Please wait a minute...
文章检索
预防医学  2022, Vol. 34 Issue (9): 923-927    DOI: 10.19485/j.cnki.issn2096-5087.2022.09.012
  疾病控制 本期目录 | 过刊浏览 | 高级检索 |
应用TreeNet算法建立原发性高血压早期预测模型
郁小红, 钱棪梅, 周晨洁, 马越, 唐艳超, 邹玲莉
空军杭州特勤疗养中心疗养三区,浙江 杭州 310002
Establishment of a TreeNet algorithm-based model for early prediction of essential hypertension
YU Xiaohong, QIAN Yanmei, ZHOU Chenjie, MA Yue, TANG Yanchao, ZOU Lingli
The Third Sanatorium Department, Air Force Special Service Sanatorium, Hangzhou, Zhejiang 310002, China
全文: PDF(1007 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 目的 应用TreeNet算法建立原发性高血压(EH)早期预测模型,为早期监测EH提供预测方法。方法 收集2014—2016年均在杭州海勤体检中心或上海亿保健康管理公司进行健康体检者的体检资料,采用TreeNet算法建立EH预测模型;采用均方根误差(RMSE)、平均绝对偏差(MAD)和决定系数(R2)评价模型特异度,绘制受试者操作特征(ROC)曲线,评价模型预测效果。结果 共收集4 265人的体检资料,其中EH 224例,占5.25%。共纳入12个关联指标,按重要性由大到小依次为2015年体质指数(BMI)、BMI 2014与2015年差值(差值)、三酰甘油(TG)差值、2015年总胆固醇(TC)、2014年高密度脂蛋白胆固醇(HDL-C)、2014年TG、2014年低密度脂蛋白胆固醇、2015年体重、2014年空腹血糖、2015年TG、尿素氮差值和2015年血小板,预测精度最高为100.00%,最低为56.89%。当2015年BMI>25 kg/m2、BMI差值>0.5 kg/m2、TG差值为1.3~3.3 mmol/L、2015年TC为2.0~2.4 mmol/L、2014年HDL-C<0.52 mmol/L时,2016年EH发病概率显著升高。预测RMSE为0.082,MAD为0.064,R2为0.811,ROC曲线下面积为0.788(95%CI:0.741~0.815),灵敏度为69.05%,特异度为66.21%。结论 应用TreeNet算法建立的EH预测模型有助于早期评价高风险个体。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
郁小红
钱棪梅
周晨洁
马越
唐艳超
邹玲莉
关键词 原发性高血压TreeNet算法数据挖掘预测模型    
AbstractObjective To create a model for early prediction of essential hypertension (EH) based on the TreeNet algorithm, so as to provide a tool for early monitoring of EH. Methods The health examination data were collected from individuals receiving health examinations in Hangzhou Haiqin Health Examination Center or Shanghai Yibao Health Management Co., Ltd from 2014 to 2016, and a predictive model for EH was created based on the TreeNet algorithm. The effectiveness of the model for early prediction of EH was evaluated using root mean square error (RMSE), mean absolute deviation (MAD), coefficient of determination (R2) and receiver operating characteristic (ROC) curve. Results A total of 4 264 healthy examination data were collected, and the prevalence of EH was 5.25% among the participants. A total of 12 variables were included in the model, and the highest contributing variable was body mass index (BMI), followed by BMI difference, two-year BMI difference, two-year triglyceride (TG) difference, two-year total cholesterol (TC) difference, high-density lipoprotein cholesterol (HDL-C) in 2014, TG in 2014, low-density lipoprotein cholesterol (LDL-C) in 2014, body weight in 2015, fasting blood glucose in 2015, TG in 2015, urea nitrogen difference and platelet in 2015. The highest predictive accuracy was 100.00%, and the lowest was 56.89%. The risk of EH significantly increased among individuals with BMI in 2015 of >25 kg/m2, two-year BMI difference of >0.5 kg/m2, two-year TG difference ranging from 1.3 to 3.3 mmol/L, TC in 2015 of 2.0 to 2.4 mmol/L and HDL-C in 2014 of <0.52 mmol/L. The model presented RMSE of 0.082, MAD of 0.064, R2 of 0.811, area under the ROC curve of 0.788 (95%CI: 0.741-0.815), sensitivity of 69.05% and specificity of 66.21% for prediction of EH. Conclusion The TreeNet algorithm-based model is effective for early monitoring of high-risk individuals for EH.
Key wordsessential hypertension    TreeNet algorithm    data mining    predictive model
收稿日期: 2022-03-09      修回日期: 2022-07-08     
中图分类号:  R544.1  
通信作者: 邹玲莉,E-mail:575723407@qq.com   
作者简介: 郁小红,本科,副主任护师,主要从事健康管理和疗养工作
引用本文:   
郁小红, 钱棪梅, 周晨洁, 马越, 唐艳超, 邹玲莉. 应用TreeNet算法建立原发性高血压早期预测模型[J]. 预防医学, 2022, 34(9): 923-927.
YU Xiaohong, QIAN Yanmei, ZHOU Chenjie, MA Yue, TANG Yanchao, ZOU Lingli. Establishment of a TreeNet algorithm-based model for early prediction of essential hypertension. Preventive Medicine, 2022, 34(9): 923-927.
链接本文:  
http://www.zjyfyxzz.com/CN/10.19485/j.cnki.issn2096-5087.2022.09.012      或      http://www.zjyfyxzz.com/CN/Y2022/V34/I9/923
[1] 赵冬. 中国成人高血压流行病学现状[J].中国心血管杂志,2020,25(6):513-515.
ZHAO D.Current epidemiology of adult hypertension in China[J].Chin J Cardiovasc Med,2020,25(6):513-515.
[2] 李禄伟,黄倩,施佳成,等.基于三种统计学方法构建的超重及肥胖人群高血压发病预测模型的分析比较[J].现代预防医学,2021,48(11):2061-2065.
LI L W,HUANG Q,SHI J C,et al.Screening risk factors and interaction analysis of hypertension in overweight and obesity population based on three statistical models[J].Mod Prev Med,2021,48(11):2061-2065.
[3] 王定坤,杨杉.基于COX比例风险模型分析心力衰竭影响因素[J].电脑知识与技术(学术版),2021,17(24):33-35.
WANG D K,YANG S.Analysis of influencing factors for heart failure based on COX proportional hazard model[J].Comput Knowl Technol,2021,17(24):33-35.
[4] 付菲,彭映辉,徐肇元,等.急性心肌梗死患者心力衰竭风险预测模型研究[J].中国心血管杂志,2021,26(6):525-530.
FU F,PENG Y H,XU Z Y,et al.Study on risk prediction model of heart failure in patients with acute myocardial infarction[J].Chin J Cardiovasc Med,2021,26(6):525-530.
[5] 刘仕俊,袁寒艳,姜彩霞,等.杭州市老年高血压患者血压控制的影响因素研究[J].预防医学,2021,33(7):660-664.
LIU S J,YUAN H Y,JIANG C X,et al.Influencing factors for blood pressure control in elderly patients with hypertension in Hangzhou[J].Prev Med,2021,33(7):660-664.
[6] PADMAJA B,RAMA PRASAD V V,SUNITHA V N.TreeNet analysis of human stress behavior using socio-mobile data[J/OL].J Big Data,2016,4(1)[2022-07-08].https://doi.org/10.1186/s40537-016-0054-3.
[7] 中国高血压防治指南修订委员会,高血压联盟(中国),中华医学会心血管病学分会,等.中国高血压防治指南(2018年修订版)[J].中国心血管杂志,2019,24(1):24-56.
Writing Group of 2018 Chinese Guidelines for the Management of Hypertension,Chinese Hypertension League,Chinese Society of Cardiology,et al.2018 Chinese guidelines for the management of hypertension[J].Chin J Cardiovasc Med,2019,24(1):24-56.
[8] 张宇宁,郑浩,梁洁,等.老年人体重指数与血压水平及高血压患病率的相关性[J].中国老年学杂志,2021,41(20):4333-4335.
ZHANG Y N,ZHENG H,LIANG J,et al.Relationship between aged people body mass index and blood pressure and prevalence rate of hypertension[J].Chin J Gerontol,2021,41(20):4333-4335.
[9] 高仲淳,邹波,蓝恭赛,等.20~59岁成年人体质指数随年龄变化轨迹与高血压发病的关系研究[J].中国全科医学,2021,24(8):954-958.
GAO Z C,ZOU B,LAN G S,et al.The relationship between trajectory of body mass index based on age and the incidence of hypertension in adults aged 20 to 59 years[J].Chin Gen Pract,2021,24(8):954-958.
[10] KAMPMANN U,MATHIASSEN O N,CHRISTENSEN K L,et al.Effects of renal denervation on insulin sensitivity and inflammatory markers in nondiabetic patients with treatment-resistant hypertension[J/OL].J Diabetes Res,2017[2022-07-08].https://doi.org/10.1155/2017/6915310.
[11] D'ELIA L,STRAZZULLO P.Excess body weight,insulin resistance and isolated systolic hypertension:potential pathophysiological links[J].High Blood Press Cardiovasc Prev,2017,25(7):1377-1389.
[12] TAHERI A,MIRZABABAEI A,SETAYESH L,et al.The relationship between Dietary approaches to stop hypertension diet adherence and inflammatory factors and insulin resistance in overweight and obese women:a cross-sectional study[J/OL].Diabetes Res Clin Pract,2021,182[2022-07-08].https://doi.org/10.1016/j.diabres.2021.109128.
[13] RAJAMANI A,BORKOWSKI K,AKRE S,et al.Oxylipins in triglyceride-rich lipoproteins of dyslipidemic subjects promote endothelial inflammation following a high fat meal[J/OL].Sci Rep,2019,9(1)[2022-07-08].https://doi.org/10.1038/s41598-019-45005-5.
[14] 丁存涛,周亚群,孙希鹏,等.糖脂代谢对原发性高血压病人血管内皮功能的影响[J].首都医科大学学报,2017,38(3):401-405.
DING C T,ZHOU Y Q,SUN X P,et al.Effects of glucose and lipid metabolism on vascular endothelial function in patients with essential hypertension[J].J Cap Med Univ,2017,38(3):401-405.
[15] LANDI F,MARTONE A M,SALINI S,et al.Effects of a new combination of medical food on endothelial function and lipid profile in dyslipidemic subjects:a pilot randomized trial[J/OL].Biomed Res Int,2019(6)[2022-07-08].https://doi.org/10.1155/2019/1970878.
[16] DJINDJIĆ B,RADOVANOVIĆZ L,KOSTIĆ T,et al.The changes of oxidative stress and endothelial function biomarkers after 6 weeks of aerobic physical training in patients with stable ischemic coronary disease[J].Mil Med Pharm J Serbia,2017,74(11):1060-1065.
[1] 何亚盛, 张红霞, 倪银, 朱越燕, 彭敏, 杨丹红. 急诊重症监护病房住院患者医院感染的预测模型研究[J]. 预防医学, 2022, 34(9): 919-922.
[2] 王迎丹, 高春洁, 王蕾. 5种时间序列模型预测肺结核发病比较[J]. 预防医学, 2022, 34(12): 1194-1200.
[3] 余璐华, 刘艳, 黄妙玲, 李俊彦, 郭倩, 满宠, 张天成. 我国原发性高血压患者血压控制微信干预效果评价的Meta分析[J]. 预防医学, 2019, 31(9): 891-896.
[4] 施明明,李娜,胡锦峰. 关联规则在社区居民常见慢性病关联性分析中的应用[J]. 预防医学, 2018, 30(8): 766-770.
[5] 李艳, 李镇武, 田艳. 原发性高血压患者全科家庭医生责任制管理效果分析[J]. 预防医学, 2018, 30(5): 505-507.
[6] 陈磊, 王芳, 李恒娜. 原发性高血压合并2型糖尿病的影响因素分析[J]. 预防医学, 2018, 30(2): 179-181.
[7] 邱旭君,范瑞 ,张莉娜,郝玲妹. AGTR1基因启动子区DNA甲基化与原发性高血压的相关性研究[J]. 预防医学, 2017, 29(3): 260-263.
[8] 俞志红, 朱利月, 周欢琴. 规律有氧运动对原发性高血压患者动脉弹性的影响[J]. 预防医学, 2016, 28(3): 240-243.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed