HeartBeatAI: An Interpretable and Robust Deep Learning Framework for Multi-Label ECG Arrhythmia Detection

• URL: http://arxiv.org/abs/2605.24588v1
• Date: Sat, 23 May 2026 13:58:12 GMT
• Title: HeartBeatAI: An Interpretable and Robust Deep Learning Framework for Multi-Label ECG Arrhythmia Detection
• Abstract summary: HeartBeatAI is a deep learning framework combining domain generalization, multi-scale feature aggregation, and clinical explainability for robust 12-lead ECG classification.<n>To mitigate domain shift, the framework employs MixStyle regularization and Label Smoothing.<n>LoDO evaluations reveal significant degradation in detecting rare anomalies, highlighting a persistent challenge in cross-institutional deployment.
• Score: 17.31345778518897
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Deep Learning (DL) enhances automated electrocardiogram (ECG) analysis, clinical deployment is hindered by class imbalance and the generalization gap. This paper presents HeartBeatAI, a deep learning framework combining domain generalization, multi-scale feature aggregation, and clinical explainability for robust 12-lead ECG classification. Moving beyond image-based paradigms, HeartBeatAI integrates a Squeeze-and-Excitation (SE) ResNet to isolate diagnostic leads alongside a Multi-Layer Concentration Pipeline to capture macro-rhythm and micro-morphological anomalies. To mitigate domain shift, the framework employs MixStyle regularization and Label Smoothing. Rigorous benchmarking across four large-scale datasets using intra-source and Leave-One-Domain-Out (LODO) protocols demonstrates high performance (98% Macro F1-score) under intra-source conditions. However, LODO evaluations reveal significant degradation in detecting rare anomalies, highlighting a persistent challenge in cross-institutional deployment.

Related papers

• Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement [81.27196033392559]
  We propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis.<n>COME injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training.<n>Our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline.
  arXiv  Detail & Related papers  (2026-07-24T04:26:47Z)
• MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detection [1.1242503819703258]
  Myocardial substrate abnormalities, such as myocardial scar and myocardial infarction (MI), are associated with adverse cardiovascular outcomes.<n>We propose a multi-scale attention-enhanced convolutional network (MSAIC-Net) for ECG-based myocardial substrate abnormality detection.<n>MSAIC-Net employs parallel atrous convolutional branches to extract ECG features across multiple temporal receptive fields.
  arXiv  Detail & Related papers  (2026-06-04T21:08:06Z)
• CoRe-ECG: Advancing Self-Supervised Representation Learning for 12-Lead ECG via Contrastive and Reconstructive Synergy [37.81373064028234]
  We propose CoRe-ECG, a unified contrastive and reconstructive pretraining paradigm.<n>CoRe-ECG aligns global representations during reconstruction, enabling instance-level discriminative signals to guide local waveform recovery.<n>Our method achieves state-of-the-art performance across multiple downstream ECG datasets.
  arXiv  Detail & Related papers  (2026-04-13T11:56:43Z)
• Demographic-Aware Self-Supervised Anomaly Detection Pretraining for Equitable Rare Cardiac Diagnosis [45.00216485193071]
  Rare cardiac anomalies are difficult to detect from electrocardiograms due to their long-tailed distribution.<n>We developed an AI-assisted two-stage ECG framework integrating self-supervised anomaly detection and demographic-aware representation learning.<n>Our method achieves an AUROC of 94.7% for rare anomalies and reduces the common-rare performance gap by 73%.
  arXiv  Detail & Related papers  (2026-03-20T07:04:00Z)
• Comparative Analysis of Data Augmentation for Clinical ECG Classification with STAR [0.0]
  Sinusoidal Time--Amplitude Resampling (STAR) is a beat-wise augmentation that operates strictly between successive R-peaks.<n>STAR is designed for practical pipelines and offers: (i) morphology-faithful variability that broadens training diversity without corrupting peaks or intervals; (ii) source-resilient training, improving stability across devices, sites, and cohorts without dataset-specific tuning; and (iv) better learning on rare classes via beat-level augmentation.
  arXiv  Detail & Related papers  (2025-10-15T14:18:03Z)
• FoundationalECGNet: A Lightweight Foundational Model for ECG-based Multitask Cardiac Analysis [1.1666234644810893]
  FoundationalECGNet is a foundational framework for automated ECG classification.<n>It first distinguishes between Normal and Abnormal ECG signals, and then classifies the Abnormal signals into one of five cardiac conditions.<n>It shows state-of-the-art performance in multi-class disease detection, including a 99% F1-score for Conduction Disorders and Hypertrophy.
  arXiv  Detail & Related papers  (2025-09-10T19:48:07Z)
• Latent Representations of Intracardiac Electrograms for Atrial Fibrillation Driver Detection [37.72464514643607]
  This study proposes a deep learning framework using convolutional autoencoders for unsupervised feature extraction.<n> latent representations of atrial electrical activity enable the characterization and automation of EGM analysis.<n>The proposed method can operate in real-time and enables integration into clinical electroanatomical mapping systems to assist in identifying arrhythmogenic regions during ablation procedures.
  arXiv  Detail & Related papers  (2025-07-24T09:40:24Z)
• EXGnet: a single-lead explainable-AI guided multiresolution network with train-only quantitative features for trustworthy ECG arrhythmia classification [1.5162243843944596]
  We propose EXGnet, a novel ECG arrhythmia classification network tailored for single-lead signals.<n>XAI supervision during training directs the model's attention to clinically relevant ECG regions.<n>We introduce an innovative multiresolution block to efficiently capture both short and long-term signal features.
  arXiv  Detail & Related papers  (2025-06-14T08:48:44Z)
• Multi-scale Masked Autoencoder for Electrocardiogram Anomaly Detection [5.614826802517409]
  MMAE-ECG partitions ECG signals into non-overlapping segments, with each segment assigned learnable positional embeddings.<n>A novel multi-scale masking strategy and multi-scale attention mechanism, along with distinct positional embeddings, enable a lightweight Transformer encoder.
  arXiv  Detail & Related papers  (2025-02-08T08:18:38Z)
• Self-supervised inter-intra period-aware ECG representation learning for detecting atrial fibrillation [41.82319894067087]
  We propose an inter-intra period-aware ECG representation learning approach. Considering ECGs of atrial fibrillation patients exhibit the irregularity in RR intervals and the absence of P-waves, we develop specific pre-training tasks for interperiod and intraperiod representations. Our approach demonstrates remarkable AUC performances on the BTCH dataset, textiti.e., 0.953/0.996 for paroxysmal/persistent atrial fibrillation detection.
  arXiv  Detail & Related papers  (2024-10-08T10:03:52Z)
• MEDPSeg: Hierarchical polymorphic multitask learning for the segmentation of ground-glass opacities, consolidation, and pulmonary structures on computed tomography [37.119000111386924]
  MEDPSeg learns from heterogeneous chest CT targets through hierarchical polymorphic multitask learning (HPML) We show PML enabling new state-of-the-art performance for GGO and consolidation segmentation tasks. In addition, MEDPSeg simultaneously performs segmentation of the lung parenchyma, airways, pulmonary artery, and lung lesions, all in a single forward prediction.
  arXiv  Detail & Related papers  (2023-12-04T21:46:39Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)

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.