Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fall, Ahmad, Granese, Federica, Lence, Alex, Fourer, Dominique, Hanczar, Blaise, Salem, Joe-Elie, Zucker, Jean-Daniel, Prifti, Edi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.07533
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913832682651648
author Fall, Ahmad
Granese, Federica
Lence, Alex
Fourer, Dominique
Hanczar, Blaise
Salem, Joe-Elie
Zucker, Jean-Daniel
Prifti, Edi
author_facet Fall, Ahmad
Granese, Federica
Lence, Alex
Fourer, Dominique
Hanczar, Blaise
Salem, Joe-Elie
Zucker, Jean-Daniel
Prifti, Edi
contents Monitoring and analyzing electrocardiogram (ECG) signals, even under varying physiological conditions, including those influenced by physical activity, drugs and stress, is crucial to accurately assess cardiac health. However, current AI-based methods often fail to account for how these factors interact and alter ECG patterns, ultimately limiting their applicability in real-world settings. This study introduces IKrNet, a novel neural network model, which identifies drug-specific patterns in ECGs amidst certain physiological conditions. IKrNet's architecture incorporates spatial and temporal dynamics by using a convolutional backbone with varying receptive field size to capture spatial features. A bi-directional Long Short-Term Memory module is also employed to model temporal dependencies. By treating heart rate variability as a surrogate for physiological fluctuations, we evaluated IKrNet's performance across diverse scenarios, including conditions with physical stress, drug intake alone, and a baseline without drug presence. Our assessment follows a clinical protocol in which 990 healthy volunteers were administered 80mg of Sotalol, a drug which is known to be a precursor to Torsades-de-Pointes, a life-threatening arrhythmia. We show that IKrNet outperforms state-of-the-art models' accuracy and stability in varying physiological conditions, underscoring its clinical viability.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07533
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IKrNet: A Neural Network for Detecting Specific Drug-Induced Patterns in Electrocardiograms Amidst Physiological Variability
Fall, Ahmad
Granese, Federica
Lence, Alex
Fourer, Dominique
Hanczar, Blaise
Salem, Joe-Elie
Zucker, Jean-Daniel
Prifti, Edi
Computer Vision and Pattern Recognition
Artificial Intelligence
Monitoring and analyzing electrocardiogram (ECG) signals, even under varying physiological conditions, including those influenced by physical activity, drugs and stress, is crucial to accurately assess cardiac health. However, current AI-based methods often fail to account for how these factors interact and alter ECG patterns, ultimately limiting their applicability in real-world settings. This study introduces IKrNet, a novel neural network model, which identifies drug-specific patterns in ECGs amidst certain physiological conditions. IKrNet's architecture incorporates spatial and temporal dynamics by using a convolutional backbone with varying receptive field size to capture spatial features. A bi-directional Long Short-Term Memory module is also employed to model temporal dependencies. By treating heart rate variability as a surrogate for physiological fluctuations, we evaluated IKrNet's performance across diverse scenarios, including conditions with physical stress, drug intake alone, and a baseline without drug presence. Our assessment follows a clinical protocol in which 990 healthy volunteers were administered 80mg of Sotalol, a drug which is known to be a precursor to Torsades-de-Pointes, a life-threatening arrhythmia. We show that IKrNet outperforms state-of-the-art models' accuracy and stability in varying physiological conditions, underscoring its clinical viability.
title IKrNet: A Neural Network for Detecting Specific Drug-Induced Patterns in Electrocardiograms Amidst Physiological Variability
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.07533