IKrNet: A Neural Network for Detecting Specific Drug-Induced Patterns in Electrocardiograms Amidst Physiological Variability

TL;DR

IKrNet is a neural network designed to detect drug-specific ECG patterns accurately across diverse physiological states, improving clinical assessment of cardiac health amidst variability caused by drugs, activity, and stress.

Contribution

The paper introduces IKrNet, a novel neural network architecture that effectively captures spatial and temporal ECG features to identify drug-induced patterns under physiological variability.

Findings

IKrNet outperforms existing models in accuracy and stability.

Evaluation on 990 volunteers shows robustness across different conditions.

Demonstrates clinical viability for real-world ECG analysis.

Abstract

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.