ElectroCardioGuard: Preventing Patient Misidentification in Electrocardiogram Databases through Neural Networks (2023-06-09T00:00:00.000000Z)

TL;DR

A small and efficient neural-network based model for determining whether two ECGs originate from the same patient is proposed, which demonstrates great generalization capabilities and achieves state-of-the-art performance in gallery-probe patient identification on PTB-XL while utilizing 760x fewer parameters.

Abstract

Electrocardiograms (ECGs) are commonly used by cardiologists to detect heart-related pathological conditions. Reliable collections of ECGs are crucial for precise diagnosis. However, in clinical practice, the assignment of captured ECG recordings to incorrect patients can occur inadvertently. In collaboration with a clinical and research facility which recognized this challenge and reached out to us, we present a study that addresses this issue. In this work, we propose a small and efficient neural-network based model for determining whether two ECGs originate from the same patient. Our model demonstrates great generalization capabilities and achieves state-of-the-art performance in gallery-probe patient identification on PTB-XL while utilizing 760x fewer parameters. Furthermore, we present a technique leveraging our model for detection of recording-assignment mistakes, showcasing its applicability in a realistic scenario. Finally, we evaluate our model on a newly collected ECG dataset specifically curated for this study, and make it public for the research community.

Authors

Michal Seják

1 papers

Jakub Sido

1 papers

David Zahour

1 papers

TL;DR

Abstract

Authors

References63 items

Simplified State Space Layers for Sequence Modeling

ECG Biometric Recognition: Review, System Proposal, and Benchmark Evaluation

An ECG Biometric System Using Hierarchical LSTM With Attention Mechanism

Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogram

Personal Identification Using an Ensemble Approach of 1D-LSTM and 2D-CNN with Electrocardiogram Signals

Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks

System for Neural Network Determination of Atrial Fibrillation on ECG Signals with Wavelet-Based Preprocessing

3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations

R-Peak Identification in ECG Signals using Pattern-Adapted Wavelet Technique

Intellectual heartbeats classification model for diagnosis of heart disease from ECG signal using hybrid convolutional neural network with GOA

An LSTM-Based Model for Person Identification Using ECG Signal

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

ECG Identification For Personal Authentication Using LSTM-Based Deep Recurrent Neural Networks

CLOCS: Contrastive Learning of Cardiac Signals

PTB-XL, a large publicly available electrocardiography dataset

Robust ECG R-peak detection using LSTM

ResNet‐Attention model for human authentication using ECG signals

An efficient removal of power-line interference and baseline wander from ECG signals by employing Fourier decomposition technique

R-peak detection based chaos analysis of ECG signal

Circle Loss: A Unified Perspective of Pair Similarity Optimization

A Simple Framework for Contrastive Learning of Visual Representations

Deep-ECG: Convolutional Neural Networks for ECG biometric recognition

Deep Metric Learning: A Survey

Biometric human recognition system based on ECG

ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks

Electrocardiogram Classification Based on Faster Regions with Convolutional Neural Network

Automatic diagnosis of the 12-lead ECG using a deep neural network

ECG-Based Advanced Personal Identification Study With Adjusted (Qi * Si)

A Novel Approach to ECG R-Peak Detection

ECG Based Biometric Human Identification Using Convolutional Neural Network in Smart Health Applications

Person Re-identification with Deep Similarity-Guided Graph Neural Network

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Effective Feature Extraction of ECG for Biometric Application

An Adaptive and Time-Efficient ECG R-Peak Detection Algorithm

Attention is All you Need

Genetic algorithm for the optimization of features and neural networks in ECG signals classification

The application of supervised learning through feed-forward neural networks for ECG signal classification

Deep Residual Learning for Image Recognition

Hardware Design and Implementation of a Wavelet De-Noising Procedure for Medical Signal Preprocessing

FaceNet: A unified embedding for face recognition and clustering

Deep Metric Learning Using Triplet Network

Check Your Biosignals Here: A new dataset for off-the-person ECG biometrics

ECG analysis for person identification

Clothing-invariant gait identification using part-based clothing categorization and adaptive weight control

ECG based personal identification using extended Kalman filter

ECG Feature Extraction Techniques - A Survey Approach

ECG personal identification in subspaces using radial basis neural networks

PhysioBank

Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet

Model-Based Face De-Identification

Human Identification System Based ECG Signal

The impact of the MIT-BIH Arrhythmia Database

ECG analysis: a new approach in human identification

Long Short-Term Memory

Assessing the Reidentification Risks Posed by Deep Learning Algorithms Applied to ECG Data

Randbehandlung bei Wavelets für Faltungsnetzwerke

Multimodal Biometric Authentication Systems Using Convolution Neural Network Based on Different Level Fusion of ECG and Fingerprint

FILTERING TECHNIQUES FOR ECG SIGNAL PROCESSING

Custom Pictorial Structures for Re-identification

IEEE international workshop on intelligent data acquisition and advanced computing systems: technology and applications

Biometric human identification based on electrocardiogram

Physionet: components of a new research resource for complex physiologic signals

Cpu benchmarks

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names