Morphological Analysis of ECG Holter Recordings by Support Vector Machines

TLDR: The results shown in the paper prove that the method can classify pathologies observed not only in the QRS alterations but also in P (or F), S and T waves of electrocardiograms.

Abstract: A new method of automatic shape recognition of heartbeats from ECG Holter recordings is presented. The mathematical basis of this method is the theory of support vector machine, a new paradigm of learning machine. The method consists of the following steps: signal preprocessing by digital filters, segmentation of the Holter recording into a series of heartbeats by wavelet technique, support vector approximation of each heartbeat with the use of Gaussian kernels, support vector classification of heartbeats. The learning sets for classification are prepared by physician. Hence, we offer a learning machine as a computer-aided tool for medical diagnosis. This tool is flexible and may be tailored to the interest of physicians by setting up the learning samples. The results shown in the paper prove that our method can classify pathologies observed not only in the QRS alterations but also in P (or F), S and T waves of electrocardiograms. The advantages of our method are numerical efficiency and very high score of successful classification.