Abstract
Point of care ECG devices can improve the early detection of atrial fibrillation (AF). The efficiency of such devices depends on the capability of automatic AF detection against normal sinus rhythm and other arrhythmias from a short single lead ECG record in the presence of noise and artifacts. The objective of this study was to develop an algorithm that classifies a short single lead ECG record into 'Normal', 'AF', 'Other' and 'Noisy' classes, and identify the challenges in developing such algorithms and potential mitigation steps. Rule-based identification was used to detect lead inversion and records too noisy to be of immediate use. A set of statistical and morphological features describing the rhythm was then extracted, and support vector machine classifiers were used to classify records into three classes: 'Normal', 'AF' or 'Other'. The algorithm was trained and tested using 12 186 short single lead ECGs recorded on a point of care device made available via the Computing in Cardiology Challenge 2017. The algorithm achieved a sensitivity of 77.5%, a specificity of 97.9% and an accuracy of 96.1% in the detection of AF from a non-AF rhythm in a five-fold cross validation. It achieved F1 measures of 89%, 78% and 67% for 'Norm...Continue Reading
References
Feb 1, 1994·Computers and Biomedical Research, an International Journal·P LagunaP Caminal
Jun 14, 2000·Circulation·A L GoldbergerH E Stanley
Jan 24, 2002·Medical & Biological Engineering & Computing·K Tateno, L Glass
Jan 8, 2008·Physiological Measurement·François Portet
Mar 13, 2008·IEEE Transactions on Bio-medical Engineering·Shantanu SarkarRahul Mehra
Jul 18, 2009·Journal of Electrocardiology·Saeed BabaeizadehSophia H Zhou
Dec 17, 2009·Biomedical Engineering Online·Jinho ParkMoongu Jeon
May 29, 2010·Stroke; a Journal of Cerebral Circulation·Hooman KamelS Claiborne Johnston
Nov 3, 2010·American Journal of Physiology. Heart and Circulatory Physiology·Douglas E Lake, J Randall Moorman
Aug 21, 2012·Physiological Measurement·G D CliffordI Rezek
Aug 30, 2012·IEEE Transactions on Bio-medical Engineering·Andrius PetrėnasArūnas Lukosevicius
Jul 9, 2013·The American Journal of Cardiology·Susan ColillaXianchen Liu
Nov 21, 2013·Annals of Noninvasive Electrocardiology : the Official Journal of the International Society for Holter and Noninvasive Electrocardiology, Inc·Xiaochuan DuXu Chen
Jun 10, 2014·Heart Rhythm : the Official Journal of the Heart Rhythm Society·Helmut PürerfellnerGerhard Hindricks
Jun 27, 2014·Clinical Epidemiology·Massimo Zoni-BerissoStefano Domenicucci
Jul 30, 2014·IEEE Journal of Biomedical and Health Informatics·Christina OrphanidouLionel Tarassenko
Dec 17, 2014·Medical & Biological Engineering & Computing·Andrius PetrėnasVaidotas Marozas
Nov 7, 2015·British Journal of Clinical Pharmacology·Christophe MombersAnnette Gilchrist
Feb 7, 2016·Cardiovascular Engineering and Technology·David T Linker
Jun 21, 2016·Physiological Measurement·M Rahimpour, B Mohammadzadeh Asl
Jul 28, 2016·Physiological Measurement·C DaluwatteC G Scully
Aug 28, 2016·European Heart Journal·Paulus KirchhofUNKNOWN ESC Scientific Document Group
Jun 5, 2018·Computing in Cardiology·Gari D CliffordRoger G Mark
Citations
May 11, 2020·Journal of Medical Systems·S K GhoshGanesh R Naik
Jul 1, 2020·Sensors·Daniele MarinucciLaura Burattini
Jan 14, 2021·Biomedical Physics & Engineering Express·Denis KleykoUrban Wiklund
Nov 22, 2019·Computers in Biology and Medicine·Italo Agustin MarsiliGiandomenico Nollo
Apr 27, 2021·Computational and Mathematical Methods in Medicine·Jingjing ShiQing Zhu
May 6, 2021·Computers in Biology and Medicine·Fons J WesseliusRichard C Hendriks
Apr 22, 2020·International Journal of Cardiology·Sarah W E BaalmanJoris R de Groot
Jul 3, 2021·Sensors·Hyeonjeong Lee, Miyoung Shin