Study of blood fat concentration based on serum ultraviolet absorption spectra and neural network

Wei-Hua Zhu, Zhi-Min Zhao, Xin Guo, Le-Xin Wang, Hui Chen
DOI: 10.4236/jbise.2009.26057                

Abstract

Blood plays an important role in the clinical di-agnosis and treatment, the analysis of blood will be of very important practical significance. The experiment shows that the absorption spectra of blood are of serious noise in the wave band of 200 to 300 nm, which hides the useful spectral characteristics. The effective separation of the noise was achieved by db4 wavelet transform, and the signals of reconstruction have been obviously improved in the noise serious wave band, reflecting some useful information. The absorption peaks of different samples are displaced to some degrees. The correlation between absorbance at 278nm and blood fat concentration is no significant and random. Based on the evident correlation between serum absorption spectrum and blood fat con-centration in the wave band of 265 to 282nm, a neural network model was built to forecast the blood fat concentration, bringing a relatively good prediction. This provides a new spectral test method of blood fat concentration.

Keywords

Blood Fat Concentration; Ultraviolet Absorption Spectra; Neural Network (NN); Serum; Wavelet Transform

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Z. Shun, (2004) Nanjing Daly.
[2]	L. X. Wang, Z. M. Zhao, H. B. Yao, et al, (2002) Infrard absorption spectrum analysis and its application to blood, Spectroscopy and Spectral Analysis, 22(6), 980–982.
[3]	Z. M. Zhao, Y. M. Chen, and X. L. Yu, (2003) Characteristic analysis and application of blood fluorescence spectra, Spectroscopy and Spectral Analysis, 23(5), 922–925.
[4]	Z. M. Zhao, L. F. Guo, X. L. Yu, et al, (2005) Analysis and application of excitation fluorescence intensity of blood, Spectroscopy and Spectral Analysis, 25(12), 2056– 2060.
[5]	X. F. Lan, J. G. Liu, Y. Liu, et al, (2006) Spectroscopy research on cholesterol in hypercholesterolemia serum, Spectroscopy and Spectral Analysis, 26(13), 467–470.
[6]	C. Q. Yu, F. G. Liu, Y. Gu, et al, (2004) Laser induced fluorescence spectra of human skin and blood, Chin. J. Laser. Med. Surg., 13, 41–444.
[7]	J. D. Li, J. H. Ding, M. Wu, et al, (2006) Diagnosis of hepatocirrhosis by fluorescence spectrum of serum, APPLIED LASER, 24(2), 112–114.
[8]	J. W. Men, R. E. Zheng, Y. D. Zhang, et al, (2003) Cancer detection by serum fluorescence analysis: A pectroscopic study, Chin. J. Laser. Med. Surg., 1(1), 43–47.
[9]	X. H. Ge, Y. L. Zhao, F. Q. Zhang, et al, (2007) Effect of cancer cells on the spectra of serums, Spectroscopy and Spectral Analysis, 24(7), 841–843.
[10]	X. F. Shi, J. Ma, W. Z. Mao, et al, (2006) Applying patial least squares discriminant analysis on autofluorescence spectra to identify gastric cancer, Spectroscopy and Spectral Analysis, 26(2), 295–298.
[11]	D. Rohleder, G. Kocherscheidt, and K. Gerber, (2005) Comparison of mid-infrared and Raman spectroscopy in the quantitative analysis of serum, J. Biomedical Optics. 10(3), 1–10.
[12]	Runger and M. Thomas, (2007) How different wavelengths of the ultraviolet spectrum contribute to skin carcinogenesis: The role of cellular damage responses, J. Invest Dermatol, 127(9), 2103–2105.
[13]	G. C. Tang, (1989) Pulsed and CW laser fluorescence from cancerous, normal and chemically treated normal human heart and lung tissues, Applied Optics, 28(12), 2337–2343.
[14]	S. Rochkind, M. Nissan, M. Alon, et al, (2001) Effects of laser irradiation on the spinal cord for the regeneration of crushed peripheral nerve in rats, Laser in Surgery Medicine, 28(3), 216–219.
[15]	M. Gniadecka, H. C. Wulf, O. F. Nielsen, et al, (1997) Distinctive molecular abnormalities in benign and malignant skin lesion: Studies by Raman spectroscopy, Photochem Photobiol, 66, 418–423.
[16]	S. P. Qin, J. H. Ding, and J. D. Li, (2006) Research on fluorescence spectra of liver pathological serum of mice with wavelet transforms method, Journal of Optoelectronics Laser, 17(5), 634–637.
[17]	Y. T. Wang and Y. C. Li, (2006) Application of wavelet threshold denoising method in the fluorescence analysis of pesticides, Journal of Applied Optics, 27(3), 192–194.
[18]	D. T. Li, C. J. Zhang, and J. Wang, Application of wavelet transform to infrared analysis, Spectroscopy and Spectral Analysis, 26(11), 2024–2026.
[19]	Y. F. Tang, Z. Y. Zhang, G. Q. Fan, et al, (2005) Identification of official rhubarb samples based on IR spectra and neural networks, Spectroscopy and Spectral Analysis, 25(5), 715–278.
[20]	G. H. Wu, C. Y. He, and R. Chen, (2002) Application of artificial neural network to simultaneous spectro-fluori- metric determination of phenol and resorcinol, Spectroscopy and Spectral Analysis, 22(5), 813–815.
[21]	Y. Z. Han, Y. X. Zhang, S. J. Chang, et al, (2005) Recognition for the noninear fluorescence spectra based on optimal wavelet transform and artificial neural network, Journal of Optoelectronics and Laser, 16(6), 719–721.
[22]	Z. M. Zhao, Y. J. Xin, L. X. Wang, et al, (2008) Measurement and analysis of absorption spectrum of human blood, Spectroscopy and Spectral Analysis, 28(1), 138– 140.
[23]	J. E. Meng, (2002) Face recognition with radial function (RBF) neural networks, IEEE Transaction on Neural Network, 13(3), 15–17.