© International Society for Bioelectromag
netism
International Journal of Bioelectromagnetism
5
, 1
175
International Journal of Bioelectromagnetism
www.tut.fi/ijbem
Vol. 5, No. 1, 2003
Learning system for computer

aided ECG analysis
based on support vector machines
Stanislaw Jankowski
a
, Artur Oreziak
b
a
Institute of Electronic Systems, Center for Co
mplex Systems Research,
Warsaw University of Technology,Warsaw, Poland
b
Chair and Department of Internal Medicine and Cardiology, Central Teaching Hospital
Warsaw, Poland
Correspondence: S. Jankowski, Institute of Electronic Systems, Warsaw University of T
echnology, 00

665 Warsaw, ul.
Nowowiejska 15/19, Poland. E

mail:
sjank@ise.pw.edu.pl
, phone +48 22 660 5589, fax +48 22 825 2300
Abstract.
A new system for computer

aided analysis of ECG Holter recordings is int
roduced. We
implement an idea of supervised learning, i.e. the data set of examples of normal and pathological
heartbeats is selected and described by cardiologists. The system is built of several units: user’s
friendly interface, learning set builder, SVM

approximation unit, SVM

classifier unit, validation unit.
In order to show the potential of our approach we analyze a patient with multifocal ventricular
contraction.
Keywords:
ECG analysis, Learning system, Support vector machine
1.
Introduction
We present
a new tool for computer

aided analysis of ECG Holter recordings. This tool
implements an idea of supervised learning from examples by using support vector machines
[Cristianini, 2000, Schölkopf, 1999,Vapnik 1998]. The knowledge is incorporated by a carefu
l
selection of data set commented by specialists. Then by using statistical procedures called “learning”
a classifier is designed. The successful recognition depends strongly on the quality of learning set
(selection of cases), data representation and the
mathematical basis of the classifier. The system is
tested at the
Chair and Department of Internal Medicine and Cardiology, Central Teaching Hospital
in Warsaw, Poland.
2.
Learning system for ECG classification
The presented system is based on our previous r
esults [Jankowski & al., 2002]. The ECG Holter
recordings is filtered and segmented into single beats. We apply the wavelet analysis to detect R

points. Then a sample of beats is analyzed and labeled by cardiologists. Hence, a learning set was
obtained All
the sample is parameterized by using the support vector approximation with Gaussian
kernels. The width of Gaussian function may be tuned with respect to signal shape. The centres are
support vectors. The function coefficients are equal to Lagrange multipl
iers. This procedure
transforms the digital signal into 30

dimensional vectors of Lagrange multipliers; each vector
encodes a single heartbeat. Then the
classifier is trained giving rise to a certain number of support
vectors. The low number of support vec
tors with respect to the total number of beats in the training
file states the efficiency of heartbeat shape representation. For multiclass support vector machine we
perform many one

to

all classifiers. The number of support vectors for classification depe
nds on the
problem complexity. We attempt to minimise the number of support vector by experiments with
various kernel functions.
The unified mathematical basis of support vector machines for approximation and classification
enables to obtain perfect genera
lisation properties and to perform efficient numerical program. For
both tasks we use sequential minimal optimisation algorithm. The program code is written in C++
language.
© International Society for Bioelectromag
netism
International Journal of Bioelectromagnetism
5
, 1
176
3.
Results
In order to estimate the system functionality we examined one case: the
ECG Holter recordings
of a patient
having sinus rhythm with multifocal ventricular contractions. The heartbeats
were
assigned into 3 classes corresponding to:
normal beats and 2 classes of pathological shapes from 2
focal ventricular contraction, probably
LBBB
–
left bundle branch block and RBBB
–
right bundle
branch block, as shown in Fig. 1.
Learning set consisted of 1712 heartbeats. We obtained 3 linear
classifiers using one

against

all scheme with the following numbers of support vectors: normal
against
all pathological beats: 46; RBBB

like morphology against all other beats: 36; LBBB

like
morphology against all other beats: 20. The test results for 9690 heartbeats are listed in Table 1.
Figure 1.
Several heartbeats with class labels assigned by a car
diologist.
Table 1.
Classification validation for a test dataset of 9852 heartbeats.
Normal
RBBB

like
LBBB

like
Total
Total number of beats
8584
244
1044
9852
Correctly classified beats
8424
231
1035
9690
Misclassified beats
22
11
2
35
Unclassified
118
2
7
127
Rate of success [%]
98.1
94.7
99.1
98.3
4.
Conclusions
The learning system for ECG computer

aided analysis is a flexible and open tool for cardiologists
in order to perform the classification
of all heartbeats from the Holter ECG recordings upon the
shape.
The cardiologists can define the goals of classification by the choice of learning sets with
respect to all details of the electrocardiograms. The test results are consistent and encouraging. We
hope that this system may be applied to long recordings in o
rder to search for precursors of
dangerous events and risk prediction.
Acknowledgements
W
ork supported by the Dean of the Faculty of Electronics and I
n
formation Technology, Warsaw
University of Technology. We thank Prof. Dr. Med. G. Opolski and Prof. J. J.
Zebrowski for helpful
r
e
marks.
References
N. Cristianini, J. Shaw

Taylor:
Support Vector Machines
, Cambridge Unive
r
sity Press, 2000
S. Jankowski, J. Tijink, G. Vumbaca, M. Balsi, G. Karpinski: Support vector machine for the recognition of atrial and
ventr
icular de[polarization in Holter ECG recordings,
IJBEM
vol. 4, No. 2. pp. 343

344, 2002
S. Jankowski, J. Tijink, G. Vumbaca, M. Balsi, G. Karpinski: Morphological analysis of ECG Holter recordings by support
vector machines, Medical Data Analysis ISMDA 200
2 (eds. A. Colosimo, A. Giuliani, P. Sirabella), Lecture Notes in
Computer Science 2526, Springer, Berlin 2002, pp. 134

143.
V. N. Vapnik
Statistical Learning Theory
, Wiley, New York, 1998.
Comments 0
Log in to post a comment