Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 36 min ago
Peer-reviewedCC BY 4.0Frontiers in Cardiovascular Medicine

Multi-modal neural network for ECG signal classification in coronary artery disease using gramian angular field

4 affiliations
  1. 1School of Laboratory Medicine, Jilin Medical University
  2. 2School of Artificial Intelligence, Jiangnan University
  3. 3Department of Cardiology, Jilin Central Hospital
  4. 4School of Clinical Medicine, Jilin Medical University

Abstract

Background: Cardiovascular diseases (CVDs) remain a major global health burden, and electrocardiogram (ECG) classification is an important component of automated cardiac screening. However, conventional deep learning approaches may lose complementary information when operating on a single representation of the signal. This study aims to develop a multimodal method for normal-versus-abnormal ECG heartbeat classification under patient-independent evaluation.

Methods: We propose a multi-modal neural network that integrates raw ECG signals and their Gramian Angular Field (GAF) image representations. This dual-modal strategy enables the model to capture complementary time-series and two-dimensional structural features. The classifier combines lightweight multi-head attention with a residual feed-forward network, and the ECG, GASF, and fused representations provide coordinated prediction pathways followed by majority voting. To address generalization and patient-level leakage concerns, all formal experiments used strict patient-level five-fold cross-validation with patient-disjoint training, validation, and test partitions. Checkpoints were selected using validation ROC AUC, and the same fixed patient partitions were used for the ablation study and the BiLSTM/CNN + Transformer comparisons.

Results: Under the strict patient-level five-fold protocol, the Full Multimodal model achieved a ROC AUC of 0.996 and an accuracy (ACC) of 0.983. In the protocol-matched comparison, ECG-only achieved 0.815/0.846, BiLSTM 0.758/0.842, and CNN + Transformer 0.854/0.884 for ROC AUC/ACC, respectively. The ablation variants all showed lower ROC AUC and ACC than the complete model, supporting the contribution of the coordinated multimodal framework.

Conclusion: The proposed framework provides a patient-independent approach to normal-versus-abnormal ECG heartbeat classification by coordinating raw ECG and GASF representations. The revised patient-level cross-validation, component-level ablation, protocol-matched comparison, and updated literature context provide a more rigorous evaluation of the framework while supporting further validation in broader and external ECG cohorts.

Related

  1. Comparative efficacy of digital health intervention delivery modalities on quality of life, anxiety, and depression in coronary heart disease: a systematic review and network meta-analysis
    Yiran Zhang, Tianyou Yu, Wenrui Huang +4
    Frontiers in psychiatryPeer-reviewedCC BYFull textPsychiatry & mental healthEurope PMC
  2. Psychological Network Structure of Kinesiophobia and Pain Catastrophizing in Patients with Stable Coronary Heart Disease: An Exploratory Cross-Sectional Dimension-Level Network Analysis.
    Ruo-Han Wang
    Patient preference and adherencePeer-reviewedCC BY-NCFull textCardiovascular medicineEurope PMC
  3. Mapping the Dynamics of Depressive and Anxiety symptoms in Coronary Artery Disease over two years: A Network Analysis
    Laura Stefana Vida, Heidi Hermans, Joris Mulder +2
    PsyArXivPreprintCC BY 4.0Full textStatisticsPsychiatry & mental healthOSF
  4. Antiplatelet monotherapy maintenance strategies after percutaneous coronary intervention in patients with coronary artery disease at high bleeding risk: a network meta-analysis
    Xiao Zhang, YuJie Wang, YuXin Guo +1
    Frontiers in Cardiovascular MedicinePeer-reviewedCC BY 4.0Full textCardiovascular medicineCrossrefDOAJEurope PMCPMC+1
  5. A multi-class fundus disease classification framework based on self-supervised contrastive learning and dual-branch network
    Lili Cai, Keke Hou, Zhong Mo +1
    Frontiers in MedicinePeer-reviewedCC BY 4.0Full textMedical imaging & radiologyPMCEurope PMC
BibTeX
@article{jiang2026multimodal,
  title = {{Multi-modal neural network for ECG signal classification in coronary artery disease using gramian angular field}},
  author = {Yong Jiang and Xiang Pan and Ying Zhao and Xin-hua Zou and Han-qi Yang and Kai-qi Li and Yan-ting Zhu and Jian-zhe Huang and Shi-yun Nie and Jia-yin Wang and Ting-miao Tang},
  journal = {Frontiers in Cardiovascular Medicine},
  year = {2026},
  month = nov,
  doi = {10.3389/fcvm.2026.1844501},
  url = {https://www.frontiersin.org/articles/10.3389/fcvm.2026.1844501/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Multi-modal neural network for ECG signal classification in coronary artery disease using gramian angular field
AU  - Yong Jiang
AU  - Xiang Pan
AU  - Ying Zhao
AU  - Xin-hua Zou
AU  - Han-qi Yang
AU  - Kai-qi Li
AU  - Yan-ting Zhu
AU  - Jian-zhe Huang
AU  - Shi-yun Nie
AU  - Jia-yin Wang
AU  - Ting-miao Tang
PY  - 2026
DA  - 2026/11/16
JO  - Frontiers in Cardiovascular Medicine
DO  - 10.3389/fcvm.2026.1844501
UR  - https://www.frontiersin.org/articles/10.3389/fcvm.2026.1844501/full
AB  - Background: Cardiovascular diseases (CVDs) remain a major global health burden, and electrocardiogram (ECG) classification is an important component of automated cardiac screening. However, conventional deep learning approaches may lose complementary information when operating on a single representation of the signal. This study aims to develop a multimodal method for normal-versus-abnormal ECG heartbeat classification under patient-independent evaluation.  Methods: We propose a multi-modal neural network that integrates raw ECG signals and their Gramian Angular Field (GAF) image representations. This dual-modal strategy enables the model to capture complementary time-series and two-dimensional structural features. The classifier combines lightweight multi-head attention with a residual feed-forward network, and the ECG, GASF, and fused representations provide coordinated prediction pathways followed by majority voting. To address generalization and patient-level leakage concerns, all formal experiments used strict patient-level five-fold cross-validation with patient-disjoint training, validation, and test partitions. Checkpoints were selected using validation ROC AUC, and the same fixed patient partitions were used for the ablation study and the BiLSTM/CNN + Transformer comparisons.  Results: Under the strict patient-level five-fold protocol, the Full Multimodal model achieved a ROC AUC of 0.996 and an accuracy (ACC) of 0.983. In the protocol-matched comparison, ECG-only achieved 0.815/0.846, BiLSTM 0.758/0.842, and CNN + Transformer 0.854/0.884 for ROC AUC/ACC, respectively. The ablation variants all showed lower ROC AUC and ACC than the complete model, supporting the contribution of the coordinated multimodal framework.  Conclusion: The proposed framework provides a patient-independent approach to normal-versus-abnormal ECG heartbeat classification by coordinating raw ECG and GASF representations. The revised patient-level cross-validation, component-level ablation, protocol-matched comparison, and updated literature context provide a more rigorous evaluation of the framework while supporting further validation in broader and external ECG cohorts.
SN  - 2297-055X
ER  -