代谢风险评分在2型糖尿病人群心血管结局预测中的应用

doi:10.6040/j.issn.1671-7554.0.2025.0119

摘要/Abstract

摘要： 目的识别2型糖尿病人群中分别与心肌梗死、心力衰竭和缺血性脑卒中相关的代谢物,进而构建代谢风险评分,并评价将代谢风险评分纳入传统临床模型是否能提高模型预测准确性。方法利用英国生物银行队列数据,应用多变量Cox比例风险回归模型筛选出分别与心肌梗死、心力衰竭和缺血性脑卒中相关的代谢物,并进行时间截断的敏感性分析。随后,基于LightGBM算法构建代谢风险评分,最后将评分纳入传统临床模型,进行模型评价。结果多变量Cox比例风险回归模型和时间截断的敏感性分析共发现了分别与心肌梗死、心力衰竭和缺血性脑卒中相关的119种、77种和12种代谢物,随后利用这些代谢物构建代谢风险评分。将构建的代谢风险评分纳入传统临床模型后,模型的预测性能显著提高,3种疾病的预测模型AUC提高到0.804、0.900和0.844,与仅利用传统临床模型相比,分别提高了0.145、0.198和0.188。此外,敏感性和特异性结果表明,这3个模型具有较高的预测准确性(敏感性:0.706、0.804、0.801;特异性:0.763、0.861、0.722),校准曲线和决策曲线同样显示模型具有较好的预测性能。结论将代谢风险评分纳入传统临床模型可以显著提高2型糖尿病人群心血管疾病的预测准确性。

关键词: 2型糖尿病, 心肌梗死, 心力衰竭, 缺血性脑卒中, LightGBM, 代谢风险评分, 预测模型

Abstract: Objective To identify metabolites associated with myocardial infarction, heart failure, and ischemic stroke respectively in a population with type 2 diabetes mellitus, thereby constructing a metabolomic risk score and evaluating whether incorporation of the metabolomic risk score into a traditional clinical model improves the models predictive accuracy. Methods Using data from the UK Biobank cohort, a multivariate Cox proportional risk regression model was applied to screen for metabolites associated with myocardial infarction, heart failure, and ischemic stroke, respectively, and a time-truncated sensitivity analysis was performed. Subsequently, metabolomic risk scores were constructed based on the LightGBM algorithm, and finally the scores were incorporated into traditional clinical models for model evaluation. Results Multivariate Cox proportional risk regression models and time-truncated sensitivity analyses identified a total of 119, 77, and 12 metabolites associated with myocardial infarction, heart failure, and ischemic stroke, respectively, and these metabolites were then used to construct metabolomic risk scores. Incorporation of the constructed metabolomic risk scores into traditional clinical models significantly improved model prediction performance, with model AUCs improving to 0.804, 0.900, and 0.844 for the three diseases respectively, and the improvements were 0.145, 0.198, and 0.188, compared to utilizing only traditional clinical models. In addition, the sensitivity and specificity results showed that the three models had high prediction accuracy(sensitivity: 0.706, 0.804, 0.801; specificity: 0.763, 0.861, 0.722), and the calibration curves and decision curves likewise showed that the models had good prediction performance. Conclusion Incorporation of metabolomic risk scores into traditional clinical models can significantly improve the predictive accuracy of cardiovascular disease in the type 2 diabetes mellitus population.

Key words: Type 2 diabetes mellitus, Myocardial infarction, Heart failure, Ischemic stroke, LightGBM, Metabolomic risk score, Predictive modeling

中图分类号:

R743.3

申路佳,逯天威,巩伟明,赵岩松,王淑康,袁中尚. 代谢风险评分在2型糖尿病人群心血管结局预测中的应用[J]. 山东大学学报 (医学版), 2025, 63(8): 69-78.

SHEN Lujia, LU Tianwei, GONG Weiming, ZHAO Yansong, WANG Shukang, YUAN Zhongshang. Application of metabolomic risk score in predicting cardiovascular outcomes in patients with type 2 diabetes mellitus[J]. Journal of Shandong University (Health Sciences), 2025, 63(8): 69-78.

参考文献

[1] Roth GA, Mensah GA, Johnson CO, et al. Global burden of cardiovascular diseases and risk factors, 1990—2019: update from the GBD 2019 study[J]. J Am Coll Cardiol, 2020, 76(25): 2982-3021.
[2] Collaboration ERF, Sarwar N, Gao P, et al. Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies[J]. Lancet, 2010, 375(9733): 2215-2222.
[3] Birkeland KI, Bodegard J, Eriksson JW, et al. Heart failure and chronic kidney disease manifestation and mortality risk associations in type 2 diabetes: a large multinational cohort study[J]. Diabetes Obes Metab, 2020, 22(9): 1607-1618.
[4] Maida CD, Daidone M, Pacinella G, et al. Diabetes and ischemic stroke: an old and new relationship an overview of the close interaction between these diseases[J]. Int J Mol Sci, 2022, 23(4): 2397. doi:10.3390/ijms23042397
[5] Jia RR, Wang Q, Huang HY, et al. Cardiovascular disease risk models and dementia or cognitive decline: a systematic review[J]. Front Aging Neurosci, 2023, 15: 1257367. doi:10.3389/fnagi.2023.1257367
[6] Khan SS, Matsushita K, Sang YY, et al. Development and validation of the American heart associations PREVENT equations[J]. Circulation, 2024, 149(6): 430-449.
[7] Khan SS, Coresh J, Pencina MJ, et al. Novel prediction equations for absolute risk assessment of total cardiovascular disease incorporating cardiovascular-kidney-metabolic health: a scientific statement from the American heart association[J]. Circulation, 2023, 148(24): 1982-2004.
[8] Dziopa K, Asselbergs FW, Gratton J, et al. Cardiovascular risk prediction in type 2 diabetes: a comparison of 22 risk scores in primary care settings[J]. Diabetologia, 2022, 65(4): 644-656.
[9] McGarrah RW, Crown SB, Zhang GF, et al. Cardiovascular metabolomics[J]. Circ Res, 2018, 122(9): 1238-1258.
[10] Xie RJ, Seum T, Sha S, et al. Improving 10-year cardiovascular risk prediction in patients with type 2 diabetes with metabolomics[J]. Cardiovasc Diabetol, 2025, 24(1): 18. doi:10.1186/s12933-025-02581-3
[11] Huang Z, Klaric L, Krasauskaite J, et al. Combining serum metabolomic profiles with traditional risk factors improves 10-year cardiovascular risk prediction in people with type 2 diabetes[J]. Eur J Prev Cardiol, 2023, 30(12): 1255-1262.
[12] Sudlow C, Gallacher J, Allen N, et al. UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age[J]. PLoS Med, 2015, 12(3): e1001779. doi:10.1371/journal.pmed.1001779
[13] Ritchie SC, Surendran P, Karthikeyan S, et al. Quality control and removal of technical variation of NMR metabolic biomarker data in ~120, 000 UK Biobank participants[J]. Sci Data, 2023, 10(1): 64. doi:10.1038/s41597-023-01949-y
[14] Inker LA, Eneanya ND, Coresh J, et al. New creatinine- and cystatin C-based equations to estimate GFR without race[J]. N Engl J Med, 2021, 385(19): 1737-1749.
[15] Qiang YX, You J, He XY, et al. Plasma metabolic profiles predict future dementia and dementia subtypes: a prospective analysis of 274, 160 participants[J]. Alzheimers Res Ther, 2024, 16(1): 16. doi:10.1186/s13195-023-01379-3
[16] Zhang SY, Wang Z, Wang YJ, et al. A metabolomic profile of biological aging in 250, 341 individuals from the UK Biobank[J]. Nat Commun, 2024, 15(1): 8081. doi:10.1038/s41467-024-52310-9
[17] Julkunen H, Cichońska A, Tiainen M, et al. Atlas of plasma NMR biomarkers for health and disease in 118, 461 individuals from the UK Biobank[J]. Nat Commun, 2023, 14(1): 604. doi:10.1038/s41467-023-36231-7
[18] McGranaghan P, Saxena A, Rubens M, et al. Predictive value of metabolomic biomarkers for cardiovascular disease risk: a systematic review and meta-analysis[J]. Biomarkers, 2020, 25(2): 101-111.
[19] American Diabetes Association Professional Practice Committee. 10. Cardiovascular disease and risk management: standards of care in diabetes-2024[J]. Diabetes Care, 2024, 47(Suppl 1): S179-S218.
[20] SCORE2-Diabetes Working Group and the ESC Cardiovascular Risk Collaboration. SCORE2-diabetes: 10-year cardiovascular risk estimation in type 2 diabetes in Europe[J]. Eur Heart J, 2023, 44(28): 2544-2556.
[21] Arques S. Human serum albumin in cardiovascular diseases[J]. Eur J Intern Med, 2018, 52: 8-12. doi:10.1016/j.ejim.2018.04.014
[22] Nelson JJ, Liao D, Sharrett AR, et al. Serum albumin level as a predictor of incident coronary heart disease: the Atherosclerosis Risk in Communities(ARIC)study[J]. Am J Epidemiol, 2000, 151(5): 468-477.
[23] Gopal DM, Kalogeropoulos AP, Georgiopoulou VV, et al. Serum albumin concentration and heart failure risk The Health, Aging, and Body Composition Study[J]. Am Heart J, 2010, 160(2): 279-285.
[24] Filippatos GS, Desai RV, Ahmed MI, et al. Hypoalbuminaemia and incident heart failure in older adults[J]. Eur J Heart Fail, 2011, 13(10): 1078-1086.
[25] Xu WH, Dong CH, Rundek T, et al. Serum albumin levels are associated with cardioembolic and cryptogenic ischemic strokes: Northern Manhattan Study[J]. Stroke, 2014, 45(4): 973-978.
[26] Visseren FLJ, Mach F, Smulders YM, et al. 2021 ESC guidelines on cardiovascular disease prevention in clinical practice: developed by the task force for cardiovascular disease prevention in clinical practice with representatives of the European Society of Cardiology and 12 medical societies with the special contribution of the European Association of Preventive Cardiology(EAPC)[J]. Rev Esp Cardiol(Engl Ed), 2022, 75(5): 429. doi:10.1016/j.rec.2022.04.003
[27] Matsushita K, Kaptoge S, Hageman SHJ, et al. Including measures of chronic kidney disease to improve cardiovascular risk prediction by SCORE2 and SCORE2-OP[J]. Eur J Prev Cardiol, 2023, 30(1): 8-16.
[28] Camont L, John Chapman M, Kontush A. Biological activities of HDL subpopulations and their relevance to cardiovascular disease[J]. Trends Mol Med, 2011, 17(10): 594-603.
[29] Bocher O, Singh A, Huang Y, et al. Disentangling the consequences of type 2 diabetes on targeted metabolite profiles using causal inference and interaction QTL analyses[J]. PLoS Genet, 2024, 20(12): e1011346. doi:10.1371/journal.pgen.1011346
[30] Teis A, Cediel G, Amigó N, et al. Particle size and cholesterol content of circulating HDL correlate with cardiovascular death in chronic heart failure[J]. Sci Rep, 2021, 11(1): 3141. doi:10.1038/s41598-021-82861-6
[31] Liu Y, Jia SD, Yuan DS, et al. Apolipoprotein B/A-I ratio predicts lesion severity and clinical outcomes in diabetic patients with acute coronary syndrome[J]. Circ J, 2020, 84(7): 1132-1139.
[32] McQueen MJ, Hawken S, Wang XY, et al. Lipids, lipoproteins, and apolipoproteins as risk markers of myocardial infarction in 52 countries(the INTERHEART study): a case-control study[J]. Lancet, 2008, 372(9634): 224-233.
[33] Walldius G, Jungner I, Holme I, et al. High apolipoprotein B, low apolipoprotein A-I, and improvement in the prediction of fatal myocardial infarction(AMORIS study): a prospective study[J]. Lancet, 2001, 358(9298): 2026-2033.
[34] Fu C, Liu DB, Liu Q, et al. Revisiting an old relationship: the causal associations of the ApoB/ApoA1 ratio with cardiometabolic diseases and relative risk factors-a mendelian randomization analysis[J]. Cardiovasc Diabetol, 2024, 23(1): 51. doi:10.1186/s12933-024-02140-2

相关文章 15

[1]	徐宁宇王磊郝恩魁苏国海. STEMI患者急诊PCI前口服阿托伐他汀对炎症介质及左心室功能的影响[J]. 山东大学学报(医学版), 2209, 47(6): 69-72.
[2]	王建民,李晓峰,由志涛,董圣杰,赵宇驰,李占菊,邹德鑫,张剑锋,孙涛,杜伟. 基于可解释机器学习的后路腰椎椎体间融合术后慢性疼痛风险预测模型构建[J]. 山东大学学报 (医学版), 2026, 64(2): 78-88.
[3]	孙爽爽,仉率杰,张伯韬,袁莹,于媛媛,薛付忠. 基于真实世界研究的18~50岁人群急性缺血性卒中影响因素[J]. 山东大学学报 (医学版), 2025, 63(9): 40-46.
[4]	孟晓梅,郝亚平,王亮,于晓,唐与晓. 血清Isthmin1、Gremlin2水平与2型糖尿病患者视网膜病变的相关性[J]. 山东大学学报 (医学版), 2025, 63(9): 102-107.
[5]	陈莹莹,王鲁,胡锡峰,朱高培,薛付忠. 基于贝叶斯网络的2型糖尿病患者并发脑卒中风险预测[J]. 山东大学学报 (医学版), 2025, 63(8): 94-102.
[6]	河南省生物医学工程学会立体心电图专业委员会,中国医药教育协会心电学专业委员会,山东中医药学会心电学专业委员会,青岛市医学会心电生理与起搏专科分会,全国医药技术市场协会远程心脏专业委员会. 心电向量图诊断标准规范化专家共识(2025)[J]. 山东大学学报 (医学版), 2025, 63(7): 1-10.
[7]	贾魁,李治国,程翠婷,李志娟,刘瑞卿. 银杏叶片联合曲美他嗪治疗老年慢性心力衰竭的效果及机制[J]. 山东大学学报 (医学版), 2025, 63(6): 19-26.
[8]	王丽云,高天勤,刘雨佳,陈青,陈柳,沙凯辉. 基于机器学习产后压力性尿失禁风险预测模型的构建及验证[J]. 山东大学学报 (医学版), 2025, 63(6): 55-66.
[9]	温学龙,刘安慧,陈经纬,吴梦婷,杨岷. 急性非ST抬高型心肌梗死行冠状动脉旁路移植手术时机Meta分析[J]. 山东大学学报 (医学版), 2025, 63(5): 60-70.
[10]	陈瑛翼,游倩,王意,张帆,李凤,季舒铭,徐浩源,饶志勇. 办公室职员肌肉质量减少预测模型的开发与验证[J]. 山东大学学报 (医学版), 2025, 63(4): 26-35.
[11]	王宝炫,焦杰,张厚君,刘奇,于冠英. 衰弱与肌少症评估在胃肠道肿瘤术后结局预测中的应用与展望[J]. 山东大学学报 (医学版), 2025, 63(4): 51-58.
[12]	李敬,郝盼盼. 急性心力衰竭患者出入院心率变化与预后相关性[J]. 山东大学学报 (医学版), 2025, 63(4): 75-82.
[13]	宋思豪,程传龙,李树芬,席睿,梁珂梦,倪志松,崔峰,李秀君. 大气污染对淄博市缺血性脑卒中患者寿命损失年的短期影响及极端温度事件修饰效应[J]. 山东大学学报 (医学版), 2025, 63(2): 84-94.
[14]	刘文钊,张远,马湘萍,魏峰涛,卜培莉. 内皮活化和应激指数预测值与心力衰竭患者死亡风险的关联[J]. 山东大学学报 (医学版), 2025, 63(11): 27-35.
[15]	李永,崔书君,杨飞,张凡,殷晓霞. 基于增强MRI的亚区域影像组学模型可预测乳腺癌患者新辅助化疗后的病理完全反应[J]. 山东大学学报 (医学版), 2025, 63(1): 81-89.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed