Abstract: . . .  immediately terminating AF from AF which terminates one minute later. Our method first uses spectral models to determine which pairs of records are recorded from the same patient. This technique achieves 100% accuracy on the training set and partitions the test set into 10 unique record pairs. We then examine by hand the end of each ECG record to determine the likely time ordering of the records in each pair, thus distinguishing which record terminates immediately. This technique achieves an accuracy of 90% on the challenge test set. * Internal Accession Date Only 1 Published in and presented at IEEE Computers in Cardiology, 19-22 September 2004, Chicago, IL Approved for External Publication Copyright IEEE 2004 Page 2 1 Introduction As described in the call for participation for the PhysioNet 2004 Challenge, atrial fibrillation (AF) is the most common serious cardiac arrhythmia. The risks of sustained AF include stroke and myocardial infarction, caused by the formation of blood clots within stagnant blood volumes in the atria[5]. AF affects about 2% of the general population and 8%-11% of those older than 65 years. The demand for effective therapeutic strategies for AF is anticipated to increase substantially as the proportion of the elderly population increases[4, 3]. The goal of this challenge is to study the changes . . .
. . .  D.D. Savage, and et al. Epidemiologic features of atrial fibrilla- tion: The framingham study. N Engl J Med , 306:10181022, 1982. [4] A. D. Krahn, Manfreda J, R. B. Tate, and et al. The natural history of atrial fibrillation : Incidence, risk factors, and prognosis in the manitoba follow-up study. Am J Med , 98:476 484, 1995. 6 Page 8 [5] George Moody. Computers in cardiology challenge 2004. URL=http://www.physionet.org/challenge/2004/, October 2003. [6] L. R. Rabiner and B. H. Juang. Fundamentals of Speech Recognition . PrenticeHall, 1993. [7] I Savelieva and A. John Camm. Atrial pacing for the prevention and termination of atrial fibrillation . Am J Geriatr Cardiol , 11(6):380398, 2002. 7 Page 9 Record Closest Second Third s01 t01 0.1118 s07 3.5054 t08 3.6134 s02 t02 0.0329 t05 0.4165 s05 0.4851 s03 t03 0.1488 s09 0.7625 t09 0.8337 s04 t04 0.0164 t10 0.7218 s10 1.0065 s05 t05 0.0330 s02 0.4851 t02 0.4935 s06 t06 0.0224 t08 1.5680 t03 1.9245 s07 t07 0.1151 t03 0.5871 t05 0.9137 s08 t08 0.3097 t03 1.8823 s06 2.0094 s09 t09 0.0613 t03 0.6669 s03 0.7625 s10 t10 0.1254 s04 1.0065 t04 1.0220 t01 s01 0.1118 s07 3.7456 t08 3.7523 t02 s02 0.0329 t05 0.4031 s05 0.4935 t03 s03 . . .
--3000,2,750,3168,19141