Abstract
Artificial neural networks (ANNs) have proved to be of value in pattern recognition tasks, e.g. classification of electrocardiograms (ECGs). Electrocardiographic lead reversals are often overlooked by ECG readers, and may cause incorrect ECG interpretation, misdiagnosis and subsequent lack of proper treatment. A database of 11000 ECGs from an emergency department, which had been purified from technically deficient ECGs as well as ECGs with lead reversals were used in the study. The same database was used to generate by computer two subsets of 11000 ECGs, one consistent with right arm/left foot lead reversal and one with left arm/left foot lead reversal. After training, the networks detected 57.6% of the ECGs with left arm/left foot lead reversal and 80.5% of the ECGs with right arm/left foot lead reversal. The specificities were 99.97% and 99.95% respectively. The results show that ANNs can be trained to detect ECG lead reversals at very high specificity.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
