DR-related factors and to construct an economic and intuitive clinical prediction model.

Research motivation

The research motivation is early intervention using the DR-related risk factors from the perspective of a predictive model to reduce the prevalence of DR in patients with type 2 diabetes mellitus (T2DM).

Research objectives

The research intends to establish a prediction model that allows clinically early prevention and treatment of DR.

Research methods

A total of 1654 Han population with T2DM were recruited in this study and were grouped in the without DR and DR groups. The DR group was further subgrouped according to the severity of DR. Then, univariate analysis, logistic regression analysis, and clinical decision tree models of clinical data were performed.

Research results

Based on the decision tree model constructed in this study, DR classification outcomes were obtained by evaluating diabetes duration followed by stages of chronic kidney disease, supine systolic blood pressure (SBP), standing SBP, and body mass index.

Research conclusions

Personalized interventions for DR-related risk factors based on a decision tree model may potentially reduce the prevalence of DR.

Research perspectives

In this study, patients with T2DM in Western China were taken as samples to analyze the influencing factors of DR and build a clinical prediction model. In the future, it is hoped that the prediction model can produce certain social and economic benefits in clinical practice. In addition, when comparing with other clinical studies on DR, we found some controversies, such as the impact of sex and body mass index on DR, which opened up a new direction for future research.