A Benchmark Study of Deep Learning Methods for Multi-Label Pediatric Electrocardiogram-Based Cardiovascular Disease Classification

• URL: http://arxiv.org/abs/2510.03780v1
• Date: Sat, 04 Oct 2025 11:08:46 GMT
• Title: A Benchmark Study of Deep Learning Methods for Multi-Label Pediatric Electrocardiogram-Based Cardiovascular Disease Classification
• Authors: Yiqiao Chen,
• Abstract summary: This paper presents the first benchmark study of deep learning for multi-label pediatric CVD classification on the recently released ZZU-pECG dataset.<n>We evaluate four representative paradigms--ResNet-1D, BiLSTM, Transformer, and Mamba 2--under both 9-lead and 12-lead configurations.<n>All models achieved strong results, with Hamming Loss as low as 0.0069 and F1-scores above 85% in most settings.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cardiovascular disease (CVD) is a major pediatric health burden, and early screening is of critical importance. Electrocardiography (ECG), as a noninvasive and accessible tool, is well suited for this purpose. This paper presents the first benchmark study of deep learning for multi-label pediatric CVD classification on the recently released ZZU-pECG dataset, comprising 3716 recordings with 19 CVD categories. We systematically evaluate four representative paradigms--ResNet-1D, BiLSTM, Transformer, and Mamba 2--under both 9-lead and 12-lead configurations. All models achieved strong results, with Hamming Loss as low as 0.0069 and F1-scores above 85% in most settings. ResNet-1D reached a macro-F1 of 94.67% on the 12-lead subset, while BiLSTM and Transformer also showed competitive performance. Per-class analysis indicated challenges for rare conditions such as hypertrophic cardiomyopathy in the 9-lead subset, reflecting the effect of limited positive samples. This benchmark establishes reusable baselines and highlights complementary strengths across paradigms. It further points to the need for larger-scale, multi-center validation, age-stratified analysis, and broader disease coverage to support real-world pediatric ECG applications.

Related papers

• FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation [63.7829089874007]
  This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation.<n>FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images.<n> Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2.
  arXiv  Detail & Related papers  (2026-01-22T01:34:39Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Advancing Few-Shot Pediatric Arrhythmia Classification with a Novel Contrastive Loss and Multimodal Learning [0.9225176258772595]
  We propose a multimodal end-to-end deep learning framework that combines dual-branch convolutional encoders for ECG and IEGM.<n>We also introduce a new contrastive loss fucntion named Adaptive Global Class-Aware Contrastive Loss.
  arXiv  Detail & Related papers  (2025-09-10T05:24:00Z)
• Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNet [0.6919386619690135]
  Cardioformer is a novel multi-granularity hybrid model.<n>It integrates cross-channel patching, hierarchical residual learning, and a two-stage self-attention mechanism.<n>It consistently outperforms four state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-05-08T16:44:21Z)
• Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension [30.124231086488976]
  We propose a lead-specific electrocardiogram multimodal variational autoencoder (textscLS-EMVAE)<n>textscLS-EMVAE incorporates a hierarchical modality expert (HiME) fusion mechanism and a latent representation alignment loss.<n>We validate textscLS-EMVAE across two retrospective cohorts in a 6L-ECG setting.
  arXiv  Detail & Related papers  (2025-03-03T16:16:38Z)
• Multi-Channel Masked Autoencoder and Comprehensive Evaluations for Reconstructing 12-Lead ECG from Arbitrary Single-Lead ECG [19.74009541199362]
  This study proposes a multi-channel masked autoencoder (MCMA) for reconstructing 12-Lead ECG from arbitrary single-lead ECG. In the signal-level evaluation, the mean square errors of 0.0317 and 0.1034, Pearson correlation coefficients of 0.7885 and 0.7420. In the feature-level evaluation, the average standard deviation of the mean heart rate across the generated 12-lead ECG is 1.0481, the coefficient of variation is 1.58%, and the range is 3.2874.
  arXiv  Detail & Related papers  (2024-07-16T08:17:45Z)
• ECG-SMART-NET: A Deep Learning Architecture for Precise ECG Diagnosis of Occlusion Myocardial Infarction [1.7894680263068135]
  Two thirds of OMI cases are difficult to visually identify from a 12-lead electrocardiogram.<n>Current state-of-the-art evidence suggests both feature-based random forests and convolutional neural networks (CNNs) are promising approaches to improve ECG detection of OMI.<n>We develop and evaluate ECG--NET for OMI identification.
  arXiv  Detail & Related papers  (2024-05-08T19:59:16Z)
• IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification [0.9449650062296824]
  In clinical settings, a cardiologist makes a diagnosis based on the standard 12-channel ECG recording. We propose a model that leverages the multiple-channel information available in the standard ECG recordings and learns patterns at the beat, rhythm, and channel level. The experimental results show that our model achieved a macro-averaged ROC-AUC score of 0.9216, mean accuracy of 88.85%, and a maximum F1 score of 0.8057 on the PTB-XL dataset.
  arXiv  Detail & Related papers  (2022-04-06T16:29:10Z)
• Identification of Ischemic Heart Disease by using machine learning technique based on parameters measuring Heart Rate Variability [50.591267188664666]
  In this study, 18 non-invasive features (age, gender, left ventricular ejection fraction and 15 obtained from HRV) of 243 subjects were used to train and validate a series of several ANN. The best result was obtained using 7 input parameters and 7 hidden nodes with an accuracy of 98.9% and 82% for the training and validation dataset.
  arXiv  Detail & Related papers  (2020-10-29T19:14:41Z)
• Multilabel 12-Lead Electrocardiogram Classification Using Gradient Boosting Tree Ensemble [64.29529357862955]
  We build an algorithm using gradient boosted tree ensembles fitted on morphology and signal processing features to classify ECG diagnosis. For each lead, we derive features from heart rate variability, PQRST template shape, and the full signal waveform. We join the features of all 12 leads to fit an ensemble of gradient boosting decision trees to predict probabilities of ECG instances belonging to each class.
  arXiv  Detail & Related papers  (2020-10-21T18:11:36Z)
• CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks [51.589769497681175]
  The novel coronavirus (SARS-CoV-2) has led to a pandemic. The current testing regime based on Reverse Transcription-Polymerase Chain Reaction for SARS-CoV-2 has been unable to keep up with testing demands. We propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus.
  arXiv  Detail & Related papers  (2020-07-20T21:47:28Z)
• A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging [90.29017019187282]
  " 2018 Left Atrium Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset. Analyse of the submitted algorithms using technical and biological metrics was performed. Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm.
  arXiv  Detail & Related papers  (2020-04-26T08:49:17Z)

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.