Advertisement

Parallel Multiclass Support Vector Interpretation of Haemodynamic Parameters for Manifestation of Aortic and Arterial Occlusive Diseases

  • S. H. Karamchandani
  • V. K. Madan
  • P. M. Kelkar
  • S. N. Merchant
  • U. B. Desai
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 195)

Abstract

Aortic and arterial occlusive diseases are congenital conditions manifested in impedance plethysmography and are difficult to interpret. A parallel multiclass support vector classification of haemodynamic parameters computed from plethysmographic observations is proposed for diagnosis of aortoarteritis, atherosclerotic narrowing and coarctation of aorta. The proposed support vector algorithm was able to detect more precisely the presence of thrombotic occlusions at proximal and distal arteries. The proposed method provided better accuracy and sensitivity of 97.46% and 98.3% compared to principal component analysis (PCA) based backpropagation and non-weighted support vector architectures respectively. The results of the genotype were ably supported by receiver operating characteristics (ROC) curves which depict a ratio of true positive rate and false positive rate of over 0.9 for all classes as compared with ratios varying from 0.7 to 0.9 for majority of classes as observed in case of non weighted architecture. A reduction of over 60% in negative likelihood ratio with a 5% increase in negative predictive value was observed as compared to Elman and PCA based backpropagation architectures. The results were validated from angiographic findings at Grant Medical College, J.J. Hospital, and Bhabha Atomic Research Centre (BARC) all in Mumbai. The proposed method also distinguished cases with nephritic syndrome, lymphangitis, and venous disorders against those with arterial occlusive diseases. Application of the proposed method has potential to enhance performance of impedance plethysmography.

Keywords

Impedance Cardiovasography Aortic Occlusive Diseases Arterial Occlusive Diseases Parallel Multiclass support vector machines 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jindal, G.D., Ananthakrishnan, T.S., Kataria, S.K.: An introduction to impedance cardiovasography. In: Proc. Symposium on Biomedical Engineering and Nuclear Medicine (SBME-NM). Bhabha Atomic Research Centre, Mumbai E /003 (2001)Google Scholar
  2. 2.
    Jindal, G.D., Ananthakrishnan, T.S., Kataria, S.K.: Electrical impedance and photo plethysmography for medical applications. In: Proc. Symposium on Biomedical Engineering and Nuclear Medicine (SBME-NM), Bhabha Atomic Research Centre, Mumbai, E /025, Microfiche 2005/60371 (Q), pp. 134–138 (2005)Google Scholar
  3. 3.
    Golden, J.C., Miles, D.S.: Assessment of Peripheral Haemodynamic using Impedance Plethysmography. Physical Therapy 66(10), 1544–1547 (1986)Google Scholar
  4. 4.
    Mohapatra, S.N., Helena, A.M.: Measurement of peripheral blood flow by electrical Impedance technique. Journal of Med. Engg. & Tech. 3(3), 132–137 (1979)CrossRefGoogle Scholar
  5. 5.
    Corciova, C., Ciorap, R., Zaharia, D., Matei, D.: On using impedance plethysmography for estimation of blood flow. In: 2011 IEEE International Workshop on Medical Measurements and Applications Proceedings (MeMeA), pp. 84–87 (2011)Google Scholar
  6. 6.
    Corciova, C., Ciorap, R., Zaharia, D., Matei, D.: Hemodynamic monitoring using peripheral impedance plethysmography. In: 7th International Symposium on Advanced Topics in Electrical Engineering (ATEE), pp. 1–4 (May 2011)Google Scholar
  7. 7.
    Lin, C.H.: Assessment of bilateral photoplethysmography for lower limb peripheral vascular occlusive disease using color relation analysis classifier. Comput. Methods Prog. Biomed. 103(3), 121–131 (2011)CrossRefGoogle Scholar
  8. 8.
    Hull, R.D., Raskob, G.E., Carter, C.J.: Serial impedance plethysmography in pregnant patients with clinically suspected deep-vein thrombosis, clinical validity of negative findings. Annals of Internal Medicine 112(9), 663–667 (1990)Google Scholar
  9. 9.
    Wang, J.J., Hu, W.C., Kao, T., Peng Liu, C., Lin, S.-K.: Development of forearm impedance plethysmography for the minimally invasive monitoring of cardiac pumping function. Journal of Biomedical Science and Engineering 4(6), 122–129 (2011)CrossRefGoogle Scholar
  10. 10.
    Peripheral Pulse Analyzer, Internet, http://www.larsentoubro.com/lntcorporate/uploads/product/Nivomon.pdf (last accessed June 2012)
  11. 11.
    Webster, J., Shankar, R., Yong, S.S.: The Contribution of Vessel Volume Change and Blood Resistivity Change to the Electrical Impedance Pulse. IEEE Transactions on Biomedical Engineering 32(3), 192–198 (1985)CrossRefGoogle Scholar
  12. 12.
    Brown, B.H., Pryce, W.H., Clarke, R.G.: Impedance Plethysmography: Can it measure Changes in limb blood flow. Medical & Biological Engg. 13, 674–681 (1975)CrossRefGoogle Scholar
  13. 13.
    Kubicek, W.G., Kottke, E.J., Ramos, F.J., Patterson, R.P., Witsoe, D.A., Labree, J.W., Remole, W.: The Minnesota impedance cardiograph theory and applications. Biomedical Engg. 9, 410–416 (1974)Google Scholar
  14. 14.
    Ananthakrishnan, T.S., Jindal, G.D., Sinha, V., Jain, R.K., Kataria, S.K., Deshpande, A.K.: Clinical validation of software for a versatile variability analyzer: Assessment of autonomic function. Journal of Medical Physics 32(3), 97–102 (2007)CrossRefGoogle Scholar
  15. 15.
    Jindal, G.D., Babu, J.P.: Calibration of dZ/dt in Impedance Plethysmography. Med. & Bio. Engg. & Comput. 23, 279–280 (1985)CrossRefGoogle Scholar
  16. 16.
    Bhuta, A.C., Babu, J.P., Parulkar, G.B.: Technical aspects of impedance plethysmography. Journal of Post Graduate Medicine 36, 264–270 (1990)Google Scholar
  17. 17.
    Jindal, G.D., Babu, J.P., Nerurkar, S.N., Kelkar, M.D., Deshpande, A.K.: Corrected formula for estimating peripheral blood flow by impedance plethysmography. Med. Bio.Engg. Comput. 32, 625–631 (1994)CrossRefGoogle Scholar
  18. 18.
    Karamchandani, S.K., Desai, U.B., Merchant, S.N., Jindal, G.D.: Principal Component Analysis Based Backpropagation Algorithm for Diagnosis of Peripheral Arterial Occlusive Diseases. In: 22nd Canadian Conference on Electrical and Computer Engineering (CCECE), Newfoundland, Canada, May 3-6, pp. 482–485. IEEE (2009)Google Scholar
  19. 19.
    Babu, J.P., Ananthakrishnan, T.S., Jindal, G.D.: PC based impedance cardio-vasography, SBME-NM, BARC (2000)Google Scholar
  20. 20.
    Ozcan, O., Mustafa, S., Duran, D.A., Bilal, G., Omer, A., Gokhan, C., Serkan, T., Dursun, A., Yucel, B., Hatice, S.: Do collaterals affect heart rate variability in patients with acute myocardial infarction? Coronary Artery Disease 15(7), 405–411 (2004)CrossRefGoogle Scholar
  21. 21.
    Hill, R.D., Smith, R.B.: Examination of the extremities: Pulses, Bruits, and Phlebitis. Clinical Methods, 148–153 (1990)Google Scholar
  22. 22.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001)Google Scholar
  23. 23.
    Ivanciuc, O.: Applications of support vector machines in chemistry. Reviews in Computational Chemistry 23, 291–400 (2007)CrossRefGoogle Scholar
  24. 24.
    Hsu, C., Lin, C.: A comparison of methods for multi-class support vector machines. IEEE Transactions on Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar
  25. 25.
    Huang, Y.-M., Du, S.-X.: Weighted support vector machine for classification with uneven training class sizes. In: Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, pp. 4365–4369 (2005)Google Scholar
  26. 26.
    Keerthi, S.S., Lin, C.J.: Asymptotic behaviors of support vector machines with Gaussian kernel. Neural Computation 15(7), 1667–1689 (2003)MATHCrossRefGoogle Scholar
  27. 27.
    Lin, H.T., Lin, C.J.: A Study on Sigmoid Kernels for SVM and the Training of non-PSD Kernels by SMO-type Methods. [Technical Report]. Department of Computer Science and Information Engineering, National Taiwan University, pp. 3–4 (2003)Google Scholar
  28. 28.
    Chamasemani, F.F., Singh, Y.P.: Multiclass Support Vector Machine (SVM) classifiers - An application in hypothyroid detection and classification. In: Sixth International Conference on IEEE Bio-Inspired Computing Theories and Applications (BIC-TA), pp. 351–356 (2011)Google Scholar
  29. 29.
    Hsu, C., Chang, C., Lin, C.: A practical guide to support vector classification, [Technical Report]. Department of Computer Science and Information Engineering, National Taiwan University, pp. 3–4 (2003)Google Scholar
  30. 30.
    Wu, T.F., Lin, C.J., Weng, R.C.: Probability Estimates for Multi-class Classification by Pairwise Coupling. Journal of Machine Learning Research 5, 975–1005 (2004)MathSciNetMATHGoogle Scholar
  31. 31.
    Liu, Y., You, Z., Cao, L.: A novel and quick SVM-based multiclass classifier. Pattern Recognition 39, 2258–2264 (2006)MATHCrossRefGoogle Scholar
  32. 32.
    Karamchandani, S.K., Desai, U.B., Merchant, S.N., Jindal, G.D.: Principal Component Analysis Based Backpropagation Algorithm for Diagnosis of Peripheral Arterial Occlusive Diseases. In: 22nd Canadian Conference on Electrical and Computer Engineering (CCECE), Newfoundland, Canada, pp. 482–485. IEEE (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • S. H. Karamchandani
    • 1
  • V. K. Madan
    • 2
  • P. M. Kelkar
    • 3
  • S. N. Merchant
    • 1
  • U. B. Desai
    • 4
  1. 1.Indian Institute of Technology – BombayMumbaiIndia
  2. 2.Kalasalingam UniversityKrishnankoil, Virudhunagar DtIndia
  3. 3.Sneha Health Care CentreMumbaiIndia
  4. 4.Indian Institute of Technology – HyderabadHyderabadIndia

Personalised recommendations