Scholarlink

<p>Interpretable, automated Artificial Intelligence (AI) solutions are essential for accurate 12-lead electrocardiogram (ECG) arrhythmia classification because they remove the time-consuming and inconsistent aspects of manual interpretation. Current models are limited in complexity, data variety, and validation. This paper proposes a novel Deep Learning (DL) architecture that combines Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (Bi-LSTMs), and transformer layers to jointly extract morphological, temporal, and spatial patterns from ECG signals. The model was trained and evaluated on the PhysioNet/Computing in Cardiology Challenge 2020 dataset, comprising more than 43,000 multi-label ECG recordings across 27 arrhythmia classes. It achieved an accuracy of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\:91.24\%\)</EquationSource> </InlineEquation>, a macro-F1 score of <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\:83.01\%\)</EquationSource> </InlineEquation>, and an Area Under the ROC Curve (AUC) exceeding <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\:0.98\)</EquationSource> </InlineEquation> for life-threatening arrhythmias such as Ventricular Premature Beats (VPB) and Atrial Fibrillation (AF). To ensure clinical transparency, the model integrates SHAP (SHAPley Additive exPlanations), enabling case-by-case interpretability by attributing predictions to physiologically relevant waveform segments and ECG leads. This approach aligns with cardiologists’ diagnostic reasoning and supports real-world decision-making. Additionally, the model is computationally efficient, with a footprint of <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\:&lt;2\:MB\)</EquationSource> </InlineEquation> and inference latency of <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(\:&lt;10\:ms\)</EquationSource> </InlineEquation>, enabling deployment in telemedicine, wearable monitoring systems, and critical care settings. The proposed framework achieves high diagnostic performance, robustness to class imbalance, and human-level interpretability simultaneously, providing a reliable, scalable solution for automated ECG analysis. These findings advance the application of explainable DL algorithms in cardiovascular diagnostics.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A joint CNN-Bi-LSTM-transformer architecture with SHAP explanations for multi-label arrhythmia detection from 12-lead ECGs

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月26日

查看全文
  • Mohammed T. Al-Bairmani,
  • Mohammadreza Yazdchi,
  • Fahimeh Nasimi

摘要

Interpretable, automated Artificial Intelligence (AI) solutions are essential for accurate 12-lead electrocardiogram (ECG) arrhythmia classification because they remove the time-consuming and inconsistent aspects of manual interpretation. Current models are limited in complexity, data variety, and validation. This paper proposes a novel Deep Learning (DL) architecture that combines Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (Bi-LSTMs), and transformer layers to jointly extract morphological, temporal, and spatial patterns from ECG signals. The model was trained and evaluated on the PhysioNet/Computing in Cardiology Challenge 2020 dataset, comprising more than 43,000 multi-label ECG recordings across 27 arrhythmia classes. It achieved an accuracy of \(\:91.24\%\) , a macro-F1 score of \(\:83.01\%\) , and an Area Under the ROC Curve (AUC) exceeding \(\:0.98\) for life-threatening arrhythmias such as Ventricular Premature Beats (VPB) and Atrial Fibrillation (AF). To ensure clinical transparency, the model integrates SHAP (SHAPley Additive exPlanations), enabling case-by-case interpretability by attributing predictions to physiologically relevant waveform segments and ECG leads. This approach aligns with cardiologists’ diagnostic reasoning and supports real-world decision-making. Additionally, the model is computationally efficient, with a footprint of \(\:<2\:MB\) and inference latency of \(\:<10\:ms\) , enabling deployment in telemedicine, wearable monitoring systems, and critical care settings. The proposed framework achieves high diagnostic performance, robustness to class imbalance, and human-level interpretability simultaneously, providing a reliable, scalable solution for automated ECG analysis. These findings advance the application of explainable DL algorithms in cardiovascular diagnostics.