Abstract 10720: Automatic Detection of Early Repolarization in Standard 12-Lead Electrocardiography
Purpose: Early repolarization pattern (ER), is defined as an elevation of the QRS-ST junction in at least two inferior (II, III, aVF) or lateral (I, aVL, V4-V6) leads of standard 12-lead electrocardiogram. Its detection is based on visual assessment of the earliest QRS offset in any of the twelve leads, which makes the manual screening of ER time-consuming and cumbersome. Also, the prevalence of ER is generally low. Therefore, we created an automatic algorithm for the detection and classification of ER.
Methods: A total of 6,047 electrocardiograms from the Health 2000 Survey, which is a cross-sectional, population-based cohort, were graded manually by two experienced readers. The automatic algorithm was based on the quantification of the characteristic slurring/notching of ER positive leads. Notched leads were detected by local peak detection and slurred leads by yield point amplitude (point where the slurring begins), terminal slope and terminal QRS area measurements (see Figure). Each inferior and lateral lead was classified into one of the following categories: negative, notched, discrete or slurred. Finally, the results from the readers were compared with those of the automatic algorithm.
Results: Readers graded 183 recordings (3.0%) as ER positive, out of which the automatic algorithm detected 176 recordings, resulting in sensitivity of 96.2%. A total of 583 (9.6%) ER negative recordings were misclassified as positive by the algorithm, resulting in specificity of 90.1%. Positive and negative predictive values for the algorithm were 23.2% and 99.9%, respectively, and its accuracy was 90.2%. Inferior ER was correctly detected in 84.6% and lateral ER in 98.6% of the cases.
Conclusions: As the automatic algorithm has high sensitivity, it could be used as a prescreening tool for ER; electrocardiograms graded positive by the algorithm would be reviewed manually. This would reduce the need for manual labor to one tenth of the original.
- © 2013 by American Heart Association, Inc.