LightX3ECG: A Lightweight and eXplainable Deep Learning System for 3-lead Electrocardiogram Classification

Wikipedia, 2020 Alday, 2020, Classification of 12-lead ECGs: The PhysioNet/Computing in cardiology challenge 2020, Physiol. Meas., 41 Park, 2022, Study on the use of standard 12-lead ECG data for rhythm-type ECG classification problems, Comput. Methods Programs Biomed., 214, 10.1016/j.cmpb.2021.106521 Hong, 2020, Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review, Comput. Biol. Med., 122, 10.1016/j.compbiomed.2020.103801 Teron, 2016, ECG holter monitor with alert system and mobile application Turakhia, 2013, Diagnostic utility of a novel leadless arrhythmia monitoring device, Am. J. Cardiol., 112, 10.1016/j.amjcard.2013.04.017 Chorba, 2021, Deep learning algorithm for automated cardiac murmur detection via a digital stethoscope platform, J. Am. Heart Assoc., 10, 10.1161/JAHA.120.019905 Marcus, 2020, The apple watch can detect atrial fibrillation: So what now?, Nat. Rev. Cardiol., 17, 10.1038/s41569-019-0330-y Bachtiger, 2022, Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: A prospective, observational, multicentre study, Lancet Digit. Health, 4 Guo, 2016, The future of remote ECG monitoring systems, J. Geriatr. Cardiol., 13 Webster, 2014 Levkov, 1987, Orthogonal electrocardiogram derived from the limb and chest electrodes of the conventional 12-lead system, Med. Biol. Eng. Comput., 25, 10.1007/BF02442844 Maheshwari, 2016, Frank vectorcardiographic system from standard 12 lead ECG: An effort to enhance cardiovascular diagnosis, J. Electrocardiol., 49, 10.1016/j.jelectrocard.2015.12.008 Karpagachelvi, 2010, ECG feature extraction techniques - A survey approach, Int. J. Comput. Sci. Inf. Secur., 8 Chandra, 2018, Feature extraction of ECG signal, J. Med. Eng. Technol., 42, 10.1080/03091902.2018.1492039 Somani, 2021, Deep learning and the electrocardiogram: Review of the current state-of-the-art, Europace, 23, 10.1093/europace/euaa377 LeCun, 2015, Deep learning, Nature, 521, 436, 10.1038/nature14539 Hu, 2020, Squeeze-and-excitation networks, IEEE Trans. Pattern Anal. Mach. Intell., 42, 10.1109/TPAMI.2019.2913372 Luong, 2015, Effective approaches to attention-based neural machine translation Chaudhari, 2021, An attentive survey of attention models, ACM Trans. Intell. Syst. Technol., 12, 10.1145/3465055 Kundu, 2021, AI in medicine must be explainable, Nat. Med., 27, 10.1038/s41591-021-01461-z Dosilovic, 2018, Explainable artificial intelligence: A survey Wang, 2022, A survey on deploying mobile deep learning applications: A systemic and technical perspective, Digit. Commun. Netw., 8 Acharya, 2017, A deep convolutional neural network model to classify heartbeats, Comput. Biol. Med., 89, 10.1016/j.compbiomed.2017.08.022 Zhang, 2021, Interpretable deep learning for automatic diagnosis of 12-lead electrocardiogram, iScience, 24 Zhu, 2021, Identification of 27 abnormalities from multi-lead ECG signals: An ensembled se-resnet framework with sign loss function, Physiol. Meas., 42, 10.1088/1361-6579/ac08e6 Yao, 2020, Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network, Inf. Fusion, 53, 10.1016/j.inffus.2019.06.024 Murugesan, 2018, ECGNet: Deep network for arrhythmia classification Li, 2018, A method to detect sleep apnea based on deep neural network and hidden Markov model using single-lead ECG signal, Neurocomputing, 294, 10.1016/j.neucom.2018.03.011 Santamaria-Granados, 2019, Using deep convolutional neural network for emotion detection on a physiological signals dataset (AMIGOS), IEEE Access, 7, 10.1109/ACCESS.2018.2883213 Attia, 2018, Noninvasive assessment of dofetilide plasma concentration using a deep learning (neural network) analysis of the surface electrocardiogram: A proof of concept study, PLoS ONE, 13, 10.1371/journal.pone.0201059 Rahman, 2022, Cov-ECGnet: COVID-19 detection using ECG trace images with deep convolutional neural network, Health Inf. Sci. Syst., 10, 10.1007/s13755-021-00169-1 Ozdemir, 2021, Classification of COVID-19 electrocardiograms by using hexaxial feature mapping and deep learning, BMC Med. Inform. Decis. Mak., 21, 10.1186/s12911-021-01521-x Deshmane, 2018, ECG based biometric human identification using convolutional neural network in smart health applications Hannun, 2019, Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network, Nat. Med., 25 Drew, 2002, Comparison of a new reduced lead set ECG with the standard ECG for diagnosing cardiac arrhythmias and myocardial ischemia, J. Electrocardiol., 35, 10.1054/jelc.2002.37150 Xue, 2007, Adapting ECG morphology changes from reduced-lead set by specifically trained algorithms for acute ischemia detection, Comput. Cardiol., 34 Green, 2007, Best leads in the standard electrocardiogram for the emergency detection of acute coronary syndrome, J. Electrocardiol., 40, 10.1016/j.jelectrocard.2006.12.011 Cho, 2020, Artificial intelligence algorithm for detecting myocardial infarction using six-lead electrocardiography, Sci. Rep., 10, 10.1038/s41598-020-77599-6 Hughes, 2021, Performance of a convolutional neural network and explainability technique for 12-lead electrocardiogram interpretation, JAMA Cardiol., 6, 10.1001/jamacardio.2021.2746 Anand, 2022, Explainable AI decision model for ECG data of cardiac disorders, Biomed. Signal Process. Control, 75, 10.1016/j.bspc.2022.103584 Ivanovs, 2021, Perturbation-based methods for explaining deep neural networks: A survey, Pattern Recognit. Lett., 150, 10.1016/j.patrec.2021.06.030 Selvaraju, 2020, Grad-CAM: Visual explanations from deep networks via gradient-based localization, Int. J. Comput. Vis., 128, 10.1007/s11263-019-01228-7 Vijayarangan, 2020, Interpreting deep neural networks for single-lead ECG arrhythmia classification Raza, 2022, Designing ECG monitoring healthcare system with federated transfer learning and explainable AI, Knowl.-Based Syst., 236, 10.1016/j.knosys.2021.107763 Ganeshkumar, 2021, Explainable deep learning-based approach for multilabel classification of electrocardiogram, IEEE Trans. Eng. Manage. Cheng, 2021, ECG signal classification based on deep CNN and bilstm, BMC Med. Inform. Decis. Mak., 21, 10.1186/s12911-021-01736-y Fawaz, 2020, Inceptiontime: Finding alexnet for time series classification, Data Min. Knowl. Discov., 34 Sandler, 2018, MobileNetV2: Inverted residuals and linear bottlenecks Howard, 2019, Searching for MobileNetV3 Panwar, 2020, A deep learning and grad-cam based color visualization approach for fast detection of COVID-19 cases using chest X-Ray and ct-scan images, Chaos Solitons Fractals, 140, 10.1016/j.chaos.2020.110190 Rajaraman, 2018, Understanding the learned behavior of customized convolutional neural networks toward malaria parasite detection in thin blood smear images, J. Med. Imaging, 5, 10.1117/1.JMI.5.3.034501 Carreira-Perpiñán, 2018, ’Learning-compression’ algorithms for neural net pruning Han, 2015, Learning both weights and connections for efficient neural networks Zheng, 2020, A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients, Sci. Data, 7, 10.1038/s41597-020-0386-x Liu, 2018, An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection, J. Med. Imag. Health Inform., 8 Kingma, 2015, Adam: A method for stochastic optimization Loshchilov, 2017, Sgdr: Stochastic gradient descent with warm restarts Gutierrez, 2011, Atrial fibrillation: Diagnosis and treatment, Am. Fam. Physician, 83 Surawicz, 2008 Barold, 2006, First-degree atrioventricular block: Clinical manifestations, indications for pacing, pacemaker management & consequences during cardiac resynchronization, J. Interv. Cardiac Electrophysiol., 17 Goldberger, 2017 Alventosa-Zaidin, 2019, Right bundle branch block: Prevalence, incidence, and cardiovascular morbidity and mortality in the general population, Eur. J. Gen. Pract., 25, 10.1080/13814788.2019.1639667 Surawicz, 2009, AHA/ACCF/HRS recommendations for the standardization and interpretation of the electrocardiogram, Circulation, 119, 10.1161/CIRCULATIONAHA.108.191095 LITFL, 2022 Adebayo, 2018, Sanity checks for saliency maps Doshi-Velez, 2017 Yeh, 2019, On the (in)fidelity and sensitivity of explanations