Lead ECG

Lead ECG analysis, focusing on extracting diagnostic information from a single lead rather than the standard 12-lead ECG, is a rapidly advancing field driven by the need for convenient and accessible cardiovascular monitoring. Research heavily utilizes deep learning models, particularly convolutional neural networks and variations like U-Nets and masked autoencoders, to reconstruct full 12-lead ECGs from single-lead data, estimate key intervals (PR, QRS, QT), and predict various cardiac and non-cardiac conditions. This work is significant because it enables wider deployment of ECG-based diagnostics through wearable devices and improves the efficiency of existing clinical workflows, potentially leading to earlier detection and better management of cardiovascular diseases.

Papers

October 11, 2024

Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture
Sehun Kim
Lead ECG Canine Electrocardiogram Joint Embedding Predictive Architecture General Purpose Representation Learning

August 12, 2024

Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models
Ridwan Alam, Collin Stultz
Supervised Learning External Validation ECG Signal Lead ECG Canine Electrocardiogram Day Lead 12 Lead ECG Monitoring System

July 16, 2024

Multi-Channel Masked Autoencoder and Comprehensive Evaluations for Reconstructing 12-Lead ECG from Arbitrary Single-Lead ECG
Jiarong Chen, Wanqing Wu, Tong Liu, Shenda Hong
Comprehensive Evaluation Electrocardiogram Signal Lead ECG 12 Lead Masked Autoencoder

May 31, 2024

ECGrecover: a Deep Learning Approach for Electrocardiogram Signal Completion
Alex Lence, Ahmad Fall, Federica Granese, Blaise Hanczar, Joe-Elie Salem, Jean-Daniel Zucker, Edi Prifti
Deep Learning Approach Electrocardiogram Signal Single Lead Electrocardiogram Data ECG Signal Lead ECG Paper Electrocardiogram

December 18, 2023

Prospects for AI-Enhanced ECG as a Unified Screening Tool for Cardiac and Non-Cardiac Conditions -- An Explorative Study in Emergency Care
Nils Strodthoff, Juan Miguel Lopez Alcaraz, Wilhelm Haverkamp
Adverse Condition Lead ECG ECG Analysis Emergency Department Feature Screening

December 17, 2023

Detecting QT prolongation From a Single-lead ECG With Deep Learning
Ridwan Alam, Aaron Aguirre, Collin Stultz
Deep Learning Lead ECG

November 27, 2023

Riemannian Prediction of Anatomical Diagnoses in Congenital Heart Disease based on 12-lead ECGs
Muhammet Alkan, Gruschen Veldtman, Fani Deligianni
Anatomical Structure Riemannian Geometry Lead ECG Riemannian Geometry Approach Covariance Neural Network

October 10, 2023

CarDS-Plus ECG Platform: Development and Feasibility Evaluation of a Multiplatform Artificial Intelligence Toolkit for Portable and Wearable Device Electrocardiograms
Sumukh Vasisht Shankar, Evangelos K Oikonomou, Rohan Khera
Multi Modal Development Activity Task Feasibility Health Monitoring Lead ECG Wearable Single Lead Electrocardiogram

September 28, 2023

End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks
Theogene Habineza, Antônio H. Ribeiro, Daniel Gedon, Joachim A. Behar, Antonio Luiz P. Ribeiro, Thomas B. Schön
Deep Neural Network Risk Prediction Survival Model Atrial Fibrillation Single Lead Electrocardiogram Data Lead ECG Cardiac Arrhythmia

March 7, 2023

ECG Classification System for Arrhythmia Detection Using Convolutional Neural Networks
Aryan Odugoudar, Jaskaran Singh Walia
Deep Learning Convolutional Neural Network ECG Signal Lead ECG Arrhythmia Detection MIT BIH Arrhythmia Cardiac Arrhythmia

January 28, 2023

MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring
Yuzhen Qin, Li Sun, Hui Chen, Wei-qiang Zhang, Wenming Yang, Jintao Fei, Guijin Wang
High Efficiency Multi Label Single Lead Electrocardiogram Data Lead ECG ECG Classification Multi Disease

November 29, 2022

MedalCare-XL: 16,900 healthy and pathological 12 lead ECGs obtained through electrophysiological simulations
Karli Gillette, Matthias A. F. Gsell, Claudia Nagel, Jule Bender, Bejamin Winkler, Steven E. Williams, Markus Bär, Tobias Schäffter, Olaf Dössel, Gernot Plank, Axel Loewe
Lead ECG Synthetic Signal Synthetic Electrocardiogram Cardiac Model

November 18, 2022

EEG aided boosting of single-lead ECG based sleep staging with Deep Knowledge Distillation
Vaibhav Joshi, Sricharan V, Preejith SP, Mohanasankar Sivaprakasam
Brain Electroencephalography Token Boosting Sleep Staging Lead ECG Sleep Monitoring

November 2, 2022

Interpretable estimation of the risk of heart failure hospitalization from a 30-second electrocardiogram
Sergio González, Wan-Ting Hsieh, Davide Burba, Trista Pei-Chun Chen, Chun-Li Wang, Victor Chien-Chia Wu, Shang-Hung Chang
Machine Learning Model High Quality Risk Description Explainable Model Lead ECG Heart Failure Predictive Power Failure Time Model

September 30, 2022

Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
Thinh Phan, Duc Le, Patel Brijesh, Donald Adjeroh, Jingxian Wu, Morten Olgaard Jensen, Ngan Le
Self Supervised Learning Electrocardiogram Classification Lead ECG Canine Electrocardiogram Electrocardiogram Arrhythmia

August 5, 2022

A novel deep learning-based approach for sleep apnea detection using single-lead ECG signals
Anh-Tu Nguyen, Thao Nguyen, Huy-Khiem Le, Huy-Hieu Pham, Cuong Do
Long Form Novel Single Lead Electrocardiogram Data Lead ECG Electrocardiogram Feature Sleep Apnea

August 2, 2022

GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction
Jiacheng Zhu, Jielin Qiu, Zhuolin Yang, Douglas Weber, Michael A. Rosenberg, Emerson Liu, Bo Li, Ding Zhao
Data Augmentation Electrocardiogram Signal Electrocardiogram Classification Lead ECG 12 Lead Wasserstein Geodesic

July 25, 2022

LightX3ECG: A Lightweight and eXplainable Deep Learning System for 3-lead Electrocardiogram Classification
Khiem H. Le, Hieu H. Pham, Thao BT. Nguyen, Tu A. Nguyen, Tien N. Thanh, Cuong D. Do
Lightweight High Lead ECG Canine Electrocardiogram ECG Classification Explainable Deep Learning 12 Lead

July 13, 2022

On Merging Feature Engineering and Deep Learning for Diagnosis, Risk-Prediction and Age Estimation Based on the 12-Lead ECG
Eran Zvuloni, Jesse Read, Antônio H. Ribeiro, Antonio Luiz P. Ribeiro, Joachim A. Behar
Deep Learning Risk Prediction Feature Engineering Age Estimation Single Lead Electrocardiogram Data Lead ECG 12 Lead Physiological Time Series

April 29, 2022

A Mixed-Domain Self-Attention Network for Multilabel Cardiac Irregularity Classification Using Reduced-Lead Electrocardiogram
Hao-Chun Yang, Wan-Ting Hsieh, Trista Pei-Chun Chen
Multi Label Lead ECG

Lead ECG

Papers

Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture

Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models

Multi-Channel Masked Autoencoder and Comprehensive Evaluations for Reconstructing 12-Lead ECG from Arbitrary Single-Lead ECG

ECGrecover: a Deep Learning Approach for Electrocardiogram Signal Completion

Prospects for AI-Enhanced ECG as a Unified Screening Tool for Cardiac and Non-Cardiac Conditions -- An Explorative Study in Emergency Care

Detecting QT prolongation From a Single-lead ECG With Deep Learning

Riemannian Prediction of Anatomical Diagnoses in Congenital Heart Disease based on 12-lead ECGs

CarDS-Plus ECG Platform: Development and Feasibility Evaluation of a Multiplatform Artificial Intelligence Toolkit for Portable and Wearable Device Electrocardiograms

End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks

ECG Classification System for Arrhythmia Detection Using Convolutional Neural Networks

MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring

MedalCare-XL: 16,900 healthy and pathological 12 lead ECGs obtained through electrophysiological simulations

EEG aided boosting of single-lead ECG based sleep staging with Deep Knowledge Distillation

Interpretable estimation of the risk of heart failure hospitalization from a 30-second electrocardiogram

Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning

A novel deep learning-based approach for sleep apnea detection using single-lead ECG signals

GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction

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

On Merging Feature Engineering and Deep Learning for Diagnosis, Risk-Prediction and Age Estimation Based on the 12-Lead ECG

A Mixed-Domain Self-Attention Network for Multilabel Cardiac Irregularity Classification Using Reduced-Lead Electrocardiogram