Our study shows that some but not all computer programs for the interpretation of ECGs perform almost as well as cardiologists in identifying seven major cardiac disorders.

In order to determine the value of cardiokymography in detecting left ventricular (LV) anterior wall asynergies, 80 consecutive patients had a cardiokymogram (CKG) and an electrocardiogram (ECG) on the day prior to coronary angiography. Technically adequate CKGs were obtained in 72 patients (67 men and 5 women, mean age 53 ± 6.5 years). For validation of regional contraction abnormalities, quantitative LV angiography was used. Stepwise linear discriminant analysis was applied to investigate the diagnostic power of CKG. Sensitivity of the CKG for LV anterior wall asynergy was 67.9% (ECG: 39.6%) and specificity was 68.4% (ECG: 94.7%) on the basis of 1 SD of the mean values of the radial axis shortening of a control group. For 2 SD, the sensitivity was 65.6% (ECG: 56.3%) and the specificity 47.5% (ECG: 90%). By combined testing, the specificity increased to 98.3%, whereas the sensitivity dropped to 26.9%. The improvement of the post-test likelihood for a positive ECG by a positive CKG is especially pronounced in the intermediate prevalence range, wheras for a negative ECG the post-test likelihood can be further decreased by a negative CKG in the intermediate and high prevalence range. The ECG as a single test seems to be the more appropriate noninvasive method for detecting LV anterior wall asynergies; however, the combined use of both ECG and CKG may considerably improve the diagnostic accuracy.

No abstract

No 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.