Why the study?
What is the accuracy of computer-generated electrocardiogram interpretations, and is cardiologist review necessary?
What is the accuracy of computer-generated electrocardiogram interpretations, and is cardiologist review necessary?
Computer-generated ECG interpretations have a high error rate (48.4%) and mandate review by an experienced electrocardiographer to prevent incorrect diagnoses and inappropriate management.
May support cardiologist review of computer ECGs; leaves open whether refined algorithms reduce errors in prospective studies.
A review of 6938 computer-generated electrocardiogram interpretations was undertaken by a single cardiologist. The computer-assisted program correctly interpreted 51.6% of the tracings. One or more corrections were necessary in 48.4%. The greatest number of incorrect interpretations involved repolarization (T wave) abnormalities, followed by ST segment changes. It is mandatory that computer-generated ECG interpretations be reviewed by an experienced electrocardiographer. Reliance on nonreviewed ECG interpretations may result in incorrect diagnoses that could lead to inappropriate management decisions.
No takes yet. Share an insight, caveat, or question.
RuDusky et al. (1997) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: