Abstract: . . .  we study the evolution of SP and SE in function of C (fig.7). We choose C=990 giving SP mean of 75% and SE mean of 73%. Once these parameters are fixed, the performances obtained are : a specificity of 90% and a sensitivity of 84.7%. With the same training base, a discriminant analysis or a neural network leads to SP=65% and SE=70% [5]. VI. CONCLUSION In this paper, SVM is applied to detect patients prone to to atrial fibrillation . The classification results are promising: 90% of specificity and 84.7% of sensitivity that represents an increase of more 20% compared to two other classic methods : discriminant analysis and neural network. R EFERENCES [1] W.B. Kanel, R.D. Abbott, D.D.Savage, P.M. McNamara, Epidemiologic features of chronic atrial fibrillation : the Framingham study, N.Engl.J.Med 306, pp1018-1022, 1982. Page 5 5 of 4 [2] E.J.Benjamin, P.A.Wolf, R.B. Dagostino, H. Silbershatz, B.K. Kannel, D. Levy, Impact of atrial fibrillation on the risk of death, Circulation ,98 : 946-52, 1998. [3] A.M. Patel, D.C. Westveer, K.C. Man, J.R. Stewart, H.I. Frumin, Treatment of underlying atrial fibrillation : paced rhythm obscures recognition, J am coll cardiol , 36:784-7, 2000. [4] A.Filippi, G. Bettoncelli, A. Zaninelli, Detected atrial fibrillation in north italy : rates, calculated stroke risk and proportion of patients receiving thrombo-prophylaxis, Fam Pract ; 14:337-9, 2000. [5] L.Clavier, J.M. Boucher, R.Lepage, J.J Blanc, J.C Cornily " Automatic P-wave analysis of patients prone to atrial fibrillation ", Medical & Biological Engineering & Computing , Vol.40, n1, pp. 63-78, Jan.2002. [6] S.Graja, J.M.Boucher Multiscale Hidden Markov Model applied to ECG segmentation IEEE Workshop on Intelligent Signal Processing 2003, p 105-109, 4-6 sept.2003 [7] H.Rix, and J.P. Malenge, Detecting small variations in shape, IEEE Trans , Pattern Anal. Mach. Intell, 13, pp. 252-264, 1980. [8] R.Lepage, J.M. Boucher, J.J Blanc, J.C Cornily " ECG segmentation and P-wave feature extraction: application to patients prone to atrial fibrillation , 23 Annual. Intern Conf of IEEE Medecine and Biology Society . Istanbul, vol 1, pp. 298-302, 2001. [9] D. Lemire, C. Pharand, J.C. Rajaonah, B.Dube and A.R. Leblanc, Wavelet time entropy, T-wave morphology and myocardial ischemia, IEEE Trans. Biomed.Eng , 47, pp. 967-970, 2000. [10] V.Vapnik, 1995, The nature of statistical learning theory , NY : Springer-Verlag,  . . .
--3000,1,1500,2835,18765