Research progress on prediction models for type 2 diabetes mellitus
WANG Yingjie1, SUN Gaofeng2
1. School of Public Health, Xinjiang Medical University, Urumqi, Xinjiang 830054, China; 2. Urumqi Center for Disease Control and Prevention (Urumqi Health Supervision Institute), Urumqi, Xinjiang 830026, China
摘要2型糖尿病（T2DM）发病率不断上升,严重影响生命健康、增加医疗负担。随着医学大数据和人工智能的不断发展,基于遗传信息、健康档案和实验室检测数据等多维度资料,应用机器学习方法构建T2DM及其并发症预测模型的研究增多,为T2DM防控提供了新思路和手段。本文通过检索中国知网、Web of Science和PubMed等数据库收集2003—2024年国内外关于T2DM及其并发症预测模型的文献,对T2DM风险相关预测模型的研究进行综述,了解T2DM预测模型分类、构建方法和应用,为T2DM早期筛查及干预提供参考。
Abstract：The incidence of type 2 diabetes mellitus (T2DM) has been continuously rising, severely impacting health and increasing the medical burden. With the development of medical big data and artificial intelligence, research into constructing T2DM and its complications prediction models using machine learning methods based on multidimensional data such as genetic information, health records and laboratory testing data have increased, providing new ideas and means for the prevention and control of T2DM. This article reviewed the research progress in prediction models related to the risk of T2DM to understand the classification, modeling methods and applications by retrieving literature on T2DM and its complications prediction models from domestic and international databases including CNKI, Web of Science, and PubMed from 2003 to 2024, so as to provide the reference for early screening and intervention of T2DM.
王英杰 综述, 孙高峰, 审校. 2型糖尿病预测模型研究进展[J]. 预防医学, 2025, 37(4): 369-372,377.
WANG Yingjie, SUN Gaofeng. Research progress on prediction models for type 2 diabetes mellitus. Preventive Medicine, 2025, 37(4): 369-372,377.
[1] AHMAD E,LIM S,LAMPTEY R,et al.Type 2 diabetes[J].Lancet,2022,400(10365):1803-1820. [2] 武亚星,刘宏,冯剑,等.2型糖尿病患者微血管并发症的影响因素分析[J].预防医学,2023,35(11):926-930. WU Y X,LIU H,FENG J,et al.Factors affecting microvascular complications among patients with type 2 diabetes mellitus[J].China Prev Med J,2023,35(11):926-930.(in Chinese) [3] LINDSTROM J,TUOMILEHTO J.The diabetes risk score:a practical tool to predict type 2 diabetes risk[J].Diabetes Care,2003,26(3):725-731. [4] 郑帅印,李丽丹,陈佩弟,等.2型糖尿病合并非酒精性脂肪肝的预测模型研究[J].预防医学,2024,36(9):741-745,749. ZHENG S Y,LI L D,CHEN P D,et al.Prediction of non-alcoholic fatty liver in patients with type 2 diabetes mellitus[J].China Prev Med J,2024,36(9):741-745,749.(in Chinese) [5] KU G M V,KEGELS G.The performance of the Finnish Diabetes Risk Score,a modified Finnish Diabetes Risk Score and a simplified Finnish Diabetes Risk Score in community-based cross-sectional screening of undiagnosed type 2 diabetes in the Philippines[J].Prim Care Diabetes,2013,7(4):249-259. [6] BUIJSSE B,SIMMONS R K,GRIFFIN S J,et al.Risk assessment tools for identifying individuals at risk of developing type 2 diabetes[J].Epidemiol Rev,2011,33(1):46-62. [7] 董建军,娄能俊,辛颖,等.不同糖尿病筛查问卷在中国人群糖尿病普查中的价值评估[J].中华内分泌代谢杂志,2009,25(1):64-65. DONG J J,LOU N J,XIN Y,et al.Evaluation of various questionnaires for screening diabetes mellitus in Chinese population[J].Chin J Endocrinol Metab,2009,25(1):64-65.(in Chinese) [8] WANG A X,CHEN G J,SU Z P,et al.Risk scores for predicting incidence of type 2 diabetes in the Chinese population:the Kailuan prospective study[J/OL].Sci Rep,2016,6(1)[2025-01-31].https://doi.org/10.1038/srep26548. [9] CARTER J A,LONG C S,SMITH B P,et al.Combining elemental analysis of toenails and machine learning techniques as a non-invasive diagnostic tool for the robust classification of type-2 diabetes[J].Expert Syst Appl,2019,115:245-255. [10] SAMANT P,AGARWAL R.Machine learning techniques for medical diagnosis of diabetes using iris images[J].Comput Methods Programs Biomed,2018,157:121-128. [11] 苏银霞,卢耀勤,田翔华,等.基于常规体检指标的2型糖尿病风险预测研究进展[J].预防医学,2022,34(12):1230-1234. SU Y X,LU Y Q,TIAN X H,et al.Research progress on risk prediction of type 2 diabetes mellitus based on routine physical examination indicators[J].China Prev Med J,2022,34(12):1230-1234.(in Chinese) [12] ALBARQOUNI L,DOUST J A,MAGLIANO D,et al.External validation and comparison of four cardiovascular risk prediction models with data from the Australian Diabetes,Obesity and Lifestyle study[J].Med J Aust,2019,210(4):161-167. [13] MASHAYEKHI M,PRESCOD F,SHAH B,et al.Evaluating the performance of the Framingham Diabetes Risk Scoring Model in Canadian electronic medical records[J].Can J Diabetes,2015,39(2):152-156. [14] 米生权. 中国成人个体糖尿病发病风险预测模型的建立及验证[D].北京:中国疾病预防控制中心,2011. MI S Q.Establishing and validating of type 2 diabetes incident prediction model of Chinese adult at individual level[D].Beijing:Chinese Center for Disease Control and Prevention,2011.(in Chinese) [15] XING Y L,LIU J,GAO Y,et al.Stronger associations of TyG index with diabetes than TyG-obesity-related parameters:more pronounced in young,middle-aged,and women[J].Diabetes Metab Syndr Obes,2023,16:3795-3805. [16] WANG Y K,ZHANG L Y,NIU M M,et al.Genetic risk score increased discriminant efficiency of predictive models for type 2 diabetes mellitus using machine learning:cohort study[J/OL].Front Public Health,2021,9[2025-01-31].https://doi.org/10.3389/fpubh.2021.606711. [17] AASMETS O,LÜLL K,LANG J M,et al.Machine learning reveals time-varying microbial predictors with complex effects on glucose regulation[J/OL].mSystems,2021,6[2025-01-31].https://doi.org/10.1128/mSystems.01191-20. [18] LIU J,WANG L,QIAN Y,et al.Metabolic and genetic markers improve prediction of incident type 2 diabetes:a nested case-control study in Chinese[J].J Clin Endocrinol Metab,2022,107(11):3120-3127. [19] GENUTH S.The UKPDS and its global impact[J].Diabet Med,2008,25(Suppl. 2):57-62. [20] HAYES A J,LEAL J,GRAY A M,et al.UKPDS outcomes model 2:a new version of a model to simulate lifetime health outcomes of patients with type 2 diabetes mellitus using data from the 30 year United Kingdom Prospective Diabetes Study:UKPDS 82[J].Diabetologia,2013,56(9):1925-1933. [21] BASU S,SUSSMAN J B,BERKOWITZ S A,et al.Development and validation of Risk Equations for Complications Of type 2 Diabetes(RECODe)using individual participant data from randomised trials[J].Lancet Diabetes Endocrinol,2017,5(10):788-798. [22] LIU Q,ZHANG M,HE Y F,et al.Predicting the risk of incident type 2 diabetes mellitus in Chinese elderly using machine learning techniques[J/OL].J Pers Med,2022,12(6)[2025-01-31].https://doi.org/10.3390/jpm12060905. [23] KHAN A,KHAN A,KHAN M M,et al.Cardiovascular and diabetes diseases classification using ensemble stacking classifiers with SVM as a meta classifier[J/OL].Diagnostics,2022,12(11)[2025-01-31].https://doi.org/10.3390/diagnostics12112595. [24] ROY K,AHMAD M,WAQAR K,et al.An enhanced machine learning framework for type 2 diabetes classification using imbalanced data with missing values[J/OL].Complexity,2021[2025-01-31].https://doi.org/10.1155/2021/9953314. [25] GOYAL M,REEVES N D,DAVISON A K,et al.Dfunet:convolutional neural networks for diabetic foot ulcer classification[J].IEEE Trans Emerg Top Comput Intell,2018,4(5):728-739. [26] OLISAH C C,SMITH L,SMITH M.Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective[J/OL].Comput Methods Programs Biomed,2022,220[2025-01-31].https://doi.org/10.1016/j.cmpb.2022.106773. [27] 袁翠杰,孙高峰,王一彤,等.2015年—2019年某市糖尿病患者死亡特征[J].中国病案,2022,23(5):64-67. YUAN C J,SUN G F,WANG Y T,et al.Analysis on the death characteristics of diabetic patients in a city from 2015 to 2019[J].Chin Med Rec,2022,23(5):64-67.(in Chinese) [28] 徐楠,王梅,刘晓东,等.应用Markov模型预测长期管理社区糖尿病患者队列心脑血管并发症转归研究[J].中国公共卫生管理,2021,37(1):45-49. XU N,WANG M,LIU X D,et al.Application of Markov model in prediction of the outcome of cardiovascular and cerebrovascular complications in long-termmanaged community diabetic patients[J].Chin J of PHM,2021,37(1):45-49.(in Chinese) [29] XUE M Y,SU Y X,LI C,et al.Identification of potential typeⅡdiabetes in a large-scale Chinese population using a systematic machine learning framework[J/OL].J Diabetes Res,2020[2025-01-31].https://doi.org/10.1155/2020/6873891. [30] 杨建宁,洪豆豆,李杨,等.甘肃省不同地区糖尿病肾脏疾病的机器学习预测模型的研究[J].中国糖尿病杂志,2025,33(1):8-15. YANG J N,HONG D D,LI Y,et al.Machine learning prediction model of diabetic kidney disease in different regions of Gansu province[J].Chin J Diabetes,2025,33(1):8-15.(in Chinese) [31] HIPPISLEY-COX J,COUPLAND C.Development and validation of risk prediction equations to estimate future risk of blindness and lower limb amputation in patients with diabetes:cohort study[J/OL].BMJ,2015,351[2025-01-31].https://doi.org/10.1136/bmj.h5441. [32] RAVAUT M,HARISH V,SADEGHI H,et al.Development and validation of a machine learning model using administrative health data to predict onset of type 2 diabetes[J/OL].JAMA Netw Open,2021,4(5)[2025-01-31].https://doi.org/10.1001/jamanetworkopen.2021.11315. [33] LUGNER M,RAWSHANI A,HELLERYD E,et al.Identifying top ten predictors of type 2 diabetes through machine learning analysis of UK Biobank data[J].Sci Rep,2024,14(1):1-9. [34] ALLEN A,IQBAL Z,GREEN-SAXENA A,et al.Prediction of diabetic kidney disease with machine learning algorithms,upon the initial diagnosis of type 2 diabetes mellitus[J].BMJ Open Diabetes Res Care,2022,10(1):1-7. [35] MAKINO M,YOSHIMOTO R,ONO M,et al.Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning[J].Sci Rep,2019,9(1):1-9. [36] ZHAO Y D,LI X Y,LI S,et al.Using machine learning techniques to develop risk prediction models for the risk of incident diabetic retinopathy among patients with type 2 diabetes mellitus:a cohort study[J/OL].Front Endocriol,2022,13[2025-01-31].https://doi.org/10.3389/fendo.2022.876559. [37] 张海燕,王宁,刘静.社区老年糖尿病患者低血糖风险评估模型的建立及应用价值分析[J].中国医师杂志,2019,21(2):247-250. ZHANG H Y,WANG N,LIU J.Establishment of hypoglycemia risk assessment model for elderly diabetic patients in community and its application value analysis[J].J Chin Physician,2019,21(2):247-250.(in Chinese)
