支持向量回归在人体血红蛋白无创检测中的应用

引用本文: 袁境泽, 卢启鹏, 王静丽, 丁海泉, 高洪智, 吴春阳, 李晚侠. 支持向量回归在人体血红蛋白无创检测中的应用[J]. 分析化学, 2017, 45(9): 1291-1296. doi: 10.11895/j.issn.0253-3820.170090 shu

Citation: YUAN Jing-Ze, LU Qi-Peng, WANG Jing-Li, DING Hai-Quan, GAO Hong-Zhi, WU Chun-Yang, LI Wan-Xia. Support Vector Regression for Non-invasive Detection of Human Hemoglobin[J]. Chinese Journal of Analytical Chemistry, 2017, 45(9): 1291-1296. doi: 10.11895/j.issn.0253-3820.170090 shu

支持向量回归在人体血红蛋白无创检测中的应用

1.
中国科学院长春光学精密机械与物理研究所, 长春 130000;2 中国科学院大学, 北京 100049;3 吉林大学第一医院肿瘤中心, 长春 130021
基金项目:
本文系国家高技术研究发展计划（863计划）（No.2012AA022602）、国家自然科学基金（Nos.61308067，61475155）、吉林省科技发展计划项目（No.20140204078GX）和应用光学国家重点实验室基金资助项目

摘要: 采用线性渐变滤光片（Linear variable filter，LVF），优化设计高性能、便携式的人体血液成分近红外检测设备，研究了支持向量回归（Support vector regression，SVR）模型对人体血红蛋白（Hemoglobin，Hb）的预测能力及稳定性，以实现贫血疾病的无创诊断。无创采集100位志愿者食指前端光谱信息并划分定标集、验证集1和2。应用网格搜索方法优选惩罚参数与核函数参数c=5.28，g=0.33，用以建立稳健的SVR模型。随后，分别对验证集1和2中Hb水平进行定量分析。实验结果表明：预测标准偏差（RMSEP）分别为10.20 g/L和10.85 g/L，相对预测标准偏差（R-RMSEP）为6.85%和7.48%，测量精度较高且SVR模型对不同样品的适应性较强，基本满足临床检测要求。基于SVR算法自行设计的LVF型近红外光谱检测设备在贫血症的无创诊断中有着良好的应用前景。

关键词:

English

Support Vector Regression for Non-invasive Detection of Human Hemoglobin

1.
State Key Laboratory of Applied Optics, Changchun Institute of Optics, Fine Mechanics, and Physics, Chinese Academy of Sciences, Changchun 130033, China;2 University of Chinese Academy of Sciences, Beijing 100049, China;3 Cancer Center, The First Hospital of Jinlin University, Changchun 130021, China
Received Date: 16 February 2017
Revised Date: 10 August 2017
Fund Project:
This work was supported by the National High Technology Research and Development Program of China (No.2012AA022602) and the National Natural Science Foundation of China (Nos. 61308067, 61475155).

Abstract: To facilitate noninvasive diagnosis of anemia, high-performance and portable near infrared (NIR) spectrometer for human blood constituents was designed and fabricated based on linear variable filter (LVF). Meanwhile, the performance of support vector regression (SVR) model for quantitative analysis of human hemoglobin (Hb) was investigated. Spectral data were collected noninvasively from 100 volunteers by self-designed LVF-NIR spectrometer, then divided into calibration set, validation set 1 and 2. To establish a robust SVR model, grid search method was applied to optimize the penalty parameter and kernel function parameter c=5.28, g=0.33. Then, Hb levels in the validation 1 and 2 sets were quantitatively analyzed. The results showed that the root mean square error of prediction (RMSEP) were 10.20 g/L and 10.85 g/L, respectively, and the relative RMSEP (R-RMSEP) were 6.85% and 7.48%, respectively. The results indicated that the SVR model had high prediction accuracy to Hb level and adaptability to different samples, and could satisfy the requirements of clinical measurement. Based on the SVR algorithm, the self-designed LVF-NIR spectrometer has a wide application prospect in the field of non-invasive anemia diagnosis.

Key words:

1. [1]
  Zhou Y, Zheng C, Cao H, Li X, Sha J. Biochem. Biophys. Res. Commun., 2012, 420(1):205-209
2. [2]
  Timm U, Leen G, Lewis E, Mcgrath D, Kraitl J, Ewald H. Procedia Engineering., 2010, 5(6):488-491
3. [3]
  LI Qiang, MA Wei, YU Bu-Wei.Shanghai Medical Journal, 2013, 36(2):98-101李强, 马伟, 于布为. 上海医学, 2013, 36(2):98-101
4. [4]
  Worldwide Prevalence on Anaemia 1993-2005"", http://www.who.int/vmnis/database/anaemia/anaemia_status_summary/en/index.html
5. [5]
  Christian P, Shahid F, Rizvi A, Klemm R D, Bhutta Z A. Am. J. Clin. Nutr., 2009, 89(3):853-861
6. [6]
  J bsis F F. Science, 1977, 198(4323):1264
7. [7]
  LIU Yan-De, ZHOU Yan-Rui, PAN Yuan-Yuan. Optics and Precision Engineering, 2014, 22(2):281-288刘燕德, 周延睿, 潘圆媛.光学精密工程, 2014, 22(2):281-288
8. [8]
  Pincella F, Isozaki K, Miki K. Light-Sci. Appl., 2014, 3(1):110-118
9. [9]
  Heise H M. Handbook of Vibrational Spectroscopy. John Wiley & Sons, Ltd.,2006
10. [10]
  Yamakoshi K, Yamakoshi Y. J. Biomed. Opt.,2006,11(5):054028
11. [11]
  LIANG Jing-Qiu, LIANG Zhong-Zhu, LYU Jin-Guang, QIN Yu-Xin, TIAN Chao, WANG Wei-Biao. Chinese Optics.,2015, (2):277-298梁静秋, 梁中翥, 吕金光, 秦余欣, 田超, 王维彪.中国光学,2015,(2):277-298
12. [12]
  Kumar G, Schmitt J M. Proceedings of the Society of Photo-Optical Instrumentation Engineer S (SPIE), Bellingham, Spie-Int Soc Optical Engineering,1996,2678:442-453
13. [13]
  Frasca D, Dahyot-Fizelier C, Catherine K, Levrat Q, Debaene B, Mimoz O. Critical Care Med.,2011,39(10):2277-2282
14. [14]
  Park Y H, Lee J H, Song H G, Byon H J, Kim H S, Kim J T. Anesth. Analg.,2012,115(6):1302
15. [15]
  Bruells C S, Menon A K, Rossaint R, Goetzenich A, Czaplik M, Zoremba N. J. Cardiothorac. Surg.,2013,8(1):1-6
16. [16]
  Bar-Noam A S, Farah N, Shoham S. Light-Sci. Appl., 2016,5, e16007
17. [17]
  LI Lin, XU Shuo, An Xin, ZHANG Lu-Da. Spectroscopy and Spectral Analysis,2011,31(10):2702-2705李林, 徐硕, 安欣, 张录达.光谱学与光谱分析,2011,31(10):2702-705
18. [18]
  Thissen U, Pepers M, Vstün B, Melssen W J, Buydens L M C. Chemometr. Intell. Lab,2004,73(2):169-179
19. [19]
  Balabin R M, Lomakina E I. Analyst,2011,136(8):1703
20. [20]
  Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines:and Other Kernel-Based Learning Method. United Kingdom at the University Press,2000
21. [21]
  Urpalainen K. Espoo:Aalto University,2011

扫一扫看文章

计量

PDF下载量: 2
文章访问数: 633
HTML全文浏览量: 98

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

支持向量回归在人体血红蛋白无创检测中的应用

English

Support Vector Regression for Non-invasive Detection of Human Hemoglobin

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

支持向量回归在人体血红蛋白无创检测中的应用

English

Support Vector Regression for Non-invasive Detection of Human Hemoglobin

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs