全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
-  2017 

基于 Relief 算法的心血管疾病辅助诊断研究

DOI: doi:10.7507/1001-5515.201609070

Keywords: 光电容积脉搏波, Relief 算法, 特征选择, k 邻近算法, 支持向量机

Full-Text   Cite this paper   Add to My Lib

Abstract:

本文研究了 Relief 特征选择方法在光电容积脉搏波(PPG)中的应用,分析寻找区分心血管疾病的指标,提出了一种辅助心血管疾病诊断的方法。通过收集 40 位志愿者的生理病理信息,并实时采集血压与指尖 PPG 波形数据,形成样本数据集。基于 PPG 波形,定义并提取了 52 个特征参数,通过特征选择 Relief 算法筛选出 10 个核心特征参数,形成最优特征子集,并分析它们对心血管疾病的影响。最后使用分类算法建模,对心血管疾病做出了辅助诊断,k 邻近算法(kNN)模型对心血管疾病的预测正确率达到 66.67%,支持向量机(SVM)模型对心血管疾病的预测正确率达到 83.33%。结果表明:① 年龄对心血管疾病辅助诊断最为重要;② 最优特征子集元素特征为心血管健康状况评价与预测提供了重要依据。本研究表明,经 Relief 算法选择得到的最优特征子集为心血管疾病辅助诊断提供了更高的准确性

References

[1]  5. Sherebrin M H, Sherebrin R Z. Frequency analysis of the peripheral pulse wave detected in the finger with a photoplethysmograph. IEEE Trans Biomed Eng, 1990, 37(3): 313-317.
[2]  8. Takazawa K, Tanaka N, Fujita M, et al. Assessment of vasoactive agents and vascular aging by the second derivative of photoplethysmogram waveform. Hypertension, 1998, 32(2): 365-370.
[3]  9. Elgendi M. Detection of c, d, and e waves in the acceleration photoplethysmogram. Comput Methods Programs Biomed, 2014, 117(2): 125-136.
[4]  10. Elgendi M, Fletcher R R, Norton I, et al. Frequency analysis of photoplethysmogram and its derivative. Comput Methods Programs Biomed, 2015, 122(3): 503-512.
[5]  11. Fischer C, Domer B, Wibmer T, et al. An algorithm for real-time pulse waveform segmentation and artifact detection in photoplethysmograms. IEEE J Biomed Health Inform, 2017, 21(2): 372-381.
[6]  12. Narayana Dutt N, Shruthi S. Digital processing of ECG and PPG signals for study of arterial parameters for cardiovascular risk assessment//2015 International Conference On Communications And Signal Processing (ICCSP). Melmaruvathur: IEEE, 2015: 1506-1510.
[7]  13. Marcinkevics Z, Rubins U, Zaharans J, et al. Imaging photoplethysmography for clinical assessment of cutaneous microcirculation at two different depths. J Biomed Opt, 2016, 21(3): 35005.
[8]  14. Wu Jianxing, Li J M, Ho Y R, et al. Bilateral photoplethysmography analysis for peripheral arterial stenosis screening with a fractional-order integratorand info-gap decision-making. IEEE Sens J, 2016, 16(8): 2691-2700.
[9]  15. 石萍, 喻洪流. 光电容积描记技术原理及其应用. 生物医学工程学杂志, 2013, 30(4): 899-904.
[10]  17. 张丽新. 高维数据的特征选择及基于特征选择的集成学习研究. 北京: 清华大学, 2004.
[11]  18. 林智仁.LIBSVM--A Library for Support Vector Machines [DB/OL]. (2015-12-01) [2016-08-30]. http://www.csie.ntu.edu. tw/~cjlin/libsvm/index.html.
[12]  6. Allen J, Murray A. Age-related changes in peripheral pulse shape characteristics at various body sites Physiol. Physiol Meas, 2003, 24(2): 297-307.
[13]  1. 罗志昌, 张松, 杨益民. 脉搏波的工程分析与临床应用. 北京: 科学出版社, 2006.
[14]  2. Wu H T, Lin Boyi, Yang Chengchan, et al. Assessment of vascular health with photoplethysmographic waveforms from the fingertip. IEEE J Biomed Health Inform, 2017, 21(2): 382-386.
[15]  3. Kiselev A R, Mironov S A, Karavaev A S, et al. A comprehensive assessment of cardiovascular autonomic control using photoplethysmograms recorded from the earlobe and fingers. Physiol Meas, 2016, 37(4): 580-595.
[16]  4. Allen J. Photoplethysmography and its application in clinical physiological measurement. Physiol Meas, 2007, 28(3): R1-39.
[17]  7. Allen J, Overbeck K, Stansby G, et al. Photoplethysmography assessments in cardiovascular disease. Measurement & Control, 2006, 39(3): 80-83.
[18]  16. 李章俊, 王成, 朱浩, 等. 基于光电容积脉搏波描记法的无创连续血压测量. 中国生物医学工程学报, 2012, 31(4): 607-614.
[19]  19. 李霞, 张田文, 李丽, 等. 决策树特征基因选择方法对 SVM 有效性的研究. 中国生物医学工程学报, 2004, 23(1): 66-72.
[20]  20. 蒋帅. 基于 AUC 的分类器性能评估问题研究. 长春: 吉林大学, 2016.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133