Deep Neural Network Architectures for Electrocardiogram Classification: A Comprehensive Evaluation

• URL: http://arxiv.org/abs/2602.17701v1
• Date: Sat, 07 Feb 2026 06:56:50 GMT
• Title: Deep Neural Network Architectures for Electrocardiogram Classification: A Comprehensive Evaluation
• Authors: Yun Song, Wenjia Zheng, Tiedan Chen, Ziyu Wang, Jiazhao Shi, Yisong Chen,
• Abstract summary: This study presents a comprehensive evaluation of deep neural network architectures for automated arrhythmia classification.<n>To address data scarcity in minority classes, the MIT-BIH Arrhythmia dataset was augmented using a Generative Adversarial Network (GAN)<n>We developed and compared four distinct architectures, including Convolutional Neural Networks (CNN), CNN combined with Long Short-Term Memory (CNN-LSTM), CNN-LSTM with Attention, and 1D Residual Networks (ResNet-1D)
• Score: 7.708113178862228
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rising prevalence of cardiovascular diseases, electrocardiograms (ECG) remain essential for the non-invasive detection of cardiac abnormalities. This study presents a comprehensive evaluation of deep neural network architectures for automated arrhythmia classification, integrating temporal modeling, attention mechanisms, and ensemble strategies. To address data scarcity in minority classes, the MIT-BIH Arrhythmia dataset was augmented using a Generative Adversarial Network (GAN). We developed and compared four distinct architectures, including Convolutional Neural Networks (CNN), CNN combined with Long Short-Term Memory (CNN-LSTM), CNN-LSTM with Attention, and 1D Residual Networks (ResNet-1D), to capture both local morphological features and long-term temporal dependencies. Performance was rigorously evaluated using accuracy, F1-score, and Area Under the Curve (AUC) with 95\% confidence intervals to ensure statistical robustness, while Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to validate model interpretability. Experimental results indicate that the CNN-LSTM model achieved the optimal stand-alone balance between sensitivity and specificity, yielding an F1-score of 0.951. Conversely, the CNN-LSTM-Attention and ResNet-1D models exhibited higher sensitivity to class imbalance. To mitigate this, a dynamic ensemble fusion strategy was introduced; specifically, the Top2-Weighted ensemble achieved the highest overall performance with an F1-score of 0.958. These findings demonstrate that leveraging complementary deep architectures significantly enhances classification reliability, providing a robust and interpretable foundation for intelligent arrhythmia detection systems.

Related papers

• How Much Temporal Modeling is Enough? A Systematic Study of Hybrid CNN-RNN Architectures for Multi-Label ECG Classification [1.8119312186036625]
  We evaluate the necessity and clinical justification of deep and stacked recurrent architectures for ECG classification.<n>A CNN integrated with a single BiLSTM layer achieves the most favorable trade-off between predictive performance and model complexity.<n>These findings suggest that architectural alignment with the intrinsic temporal structure of ECG signals, rather than increased recurrent depth, is a key determinant of robust performance.
  arXiv  Detail & Related papers  (2026-01-25T17:29:13Z)
• A Lightweight CNN-Attention-BiLSTM Architecture for Multi-Class Arrhythmia Classification on Standard and Wearable ECGs [0.37331950863394864]
  We propose a lightweight deep learning model combining 1D Convolutional Neural Networks (CNN), attention mechanisms, and Bidirectional Long Short-Term Memory (BiLSTM) for classifying arrhythmias from both 12-lead and single-lead ECGs.<n>With only 0.945 million parameters, our model is well-suited for real-time deployment in wearable health monitoring systems.
  arXiv  Detail & Related papers  (2025-11-11T05:25:58Z)
• BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait Prediction [33.650792366699385]
  Functional and structural connectivity (FC/SC) are key biomarkers for brain analysis, yet their clinical utility is hindered by costly acquisition, complex preprocessing, and frequent missing modalities.<n>We propose BrainCSD, a hierarchical mixture-of-experts foundation model that jointly synthesizes FC/SC biomarkers and supports downstream decoding tasks (diagnosis and prediction)<n>BrainCSD achieves 95.6%% accuracy for MCI vs. CN classification without FC, low error synthesis (FC RMSE: 0.038; SC RMSE: 0.006), brain age prediction (MAE: 4.04 years), and MMSE score (MAE: 1.72 points
  arXiv  Detail & Related papers  (2025-11-07T04:40:47Z)
• H-Infinity Filter Enhanced CNN-LSTM for Arrhythmia Detection from Heart Sound Recordings [0.7394388288509157]
  Early detection of heart arrhythmia can prevent severe future complications in cardiac patients.<n>Deep learning has emerged as a powerful tool to automate arrhythmia detection.<n>A novel CNN-H-Infinity-LSTM architecture is proposed to identify arrhythmic heart signals from heart sound recordings.
  arXiv  Detail & Related papers  (2025-11-04T09:00:17Z)
• Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation [30.94379425064039]
  We introduce the Predictive-Corrective (PC) paradigm, a framework that decouples the modeling task to fundamentally accelerate learning.<n>PCambaNet is composed of two synergistic modules. First, the Predictive Prior Module (PPM) generates a coarse approximation at low computational cost.<n>Next, the Corrective Residual Network (CRN) learns to model the residual error, focusing the network's full capacity on refining these challenging regions.
  arXiv  Detail & Related papers  (2025-10-17T08:51:33Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• Benchmarking Foundation Models and Parameter-Efficient Fine-Tuning for Prognosis Prediction in Medical Imaging [40.35825564674249]
  This study introduces the first structured benchmark to assess the robustness and efficiency of transfer learning strategies for Foundation Models.<n>Four publicly available COVID-19 chest X-ray datasets were used, covering mortality, severity, and admission.<n>CNNs pretrained on ImageNet and FMs pretrained on general or biomedical datasets were adapted using full finetuning, linear probing, and parameter-efficient methods.
  arXiv  Detail & Related papers  (2025-06-23T09:16:04Z)
• Machine Learning for ALSFRS-R Score Prediction: Making Sense of the Sensor Data [44.99833362998488]
  Amyotrophic Lateral Sclerosis (ALS) is a rapidly progressive neurodegenerative disease that presents individuals with limited treatment options. The present investigation, spearheaded by the iDPP@CLEF 2024 challenge, focuses on utilizing sensor-derived data obtained through an app.
  arXiv  Detail & Related papers  (2024-07-10T19:17:23Z)
• Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
  Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
  arXiv  Detail & Related papers  (2023-04-14T09:39:06Z)
• HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN [3.8791511769387625]
  We have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU-BiLSTM) architecture to generate fusion features. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise.
  arXiv  Detail & Related papers  (2023-03-06T13:26:29Z)
• Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks [24.226952040270564]
  We propose 1D Self-organized Operational Neural Networks (1D Self-ONNs) for ECG classification. 1D Self-ONNs have the utmost advantage and superiority over conventional ONNs where the prior operator search within the operator set library is entirely avoided. Our results over the MIT-BIH arrhythmia benchmark database demonstrate that 1D Self-ONNs can surpass 1D CNNs with a significant margin.
  arXiv  Detail & Related papers  (2021-09-30T19:37:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.