[1]左雨露,吴 宇,杨锦鹏,等.基于机器学习的血脂新特征构建及其在冠状动脉粥样硬化中的应用[J].医学信息,2024,37(01):29-34.[doi:10.3969/j.issn.1006-1959.2024.01.005]
　ZUO Yu-lu,WU Yu,YANG Jin-peng,et al.Construction of New Blood Lipid Features Based on Machine Learning and its Application in Coronary Atherosclerosis[J].Journal of Medical Information,2024,37(01):29-34.[doi:10.3969/j.issn.1006-1959.2024.01.005]
点击复制

基于机器学习的血脂新特征构建及其在冠状动脉粥样硬化中的应用()
分享到：

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
37卷
期数:
2024年01期
页码:
29-34
栏目:
临床信息学
出版日期:
2024-01-01

文章信息/Info

Title:
Construction of New Blood Lipid Features Based on Machine Learning and its Application in Coronary Atherosclerosis
文章编号:
1006-1959（2024）01-0029-06
作者:
左雨露; 吴 宇; 杨锦鹏; 等
（惠州市中大惠亚医院心血管内科，广东 惠州 516081）
Author(s):
ZUO Yu-lu; WU Yu; YANG Jin-peng; et al.
(Department of Cardiovascular Internal Medicine,Huiya Hospital of the First Affiliated Hospital,Sun Yat-sen University,Huizhou 516081,Guangdong,China)
关键词:
机器学习; 随机森林模型; 血脂; 冠状动脉粥样硬化
Keywords:
Machine learning; Random forest model; Lipids; Coronary atherosclerosis
分类号:
R541.4
DOI:
10.3969/j.issn.1006-1959.2024.01.005
文献标志码:
A
摘要:
目的 运用机器学习模型分析血脂谱，构建血脂新特征，找到可以整合血脂谱的方法。方法 筛选我院2021年6月-2022年6月收治的冠状动脉粥样硬化患者68例，收集患者血脂谱中载脂蛋白B（ApoB）、非高密度脂蛋白胆固醇（N-HDL-C）、低密度脂蛋白胆固醇（LDL-C）、高密度脂蛋白胆固醇（HDL-C）、总胆固醇（TC）、甘油三酯（TG）、脂蛋白（a）Lp（a）数据，查看患者冠脉造影结果，采用改良的Gensini积分计算患者Gensini积分。根据血脂谱中各成分的关系，构建可解释的新特征-胆固醇指数。将患者随机分为训练集、测试集（3:1），运用随机森林模型，通过观察曲线下面积（AUC）、f1值、精准度、召回率、准确率来验证构建的胆固醇指数对严重冠状动脉粥样硬化的预测价值。结果 共收集68例冠状动脉粥样硬化患者，其中男48例，女20例，平均年龄（57.96±11.33）岁。训练集和测试集的年龄、TC、ApoB、N-HDL-C、LDL-C、HDL-C、TG、Lp（a）及胆固醇指数比较，差异无统计学意义（P＞0.05）。采用原始血脂谱，应用随机森林模型预测严重冠状动脉粥样硬化的AUC为0.64（95%CI：0.41~0.80）。纳入构建的新特征胆固醇指数=■/HDL-C可很大程度的提高随机森林模型的预测效果，其AUC为0.84（95%CI：0.57~0.93），且其f1值、精准度、召回率、准确率都有不同程度的提升，分别为0.83、1.00、0.71、0.88。结论 胆固醇指数可有效的整合胆固醇数据，提升随机森林模型对严重冠状动脉粥样硬化的预测效果。
Abstract:
Objective To analyze lipid profile and find a method that can integrate lipid profile using machine learning.Methods A total of 68 patients with coronary atherosclerosis admitted to our hospital from June 2021 to June 2022 were screened. Apolipoprotein B (ApoB), non-high-density lipoprotein cholesterol (N-HDL-C), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), total cholesterol (TC), triglyceride (TG), lipoprotein(a)Lp(a) data in the blood lipid profile of the patients were collected. The results of coronary angiography were reviewed, and the Gensini score of the patients was calculated by modified Gensini score. According to the relationship between the components in the blood lipid spectrum, an interpretable new feature-cholesterol index was constructed. The patients were randomly divided into training set and test set (3:1). The random forest model was used to verify the predictive value of the constructed cholesterol index for severe coronary atherosclerosis by observing the area under the curve (AUC), f1 value, accuracy, recall rate and accuracy rate.Results A total of 68 patients with coronary atherosclerosis were collected, including 48 males and 20 females, with an average age of (57.96±11.33) years. There was no significant difference in age, TC, ApoB, N-HDL-C, LDL-C, HDL-C, TG, Lp(a) and cholesterol index between the training set and the test set (P>0.05). Using the original lipid profile, the AUC of the random forest model for predicting severe coronary atherosclerosis was 0.64 (95%CI: 0.41-0.80). The prediction effect of the random forest model was greatly improved using new feature cholesterol index=■/HDL-C, and its AUC value was 0.84(95%CI:0.57-0.93), and f1 value, accuracy, recall rate, and accuracy are improved to varying degrees, which were 0.83, 1.00, 0.71, and 0.88, respectively.Conclusion Cholesterol index can effectively integrate cholesterol data and improve the prediction effect of random forest model on the severity of coronary atherosclerosis.

参考文献/References:

[1]Rampidis GP,Benetos G,Benz DC,et al.A guide for Gensini Score calculation[J].Atherosclerosis,2019,287:181-183.[2]中华医学会心血管病学分会,中国康复医学会心脏预防与康复专业委员会,中国老年学和老年医学会心脏专业委员会,等.中国心血管病一级预防指南[J].中华心血管病杂志,2020,48(12):1000-1038.[3]王增武,刘静,李建军,等.中国血脂管理指南（2023年）[J].中国循环杂志,2023,38(3):237-271.[4]Mach F,Baigent C,Catapano AL,et al.2019 ESC/EAS Guidelines for the management of dyslipidaemias: lipid modification to reduce cardiovascular risk[J].Eur Heart J,2020,41(1):111-188. [5]Visseren FLJ,Mach F,Smulders YM,et al.2021 ESC Guidelines on cardiovascular disease prevention in clinical practice[J].Eur Heart J,2021,42(34):3227-3337. [6]Wilson PWF,Jacobson TA,Martin SS,et al.Lipid measurements in the management of cardiovascular diseases: Practical recommendations a scientific statement from the national lipid association writing group[J].J Clin Lipidol,2021,15(5):629-648. [7]Ben-Aicha S,Badimon L,Vilahur G.Advances in HDL: Much More than Lipid Transporters[J].Int J Mol Sci,2020,21(3):732.[8]Aday AW,Lawler PR,Cook NR,et al.Lipoprotein Particle Profiles, Standard Lipids, and Peripheral Artery Disease Incidence[J].Circulation,2018,138(21):2330-2341. [9]Sniderman AD,Couture P,Martin SS,et al.Hypertriglyceridemia and cardiovascular risk: a cautionary note about metabolic confounding[J].J Lipid Res,2018,59(7):1266-1275. [10]Cantey EP,Wilkins JT.Discordance between lipoprotein particle number and cholesterol content: an update[J].Curr Opin Endocrinol Diabetes Obes,2018,25(2):130-136. [11]Allan D.Sniderman, Michael Pencina, George Thanassoulis, et al.ApoB:The Power of Physiology to Transform the Prevention of Cardiovascular Disease[J].Circulation Research,2019,124:1425-1427.[12]吴信辉,杨建敏,楼朝臣.载脂蛋白AⅠ/载脂蛋白B、可溶性糖基化终产物受体和几丁质酶-3样蛋白1与H型高血压患者冠状动脉病变程度的关系[J].中华高血压杂志,2022,30(10):985-989.[13]王宏宇,付茜,苏福祥.载脂蛋白B/载脂蛋白A1比值与急性冠脉综合征患者冠状动脉多支病变及斑块易损性的相关性[J].中国医科大学学报,2022,51(7):577-582.[14]Bi Q,Goodman KE,Kaminsky J,et al.What is Machine Learning? A Primer for the Epidemiologist[J].American Journal of Epidemiology,2019,188(12):2222-2239.[15]Madsen CM,Varbo A,Nordestgaard BG.Unmet need for primary prevention in individuals with hypertriglyceridaemia not eligible for statin therapy according to European Society of Cardiology/European Atherosclerosis Society guidelines: a contemporary population-based study[J].Eur Heart J,2018,39(7):610-619. [16]Bhatt DL,Steg PG,Miller M,et al.Cardiovascular Risk Reduction with Icosapent Ethyl for Hypertriglyceridemia[J].N Engl J Med,2019,380(1):11-22.[17]Marston NA,Giugliano RP,Im K,et al.Association Between Triglyceride Lowering and Reduction of Cardiovascular Risk Across Multiple Lipid-Lowering Therapeutic Classes: A Systematic Review and Meta-Regression Analysis of Randomized Controlled Trials[J].Circulation,2019,140(16):1308-1317. [18]Mehta A,Virani SS,Ayers CR,et al.Lipoprotein(a) and Family History Predict Cardiovascular Disease Risk[J].J Am Coll Cardiol,2020,76:781-793.[19]Burgess S,Ference BA,Staley JR,et al.Association of LPA Variants With Risk of Coronary Disease and the Implications for Lipoprotein(a)-Lowering Therapies:A Mendelian Randomization Analysis[J].JAMA Cardiol,2018,3(7):619-627. [20]Lamina C,Kronenberg F,Lp(a)-GWAS-Consortium.Estimation of the Required Lipoprotein(a)-Lowering Therapeutic Effect Size for Reduction in Coronary Heart Disease Outcomes:A Mendelian Randomization Analysis[J].JAMA Cardiol,2019,4(6):575-579. [21]Hu X,Cristino J,Gautam R,et al.Characteristics and lipid lowering treatment patterns in patients tested for lipoprotein(a): A real-world US study[J].Am J Prev Cardiol,2023,14:100476.

相似文献/References:

[1]周 阳,王 妮,黄艳群,等.基于社区居民健康大数据预测高血压的患病风险[J].医学信息,2020,33(06):1.[doi:10.3969/j.issn.1006-1959.2020.06.001]
　ZHOU Yang,WANG Ni,HUANG Yan-qun,et al.Risk of Hypertension Based on Big Data of Community Residents’ Health[J].Journal of Medical Information,2020,33(01):1.[doi:10.3969/j.issn.1006-1959.2020.06.001]
[2]朱 光,邓弘林.大数据背景下医院门诊挂号预约爽约行为预测研究[J].医学信息,2020,33(22):13.[doi:10.3969/j.issn.1006-1959.2020.22.004]
　ZHU Guang,DENG Hong-lin.An Investigation of Predicting Patient Missing Appointment Behavior Under the Big Data Background[J].Journal of Medical Information,2020,33(01):13.[doi:10.3969/j.issn.1006-1959.2020.22.004]
[3]李言生,龚后武,栗翊超,等.基于真实世界数据的疾病风险预测研究[J].医学信息,2020,33(23):17.[doi:10.3969/j.issn.1006-1959.2020.23.006]
　LI Yan-sheng,GONG Hou-wu,LI Yi-chao,et al.Research on Disease Risk Prediction Based on Real World Data[J].Journal of Medical Information,2020,33(01):17.[doi:10.3969/j.issn.1006-1959.2020.23.006]
[4]佟金铎,郭凤英,翟 兴,等.基于用户画像的患者就医影响因素研究[J].医学信息,2021,34(02):11.[doi:10.3969/j.issn.1006-1959.2021.02.004]
　TONG Jin-duo,GUO Feng-ying,ZHAI Xing,et al.Study on the Influencing Factors of Patient Medical Treatment Based on User Portrait[J].Journal of Medical Information,2021,34(01):11.[doi:10.3969/j.issn.1006-1959.2021.02.004]
[5]郑 阳.医疗人工智能的关键技术及应用[J].医学信息,2021,34(02):19.[doi:10.3969/j.issn.1006-1959.2021.02.006]
　ZHENG Yang.Key Technology and Application of Medical Artificial Intelligence[J].Journal of Medical Information,2021,34(01):19.[doi:10.3969/j.issn.1006-1959.2021.02.006]
[6]李 轩,王子为,赵靖萱,等.肿瘤预后预测领域机器学习应用的文献计量与热点可视化分析[J].医学信息,2022,35(09):90.[doi:10.3969/j.issn.1006-1959.2022.09.023]
　LI Xuan,WANG Zi-wei,ZHAO Jing-xuan,et al.Visualization Analysis on Bibliometrics and Hot Spots of Machine Learning Applications in the Field of Tumor Prognosis Prediction[J].Journal of Medical Information,2022,35(01):90.[doi:10.3969/j.issn.1006-1959.2022.09.023]
[7]富 坤,李佳宁.LncRNA-疾病关联预测方法研究[J].医学信息,2023,36(04):166.[doi:10.3969/j.issn.1006-1959.2023.04.036]
　FU Kun,LI Jia-ning.Research on LncRNA-disease Association Prediction Method[J].Journal of Medical Information,2023,36(01):166.[doi:10.3969/j.issn.1006-1959.2023.04.036]
[8]凌 天,焦 阳,狄碧云,等.面向机器学习的智慧诊疗语料库构建研究[J].医学信息,2023,36(10):6.[doi:10.3969/j.issn.1006-1959.2023.10.002]
　LING Tian,JIAO Yang,DI Bi-yun,et al.Research on the Construction of Intelligent Diagnosis and Treatment Corpus for Machine Learning[J].Journal of Medical Information,2023,36(01):6.[doi:10.3969/j.issn.1006-1959.2023.10.002]
[9]段永飞,高继学,倪建鑫,等.基于人工智能学习模型在结节性硬化症相关肾血管平滑肌脂肪瘤诊疗中的研究[J].医学信息,2023,36(11):171.[doi:10.3969/j.issn.1006-1959.2023.11.037]
　DUAN Yong-fei,GAO Ji-xue,NI Jian-xin,et al.Research on the Diagnosis and Treatment of Tuberous Sclerosis Complex-associated Renal Angiomyolipoma Based on Artificial Intelligence Learning Model[J].Journal of Medical Information,2023,36(01):171.[doi:10.3969/j.issn.1006-1959.2023.11.037]

更新日期/Last Update: 1900-01-01