Tuomas Kenttä1, Kimmo Porthan2, Jani T Tikkanen1, Heikki Väänänen3, Lasse Oikarinen2, Matti Viitasalo2, Hannu Karanko4, Maarit Laaksonen4, Heikki V Huikuri1. 1. Medical Research Center Oulu, University of Oulu and University Hospital of Oulu, Oulu, Finland. 2. Division of Cardiology, Department of Medicine, Helsinki University Central Hospital, Helsinki, Finland. 3. Department of Biomedical Engineering and Computational Science, Aalto University, Helsinki, Finland. 4. National Institute for Health and Welfare, Helsinki, Finland.
Abstract
BACKGROUND: Early repolarization (ER) is defined as an elevation of the QRS-ST junction in at least two inferior or lateral leads of the standard 12-lead electrocardiogram (ECG). Our purpose was to create an algorithm for the automated detection and classification of ER. METHODS: A total of 6,047 electrocardiograms were manually graded for ER by two experienced readers. The automated detection of ER was based on quantification of the characteristic slurring or notching in ER-positive leads. The ER detection algorithm was tested and its results were compared with manual grading, which served as the reference. RESULTS: Readers graded 183 ECGs (3.0%) as ER positive, of which the algorithm detected 176 recordings, resulting in sensitivity of 96.2%. Of the 5,864 ER-negative recordings, the algorithm classified 5,281 as negative, resulting in 90.1% specificity. 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; only the electrocardiograms graded positive by the algorithm would be reviewed manually. This would reduce the need for manual labor by 90%.
BACKGROUND: Early repolarization (ER) is defined as an elevation of the QRS-ST junction in at least two inferior or lateral leads of the standard 12-lead electrocardiogram (ECG). Our purpose was to create an algorithm for the automated detection and classification of ER. METHODS: A total of 6,047 electrocardiograms were manually graded for ER by two experienced readers. The automated detection of ER was based on quantification of the characteristic slurring or notching in ER-positive leads. The ER detection algorithm was tested and its results were compared with manual grading, which served as the reference. RESULTS: Readers graded 183 ECGs (3.0%) as ER positive, of which the algorithm detected 176 recordings, resulting in sensitivity of 96.2%. Of the 5,864 ER-negative recordings, the algorithm classified 5,281 as negative, resulting in 90.1% specificity. 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; only the electrocardiograms graded positive by the algorithm would be reviewed manually. This would reduce the need for manual labor by 90%.
Authors: Jani T Tikkanen; Olli Anttonen; M Juhani Junttila; Aapo L Aro; Tuomas Kerola; Harri A Rissanen; Antti Reunanen; Heikki V Huikuri Journal: N Engl J Med Date: 2009-11-16 Impact factor: 91.245
Authors: Jani T Tikkanen; M Juhani Junttila; Olli Anttonen; Aapo L Aro; Samuli Luttinen; Tuomas Kerola; Solomon J Sager; Harri A Rissanen; Robert J Myerburg; Antti Reunanen; Heikki V Huikuri Journal: Circulation Date: 2011-05-31 Impact factor: 29.690
Authors: Peter A Noseworthy; Jani T Tikkanen; Kimmo Porthan; Lasse Oikarinen; Arto Pietilä; Kennet Harald; Gina M Peloso; Faisal M Merchant; Antti Jula; Heikki Väänänen; Shih-Jen Hwang; Christopher J O'Donnell; Veikko Salomaa; Christopher Newton-Cheh; Heikki V Huikuri Journal: J Am Coll Cardiol Date: 2011-05-31 Impact factor: 24.094
Authors: Arthur L Klatsky; Rudolph Oehm; Robert A Cooper; Natalia Udaltsova; Mary Anne Armstrong Journal: Am J Med Date: 2003-08-15 Impact factor: 4.965
Authors: Michel Haïssaguerre; Nicolas Derval; Frederic Sacher; Laurence Jesel; Isabel Deisenhofer; Luc de Roy; Jean-Luc Pasquié; Akihiko Nogami; Dominique Babuty; Sinikka Yli-Mayry; Christian De Chillou; Patrice Scanu; Philippe Mabo; Seiichiro Matsuo; Vincent Probst; Solena Le Scouarnec; Pascal Defaye; Juerg Schlaepfer; Thomas Rostock; Dominique Lacroix; Dominique Lamaison; Thomas Lavergne; Yoshifusa Aizawa; Anders Englund; Frederic Anselme; Mark O'Neill; Meleze Hocini; Kang Teng Lim; Sebastien Knecht; George D Veenhuyzen; Pierre Bordachar; Michel Chauvin; Pierre Jais; Gaelle Coureau; Genevieve Chene; George J Klein; Jacques Clémenty Journal: N Engl J Med Date: 2008-05-08 Impact factor: 91.245