Abstract
In this study, 1 D wavelet and Partial correlation analyses were applied to a data set obtained from patients with Multiple Sclerosis along with a control group of healthy individuals. The analysis is limited to a sample of 139 individuals, 76 being with Relapsing-Remitting Multiple Sclerosis, 38 with Secondary Progressive Multiple Sclerosis, 6 with Primary Progressive Multiple Sclerosis, and 19 being Healthy individuals. It is the main objective of the study to develop a clinical decision support system in order to classify the patients’ diagnostic data based on features gathered from Magnetic Resonance Imaging. The 1-D Continuous Wavelet Transforms are developed to measure the health status of the patients based on features gathered from Magnetic Resonance Imaging and Expanded Disability Status Scale (EDSS). Classification of the Multiple Sclerosis (MS) diagnosis level indicates that it can be used as an important indicator for making decisions to identify MS health status of patients. Our results of relative distribution of three indicators help to identify some differences of “Remitting Relapsing Multiple Sclerosis”, “Secondary Progressive Multiple Sclerosis”, and “Primary Progressive Multiple Sclerosis”. Features like sex, the maximum and minimum lesion sizes, and maximum and minimum values of EDSS scores are widely known and applied in medical studies. This study has fulfilled what lacked in terms of mathematical explanation concerning the significance of such features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gilroy, J.: Basic Neurology, 3rd edn, pp. 225–278. The McGraw-Hill Companies, New York (2000)
Karaca, Y., Osman, O., Karabudak, R.: Linear modeling of multiple sclerosis and its subgroups. Turk. J. Neurol. 21(1), 7–12 (2015)
Karaca, Y.: Constituting an optimum mathematical model for the diagnosis of multiple sclerosis. Ph.D. thesis, Institute of Science and Technology, Marmara University, İstanbul, Turkey (2012)
Karabudak, R., Işık, N., Siva, A.: Multiple Sklerozda Tanı ve Tedavi Kılavuzu, Bilimsel Tıp yayınevi, pp. 5–20 (2009)
Shahvar, M.B., Badounak, N.D., Kharrat, R.: A new approach for compressional slowness modeling using wavelet coefficients, energy sources, part a: recovery. Util. Environ. Eff. 36-19, 2106–2112 (2014)
Safarinezhadian, B., Karimaghaee, P., Prof, A., Safavi, A.A., Abedini, M.J.: Analysis of laser-scanned topographic data using wavelet methods. Instrum. Sci. Technol. 36(3), 323–336 (2008)
Zope-Chaudhari, S., Venkatachalam, P., Buddhiraju, K.M.: Assessment of distortion in watermarked geospatial vector data using different wavelets. Geo-Spat. Inf. Sci. 18(2–3), 124–133 (2015)
Aloe, A.M.: An empirical investigation of partial effect sizes in meta-analysis of correlational data. J. Gen. Psychol. 141-1, 47–64 (2014)
Algina, J., Olejnik, S.: Sample size tables for correlation analysis with applications in partial correlation and multiple regression analysis. Multivar. Behav. Res. 38-3, 309–323 (2003)
Karaca, Y., Aslan, Z., Cattani, C., Galletta, D., Zhang, Y.: Rank determination of mental functions by 1D wavelets and partial correlation, Springer. J. Med. Syst. 41-1, 1–10 (2017)
Karaca, Y., Zhang, Y., Cattani, C., Ayan, U.: The differential diagnosis of multiple sclerosis using convex combination of infinite kernels. CNS Neurol. Disord. Drug Targets 16-1, 36–43 (2016)
Expanded disability status scale (EDSS). https://www.mstrust.org.uk/a-z/expanded-disability-status-scale-edss (14.11.2016)
Joy, J.E., Jonston, R.B., Jr. Editors: Multiple Sclerosis Current Status and Strategies for the Future. National Academy Press, Washington (2001)
Karaca, Y., Aslan, Z.: Wavelet analysis of anxiety and mathematics. Indian J. Ind. Appl. Math. 4-2, 118–130 (2013)
Abramovich, F., Bailey, T.C., Sapatinas, T.: Wavelet analysis and its statistical applications. Stat. Part 1, 1–29 (2000)
Lee, D.T.L., Yamamoto, A.: Wavelet analysis: theory and applications. Hewlett Packard J., 44–52 (1994)
Siddiqi, A.H.: Applied Functional Analyses: Numerical Methods, Wavelet Methods, and Image Processing, vol. 258, pp. 356–425. CRS Press, Boca Raton (2003)
Melissa, A.S., Raghuraj, K.R., Lakshminarayanan, S.: Partial correlation metric based classifier for food product characterization. J. Food Eng. 90(2), 146–152 (2009)
Cramer, D.: A cautionary tale of two statistics: partial correlation and standardized partial regression. J. Psychol. 137-5, 507–511 (2003)
Marreles, G., Horwitz, B., Kim, J., Pelegrini-Issac, M., Benali, H., Doyan, J.: Using partial correlation to enhance structural equation modeling of functional MRI data. Magn. Reson. Imaging 25, 1181–1189 (2007)
Acknowledgements
The authors are thankful to Prof. Dr. Rana Karabudak and her team along with Hacettepe University Neurology Department and Radiology Units. Dr. Yeliz Karaca is particularly grateful to Turkish Neurology Association.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Karaca, Y., Aslan, Z., Siddiqi, A.H. (2017). 1D Wavelet and Partial Correlation Application for MS Subgroup Diagnostic Classification. In: Manchanda, P., Lozi, R., Siddiqi, A. (eds) Industrial Mathematics and Complex Systems. Industrial and Applied Mathematics. Springer, Singapore. https://doi.org/10.1007/978-981-10-3758-0_11
Download citation
DOI: https://doi.org/10.1007/978-981-10-3758-0_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3757-3
Online ISBN: 978-981-10-3758-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)