What are the sensitivity and specificity of computer-generated ECG interpretation? What is the most common reason cardiologists disagree with such interpretation?
—Harry Ballantyne, PA-C, Odenton, Md.
Computer-generated ECG interpretations have shown lower accuracy than those of clinician interpreters and should be relied on only as an adjunct tool for a trained provider. Among expert electrocardiographers, interpretations of the same ECG can vary substantially. Repeat interpretation of the same ECG by the same cardiologist is also subject to variations, as is repeat computer analysis.
Comparisons of the accuracy of computer ECG analysis with that of expert electrocardiographers demonstrate 58%-94% of disorders are classified correctly, with arrhythmias being the most problematic diagnosis. Sensitivity is lowest for ST-segment or wave changes (83.1%). This represents the most common category of misinterpretation, with a false-negative rate of nearly 17%. Due to the variations in interpretation, there can be more than one common disagreement. The following are a few examples of the sensitivity and specificity of computer analysis of ECG from various studies worldwide: infarction (sensitivity: 86.5%; specificity: 93.9%); arrhythmias and atrioventricular nodal block (sensitivity: 89%; specificity: 90.5%); ST-wave changes (sensitivity: 83.1%; specificity: 84.1%); ventricular hypertrophy (sensitivity: 94%; specificity: 84.3%); and detection of abnormal ECGs (sensitivity: 87.4%; specificity: 83.5%).
For more information, see Ann Intern Med. 2003;138:747-750 and Ann Intern Med. 2003;138: 751-760.
—Debra Kleinschmidt, PhD, PA (99-5)