AICRN: Attention-Integrated Convolutional Residual Network for Interpretable Electrocardiogram Analysis

2025-08-16

AI Summary

This study addresses the low accuracy and poor interpretability in regression of key electrocardiogram (ECG) parameters—namely PR, QT, and QRS intervals; heart rate; and R- and T-wave amplitudes. We propose AICRN, a novel interpretable deep learning model that integrates spatial and channel attention mechanisms into a convolutional residual network. This design jointly enhances modeling of temporally localized features and discriminative channel-wise responses, mitigating gradient vanishing while improving feature focus. Evaluated on multiple public ECG datasets, AICRN achieves statistically significant improvements across all six parameter regression tasks, reducing mean absolute error (MAE) by 12.6% on average over state-of-the-art methods. Crucially, AICRN delivers both high predictive accuracy and human-interpretable visualizations—e.g., attention heatmaps aligned with physiological landmarks—enabling transparent, real-time, automated ECG parameter monitoring and supporting clinical decision-making.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Interpretability, Explainability, and Transparency
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The paradigm of electrocardiogram (ECG) analysis has evolved into real-time digital analysis, facilitated by artificial intelligence (AI) and machine learning (ML), which has improved the diagnostic precision and predictive capacity of cardiac diseases. This work proposes a novel deep learning (DL) architecture called the attention-integrated convolutional residual network (AICRN) to regress key ECG parameters such as the PR interval, the QT interval, the QRS duration, the heart rate, the peak amplitude of the R wave, and the amplitude of the T wave for interpretable ECG analysis. Our architecture is specially designed with spatial and channel attention-related mechanisms to address the type and spatial location of the ECG features for regression. The models employ a convolutional residual network to address vanishing and exploding gradient problems. The designed system addresses traditional analysis challenges, such as loss of focus due to human errors, and facilitates the fast and easy detection of cardiac events, thereby reducing the manual efforts required to solve analysis tasks. AICRN models outperform existing models in parameter regression with higher precision. This work demonstrates that DL can play a crucial role in the interpretability and precision of ECG analysis, opening up new clinical applications for cardiac monitoring and management.

Problem

• Develops AICRN for interpretable ECG parameter regression
• Addresses vanishing gradients via convolutional residual network
• Improves ECG analysis precision and clinical applications

Innovation

• Attention-integrated convolutional residual network
• Spatial and channel attention mechanisms
• Convolutional residual network for gradient issues