糖尿病并发视网膜病变的关键影响因素分析和风险预测研究  

Analysis of key influencing factors and risk prediction of diabeticretinopathy

作　　者：武巾媛 安洪庆[1] WU Jin-yuan;AN Hong-qing(Weifang Medical College,Weifang,Shandong 261053,China)

机构地区：[1]潍坊医学院,山东潍坊261053

出　　处：《现代预防医学》2024年第3期557-563,共7页Modern Preventive Medicine

基　　金：中国学位与研究生教育学会课题(2020MSA105);中国高等教育学会2023年度课题(23PG0411);山东省高等医学教育研究中心规划课题(YJKT202126)。

摘　　要：目的 探究糖尿病并发视网膜病变(diabetic retinopathy,DR)的关键影响因素,进行发病现状分析,并构建发病风险预测模型。方法 基于“国家人口与健康科学数据共享平台”公布的“糖尿病并发症预警数据集”,利用单因素和多因素logistic回归分析得到DR发病关键影响因素;运用熵权法、优劣解距离法(technique for order preferenceby similarity to ideal solution,TOPSIS)、联合秩和比方法(rank-sum ratio,RSR)进行发病风险分层;分别构建logistic回归、随机森林、支持向量机模型,使用投票、平均、加权平均三种方法进行模型融合,对模型预测效果进行评估,取得最佳预测模型。结果最终提取年龄、高脂血等14个指标作为关键影响因素;分层结果显示未患DR的糖尿病患者中存在50人患病风险较高,约为82.99%,需要重点关注;投票器融合模型预测效果最佳(Acc:80.18%,F1:0.786 8)。结论 分析得到DR关键影响因素,提供了治疗与预防方向;进行发病风险现状分析,划分DR低中高风险人群,进行风险预警;通过模型间效果对比,构建DR发病风险预测模型,为其临床预警提供了数据分析思路与方法。Objective To explore the key influencing factors of diabetic retinopathy(DR),analyze the current situation of DR,and construct a risk prediction model.Methods Based on the diabetic complication early warning data set published by the national population and health science data sharing platform,the key influencing factors of DR were obtained by univariate and multivariate Logistic regression analyses.The entropy weighting method,the Technique for Order Preference by Similarity to Ideal Solution(TOPSIS),and the rank-sum ratio(RSR)were used to quantify the risk of DR development in patients and stratified into three levels:high,medium,and low.Logistic regression,random forest,and support vector machine models were constructed,respectively,and model fusion was performed using voting,averaging,and weighted averaging to evaluate the model predictive effect and obtain the best predictive model.Results Finally,14 indexes including age and hyperlipidemia were extracted as key influencing factors.The stratification results showed that there were 50 diabetic patients without DR in this data set with a risk of about 82.99%,which was a high-risk group for DR and needed more attention.The best prediction effect was obtained from the voting machine fusion model(Acc:80.18%,F1:0.7868).Conclusion The key influencing factors of DR are analyzed,providing the direction of treatment and prevention.The low,medium,and high-risk groups of DR are classified for risk early warning.By comparing the effect between the models,the prediction model of morbidity risk of DR is constructed,providing insights for clinical early warning and data analysis.

关 键 词：糖尿病视网膜病变 LOGISTIC TOPSIS RSR 预测模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] R587.2[自动化与计算机技术—控制科学与工程] R774.1[医药卫生—内分泌]