[1]李瑞平,朱俊杰.基于改进Borderline-Smote-GBDT的冠心病预测[J].中国医学物理学杂志,2023,40(10):1278-1284.[doi:DOI:10.3969/j.issn.1005-202X.2023.10.015]
　LI Ruiping,ZHU Junjie.Coronary heart disease prediction based on improved Borderline-Smote-GBDT[J].Chinese Journal of Medical Physics,2023,40(10):1278-1284.[doi:DOI:10.3969/j.issn.1005-202X.2023.10.015]
点击复制

基于改进Borderline-Smote-GBDT的冠心病预测()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第10期
页码:
1278-1284
栏目:
医学信号处理与医学仪器
出版日期:
2023-10-27

文章信息/Info

Title:
Coronary heart disease prediction based on improved Borderline-Smote-GBDT
文章编号:
1005-202X（2023）10-1278-07
作者:
李瑞平1; 朱俊杰2
1.河南理工大学电气工程与自动化学院， 河南 焦作 454003； 2.河南省煤矿装备智能检测与控制重点实验室， 河南 焦作 454003
Author(s):
LI Ruiping1;  ZHU Junjie2
1. School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China 2. Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment, Jiaozuo 454003, China
关键词:
冠心病; Borderline-Smote; 梯度提升树
Keywords:
Keywords: coronary heart disease Borderline-Smote gradient boosting decision tree
分类号:
R318；TP391
DOI:
DOI:10.3969/j.issn.1005-202X.2023.10.015
文献标志码:
A
摘要:
针对样本不平衡问题，提出一种基于欧氏距离改进的Borderline-Smote过采样算法。首先根据欧式距离判断少数类样本类别；然后根据边界上的少数类样本的k近邻数据找出线性直线，由同侧近邻数据判别是否为噪音；最后重新判别删除噪音的剩余少数类样本的类别，对边界少数类样本和密集的非边界区域的少数类样本过采样合成新样本。等磁场图和二维电流密度图中提取的心磁特征数据集经过改进Borderline-Smote过采样处理，结果表明改进Borderline-Smote-GBDT冠心病预测模型相比Borderline-Smote-GBDT模型准确率提高8.4%，精确率提高2.9%，召回率提高9.1%，AUC提高4.6%。此外，与逻辑回归、随机森林、k近邻、极端随机树模型对比发现，GBDT结果最优，改进Borderline-Smote-GBDT准确率、召回率、精确率、AUC分别为91.7%、91.7%、81.8%、87.1%，验证了该模型的可行性。
Abstract:
A Borderline-Smote oversampling algorithm which is improved based on the Euclidean distance is proposed to address the problem of sample imbalance. The category of minority class samples is determined according to the Euclidean distance. Then, the k nearest neighbor data of minority class samples on the boundary is used to find the linear straight-line, and the noise is removed after identifying whether it is the noise misrecognized as boundary samples based on the ipsilateral neighbor data. Finally, the category of the remaining minority class samples is re-determined, and new samples are synthesized through the oversampling for minority class samples on the boundary and those in the dense non-boundary region. The feature datasets extracted from the isomagnetic field map and the two-dimensional current density map are processed with the improved Borderline-Smote oversampling, and the results show that compared with Borderline-Smote-GBDT model, the improved Borderline-Smote-GBDT model for coronary heart disease prediction enhances the accuracy, precision, recall rate and AUC by 8.4%, 2.9%, 9.1%, and 4.6%, respectively. Through the comparison with logistic regression, random forest, k nearest neighbor and extremely randomized tree, it is found that GBDT performs best, and that improved Borderline-Smote-GBDT model has an accuracy, recall rate, precision and AUC of 91.7%, 91.7%, 81.8%, and 87.1%, respectively, which verifies the model feasibility.

相似文献/References:

[1]杨希立,龚连生,张健瑜.脂蛋白相关磷脂酶A2与iMAP血管内超声斑块特征的相关性[J].中国医学物理学杂志,2015,32(04):525.[doi:10.3969/j.issn.1005-202X.2015.04.016]
　[J].Chinese Journal of Medical Physics,2015,32(10):525.[doi:10.3969/j.issn.1005-202X.2015.04.016]
[2]张晔,尹亮,祁欣.体外超声震波治疗冠心病的能量传递过程及声场分布[J].中国医学物理学杂志,2015,32(06):826.[doi:doi:10.3969/j.issn.1005-202X.2015.06.014]
　[J].Chinese Journal of Medical Physics,2015,32(10):826.[doi:doi:10.3969/j.issn.1005-202X.2015.06.014]
[3]涂圣贤,田峰,姜永军,等. 血管内光学成像与血流的融合：冠心病介入诊疗评估新技术研制[J].中国医学物理学杂志,2016,33(12):1208.[doi:10.3969/j.issn.1005-202X.2016.12.005]
　[J].Chinese Journal of Medical Physics,2016,33(10):1208.[doi:10.3969/j.issn.1005-202X.2016.12.005]
[4]张爱华,靳冠军. 基于脉搏波传导时间变异性的冠心病识别方法[J].中国医学物理学杂志,2017,34(5):527.[doi:DOI:10.3969/j.issn.1005-202X.2017.05.018]
　[J].Chinese Journal of Medical Physics,2017,34(10):527.[doi:DOI:10.3969/j.issn.1005-202X.2017.05.018]
[5]黄红艳,吴碧君,崔楠,等. 三维斑点追踪成像对不同程度冠状动脉狭窄患者左心室局部功能评价及冠心病诊断价值分析[J].中国医学物理学杂志,2017,34(6):598.[doi:DOI:10.3969/j.issn.1005-202X.2017.06.012]
　[J].Chinese Journal of Medical Physics,2017,34(10):598.[doi:DOI:10.3969/j.issn.1005-202X.2017.06.012]
[6]冯慧,吴钟伟,刘超权.冠心病患者心率变异性指标与冠状动脉病变程度的关系[J].中国医学物理学杂志,2019,36(12):1472.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.021]
　FENG Hui,WU Zhongwei,LIU Chaoquan.Relationship between heart rate variability indexes and severity of coronary artery lesions in patients with coronary heart diseases[J].Chinese Journal of Medical Physics,2019,36(10):1472.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.021]
[7]文翠,赵新军,张震洪,等.冠心病患者心电图ST段改变与多排螺旋CT冠状动脉成像的关系分析[J].中国医学物理学杂志,2020,37(8):1035.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.018]
　WEN Cui,ZHAO Xinjun,ZHANG Zhenhong,et al.Relationships between ECG ST-segment changes and multi-slice spiral CT coronary angiography in patients with coronary heart disease[J].Chinese Journal of Medical Physics,2020,37(10):1035.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.018]
[8]张优,李静,李晖,等.冠脉CT与冠脉造影诊断心肌桥的临床价值比较[J].中国医学物理学杂志,2021,38(4):441.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.009]
　ZHANG You,LI Jing,LI Hui,et al.Comparison of clinical value of coronary CT and coronary angiography in diagnosis of myocardial bridge[J].Chinese Journal of Medical Physics,2021,38(10):441.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.009]
[9]李亮,钟元利,阮红,等.动态与常规心电图诊断冠心病心肌缺血、心律失常、心绞痛的比较分析[J].中国医学物理学杂志,2021,38(8):946.[doi:DOI:10.3969/j.issn.1005-202X.2021.08.005]
　LI Liang,ZHONG Yuanli,RUAN Hong,et al.Comparison of dynamic and routine electrocardiograms for diagnosing myocardial ischemia, arrhythmia and angina pectoris of coronary heart disease[J].Chinese Journal of Medical Physics,2021,38(10):946.[doi:DOI:10.3969/j.issn.1005-202X.2021.08.005]
[10]艾海明,董哲,葛静茹,等.超导心磁信号测量技术及冠心病筛查[J].中国医学物理学杂志,2024,41(10):1265.[doi:DOI:10.3969/j.issn.1005-202X.2024.10.011]
　AI Haiming,DONG Zhe,GE Jingru,et al.Superconducting magnetocardiography signal measurement technology and coronary heart disease screening[J].Chinese Journal of Medical Physics,2024,41(10):1265.[doi:DOI:10.3969/j.issn.1005-202X.2024.10.011]

备注/Memo

备注/Memo:
【收稿日期】2023-04-10 【基金项目】国家自然科学基金（61601173） 【作者简介】李瑞平，硕士，研究方向：交通信息处理与装置，E-mail: 1835507496@qq.com 【通信作者】朱俊杰，博士，讲师，研究方向：生物医学信号处理，E-mail: junjiezhu@hpu.edu.cn
更新日期/Last Update: 2023-10-27