8/3/2019 Ecg Comparison

http://slidepdf.com/reader/full/ecg-comparison 1/4

ECG Signal Analysis by Pattern Comparison

R Bousseljot, D Kreiseler

Physikalisch-Technische Bundesanstalt, Berlin, Germany

Abstract

A new technique fo r the ECG interpretation by wave form

recognition is introduced. The basis fo r the pattern

matching algorithm without feature extraction is un ECG

wave form database with ECG signals and patientdiagnosis information. The recognition takes place by

comparing the wave form s of 12 leads of the examined

ECG with the same leads of different ECGs from the

database. The similarity of the compared ECG beats is

calculated with the cross co rrelation functio n. By means of

the algorithm, we select ECGs o the database which are

the most similar to the examined ECG considering all of

the individual leads. Using the available database

information, the diagnosis which corresponds to the most

similar ECGs of the database is then identified as the

diagnosis fo r the examined ECG. The new method has

been tested with 249 original ECG s, most of them fro m

patients with myocardial injurction or fro m healthy

persons.

1. Introduction

For the computer-aided analysis of ECGs, procedures are

at present used which, among other things, measure the

waveforms of the ECG to extract features from the signals

for use as parameters [l] .With the aid of sets of features

and on the basis of decisions allowing for the applicable

rules or using neural networks [ 2 ] , classifications and

defined diagnostic statements are made. This decision-

making takes place automatically without the doctor

exerting any influence.

The present publication presents a novel technique which

is not based on the measurement and extraction of

individual features of the ECG. By comparison of the

signal patterns of a 12-channel ECG of unknown diagnosiswith signal waveforms of an ECG d atabase, those ECG are

searched in the database whose waveforms are most

similar to those of the unknown ECG .

0276-6547/98 $10.000 998 IEEE 349

2. Hypothesis

The technique is based on the hypothesis that those ECGs

whose signal waveforms are in best agreement in their

leads can in all probability be assigned to the same

diagnosis. As this assumption is at the basis of medicalexperienc e, it should be possible to obtain the diag nosis for

an unknown ECG from a comparison between the signal

waveforms of this ECG with unknown diagnosis and an

EC G of known diagnosis stored in a database. The

technique thus starts from the assumption that the

waveforms of the quasi-periodical signal sections of the

leads of the 12-channel ECG represent a "finger print" of

the ECG in question.

3. Procedure

The method developed for ECG signal analysis by pattern

comparison with the aid of an ECG database consists of

four succe,sive steps:

3.1. Signal conditioning

The first step ensures the computational preparation of the

derived and digitized 12-channel ECG . The analysis

relates to beat variance, drift, signal offset, extra beats, etc.

To realize this step, signal processing methods can be used

which often are already implemented in computer-aided

ECG equipment.

According to the periodicity of the ECG signal, a

representative ECG beat is selected isochronous over all

leads. This selection can be made automatically or by

interaction at the display usinga

line cursor taking in allleads. The ECG signal patterns thus provided are the

prerequisite to the comparison of the waveforms with the

ECG of the database.

3.2. Pattern correlation

The assessment of the similarity of the ECG signal patterns

of equal ECG leads is carried out by calculation of

Computers in Cardiology 1998 Vol25

8/3/2019 Ecg Comparison

http://slidepdf.com/reader/full/ecg-comparison 2/4

correlation functions whose function values are formed

from the correlation coefficients K :

N 1 N N

In dependence on the temporal shift of the signal window

with the time series x,, unknown ECG) and y,, (reference

ECG) - with 1 5 n 2 N . N = number of function values - the

correlation functions form maxima according to the

periodicity of the ECG if the patterns are similar.

Figs.1 

and 2 show two examples of correlation functionsin the case of similarity of the ECG beats as well as i n the

case of strong differences of the waveforms from one

another. According to the periodicity of the ECG signals,

the correlation functions are also periodical. The different

maxima are due to the variance between the ECG beats.

The examples show that it is permissible for ECG without

disrhythmias or strong anomalies between the beats to limit

the correlation analysis to only one beat typical of the ECG

in question.

1

Kit)

p.5

0

-0.5

-11 2 3 4 5

+tis

Fig. 1 Correlatio n function for very similar signal

patternsx x - ~ - " ~---

Fig. 2 Correlatio n function with distinct differences of

the signal patterns

In pattern correlation , the unknown EC G is compa red with

the ECGs of the datab ase in all 12 leads. The result of each

reference ECG comparison is a 12-dimensional vector

whose elements give the correlation values for the

respective lead. The range of values corresponds to the

definition range of the correlation coefficient K with -1 IK I + l .For the further considerations, only the positive

correlations are taken into account. The correlation

measure 100% ( K = l ) thus means identity of the patterns. A

correlation statement towards K=O indicates completely

different signal patterns in the waveforms of the lead

considered.

3.3. Classification

It is the aim of classification to summarily assess theagreement of the lead-related correlation results obtained

from the comparison of the unknown ECG with any

reference EC G. It must be taken into consideration that the

result of two ECG pattern comparisons may be

multivariable and available as a 12-dimensional vector of

the correlation results of the individual leads and the

number of comparisons with the reference ECG may be

very great. To solve this task, a modified distance

technique of the multivariate signal analysis is used. As the

method can be applied independantly of the dimension of

the vector of the correlation results and thus independantly

of the number of leads to be taken into account, the

classification step is illustrated by the example of the

dimension nz = 3.i  Mi IB

Fig. 3 Graphical interpretation of the multichannel

correlation results (dimension nz = 3)

Fig. 3 shows a three-dimensional Cartesian system of

coordinates which is formed by the correlation results of

three ECG leads. Acco rding to the used range of values for

the correlation coefficient K , the axial ranges from 0 to 1

350

8/3/2019 Ecg Comparison

http://slidepdf.com/reader/full/ecg-comparison 3/4

are obtained. Any comparison of signal patterns of the

unknown ECG with those of an ECG from the database

leads to a point inside the cube formed for the three-dimensional case

If the signal patterns are identical in all leads ( K = I), point

Po ( l , l , l ) will be obtained. The length of the diagonal in

this cube represents the maximu m similarity measu re in the

case of three leads. All other points are associated with

vectors whose magnitude are smaller compared with the

length of the diagonal and thus indicate less similarity of

the signal patterns.

When all leads of the 12-channel ECG are allowed for, the

dimension m = 12 is obtained. The normalized modulus

vector as similarity measure then reads

Mi: maxima of the

m: dimension

correlations of a lead171= J T W=l

JmA second value should allow for the uniformity of the

correlations of the leads. This is possible by indicating the

angle cp or the distance b:/

The value b = 0 means here that equal correlation values

were calculated for all leads. This does not allow

conclusions to be drawn for the similarity of the signal

patterns of all leads. It is, however, possible, for example,

to take in the influence of noise-affected signals, or other

technical disturbances in a lead, on the overall result.

The two values r an d b can be calculated for any

comparison between an ECG of unknown diagnosis with

the reference ECG. In the following, the value r will be

given in %.

The assignment of the known diagnoses of the reference

ECGs to the distributions according to Fig. 4 allows the

diagnosis of the unknown ECG to be estimated.

I -

70 80 90 10'0- r 1 %

~--- . _ L X- X- ^ _ " I ~ - _ I ~ " , - _ ^ I . " _ . x I I * l ' ~ ~ . . " " . . " ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~

Fig. 4 Detail of an r-b diagram showing the distribution

of the pattern correlations of an unknown E CG

3.4 Evaluation of the classification results

Fig.  5 shows as an example the distribution of the

correlation results, including the diagnostic information

from the database.

NORM0 MIA AhdlV ASMl+ ALMl

0.1 5

0.1

0.05

n85 90 95 10 0

- r ( %

Fig. 5 Assignment of the pattern correlations

according to Fig. 4 to the diagn oses of the

reference EC Gs (detail)

The correlations of the patterns of the ECG of unknown

diagnosis with themselves furnish in all leads a 100%

similarity (r = loo%, b = 0). In the range r > 85%, some

correlation results indicate database ECGs with a greatsimilarity of the signal patterns in all leads. These ECGs

stem from patients with inferior myocardial infarctions

(IMI). In the example given, the IMI diagnosis can

therefore also be inferred for the unknown ECG.

351

8/3/2019 Ecg Comparison

http://slidepdf.com/reader/full/ecg-comparison 4/4

The evaluation of the classification results according to

Fig. 5 can be supported a s follows:

inferior MI

normal person

clustering of the d istributions

taking into consideration of selected leads or of their

combinations for the correlation process

inserting of th e ECG signal patterns

representation of the discrete correlation results for

every lead

inserting of detailed information from the database

about findings, anamnesis, anonymized patient

information, medications, technical parameters, etc.

89,26% I 84 ,38Yo

67,92% I 96,43%

These interactive possibilities are intended to enable the

doctor - in contrast to conventional methods of computer-

aided ECG interpretation - to separately evaluate the

results including the patient information available.

The result of the signal pattern comparison is not a

diagnostic statement which can be accepted or rejected but

a probability statement on the basis of similar cases of an

ECG databa se. Accordingly, the quality of this database as

regards the extent and the validation is a decisive

prerequisite for the function of the technique presented.

4. Results

The operation of the method presented was checked with

the aid of the CARDIODAT signal pattern database of the

Physikalisch-Technische Bundesanstalt [3 ]. Within the

scope of initial investigations, 249 ECGs of patients withmyocardial infarctions and normal persons were allowed

for. For all types of investigation the distributions in the r-

b diagram was calculated and evaluated in accordance with

the known diagnoses of the reference ECGs. For the

evaluation those five ECGs were taken into account for

each diagnostic g roup wh ich, compared with the respective

unknown ECG, furnished the best correlations. Pooling of

the five best results is made by unweighted averaging. The

following table shows the sensitivities and specificities

reached. In the anterior myocardial infarct group, 75 ECGs

of patients with the AMI, ASM I and ALM I diagnoses were

pooled. The inferior myocardial infarct group considers

12 1 ECGs with the diagnoses IMI, ILMI, IPMI, IPLMI.

The normal pe rsons group contains 5 3 test persons.

Finding 1 Sensitivity I Specificity

anterior MI I 89.33% I 93.68%

5. Advantages

The presented method for computer-aided interpretation of

ECGs by signal pattern comparison with ECG databases

offers the following advantages:

no feature extraction for the EC G

no limitation of the diagnostic statements

inclusion of rare diseases by specialized ECG

databases

possibility of extending the databases as bases of

knowledge w ithout changes of the algorithm

inclusion of further patient information from the

database for making diagnoses

lead-related inclusion of EC G patterns

robustness with respect to disturbances or signal

failures in a leadlearning ability by inclusion of the results of current

patient examinations

cost advantages by use of existing PCs

local availability of the ECG database on CD or use of

centralized databases via modem, IS DN or network.

References

[ l ] Willems J.L., Abreu-Lima C., Arnaud P., va n Bemmel J.H.,

Brohet C., Degani R., Denis B., Gehring J . , Graham I., vanHerpen G., Machade H., Macfarlane P.W., Michaelis J. ,

Moulopoulos S.D., P. Rubel P. “The diagnostic performance ofcomputer programs for the interpretation of electrocardiograms”

New England Journal of Medicine, vol. 325 , 1767 -1804, 1991[2] Macfarlane P.W. “Recent developments in computer analysisof ECG s”, Clinical P hysiology, vol. 12 ( 1 992), 3 13-7[3] Bousseljot R. , .Aufbau der EKG-Datenbank CARDIODATder PTB (Setting-up of the ECG database CARDIODAT of

PTB). ,26th Annual Meeting of the Deutsche Gesellschaft fu r

Biomedizinische Technik, Biomedizinische Technik, vol. 39,Supplement 1 (1994), 250-251

Authors’ addresses

Dr. Ralf BousseljotDr. Dieter KreiselerPhysikalisch-TechnischeBundesanstalt

Labor 8.21Abbestrasse 2- 12

10587 Berlin, Germanye-mail: rbousseljot@biodat.berlin.ptb.de

e-mail: dkreiseler@biodat.berlin.ptb.de  

352