Methods Inf Med 1990; 29(04): 308-316
DOI: 10.1055/s-0038-1634794
ECG Interpretation Systems
Schattauer GmbH

Evaluation of ECG Interpretation Results Obtained by Computer and Cardiologists[*]

J. L. Willems
1   CSE Coordinating Center, Univ. of Leuven, Belgium
,
C. Abreu-Lima
2   Department of Cardiology, University of Porto, Portugal
,
P. Arnaud
3   INSEPvM, Unité 121, Hôp. Cardiovasculaire, Lyon, France
,
C. R. Brohet
4   Department of Cardiology, University of Louvain, Brussels, Belgium
,
B. Denis
5   Service de Cardiologie, Univ. of Grenoble, France
,
J. Gehring
6   Clinic for Cardiovascular Diseases, Höhenried, Federal Republic of Germany
,
I. Graham
7   Adelaide Hospital, Dublin, Ireland
,
G. van Herpen
8   University Hospital, Leiden, The Netherlands
,
H. Machado
9   University Hospital Santa Maria, Lisbon, Portugal
,
J. Michaelis
10   Institut für Medizinische Statistik und Dokumentation, Mainz, Federal Republic of Germany
,
S. D. Moulopoulos
11   Department of Therapeutics, University of Athens, Athens, Greece
› Institutsangaben
The research presented in this paper has been supported by the European Commission within the frame of its 2nd, 3rd and 4th Medical and Public Health Research Programmes of DG XII, Section Biomedical Engineering, and by various funding agencies in ten Member States of the European Community. The authors are grateful to Ms. I. Tassens for secretarial assistance and to Mr. I. Schoolmeesters for computer programming help.
Weitere Informationen

Publikationsverlauf

Publikationsdatum:
06. Februar 2018 (online)

Zoom Image

Abstract

In an international project investigators from 25 institutes are trying to establish a common reference library and evaluation methods for testing the diagnostic performance of various ECG computer programs and of cardiologists, based on ECG-independent clinical information. A first set of 500 validated ECGs was collected and analyzed by fifteen different computer programs and nine cardiologists, seven of who analysed the ECG and five the VCG. A coding scheme was used to map individual diagnostic statements onto a common set. Combined program and referee results were obtained by weighted averaging. Preliminary results indicate that the classification accuracy of several programs can still be improved. However, it was also apparent that the results of the best 12-lead ECG computer programs proved to be almost as accurate as the best of seven cardiologists in classifying seven main disease categories, i.e., normal, left, right and biventricular hypertrophy, anterior, inferior and combined myocardial infarction. Evaluation of rhythm statements and conduction disturbances was not included in the study. The data collection is still being pursued in order to reach over 1,000 cases. In this way a common diagnostic database is being established for comparative testing of diagnostic computer programs. This should lead to consumer protection and improve the accuracy and reliability of computerized electrocardiography.

* For the CSE Working Party