Employment of intra-individual variability to improve computerized ECG interpretation

One of the reasons for the limited practical utility of computer programs for interpretation of electrocardiograms (ECGs) is their susceptibility to intra-individual variability. Two of the most prominent sources of intra-individual variability in ECGs, electrode placement variations and respiration, were studied for their effects on computerized ECG interpretation. Previous research has shown that the effects of intra-individual variability on computerized ECG interpretation depend largely on the individual ECG. To enable the assessment of chest electrode position variations for individual standard 12- lead ECGs, ECGs resulting from simulations of such position variations were interpreted. Variability due to respiration was assessed by interpreting all individual ECG beats instead of an averaged beat. In this paper two methods are presented that employ information about the intra-individual variability in individual ECGs. The first method provides an estimate of the reliability of the interpretation, the second attempts to improve the interpretation itself. In the first method we quantified the variation in interpretation caused by the two sources of intra-individual variability with the use of a stability index, a high index value indicating a low variation in interpretation. This index was subsequently studied using two sets of ECGs. For the first set a â clinical' reference interpretation was obtained from discharge letters. For the second set three cardiologists provided a â cardiologists' reference. The performance of subgroups of ECGs having stability indices higher than a particular value was computed. It appeared that for the â cardiologists' reference, the interpretations of ECGs with a high stability index were more often correct. No effect was found for the â clinical' reference. In the second method we attempted to improve the original interpretation by combining the alternative interpretations into a new interpretation. This was done by taking the median or the average of the quantified alternatives. These combined interpretations proved to perform better than the original interpretation when a cardiologist's interpretation was taken as a reference. This paper shows that intra-individual ECG variability can be used to improve original interpretations. This can be done without having to record multiple ECGs, provided that a model is available to simulate intra-individual variability. The presented methods do not depend on the classification algorithm that is used. They can be used both during classifier design to correct imperfections, and in routine use of the classifier to produce more representative classifications.