Explainable Deep Neural Network for Multimodal ECG Signals: Intermediate Versus Late Fusion
IEEE Access · 2025 · 13 · 202700-202736
DOI: 10.1109/access.2025.3631544 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Timothy Oladunni und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 103 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ASCEND Research Fellowship, Yale University.
Abstract (Originalsprache)
This study investigates the effectiveness of intermediate and late fusion strategies for multimodal ECG classification across time, frequency, and time–frequency domains. Multiple fusion architectures were designed and evaluated to identify the most efficient and interpretable configuration. Intermediate fusion consistently outperformed late fusion, achieving a peak accuracy of 97 %, with a large effect size (Cohen’s d > 0.8) relative to single-domain models and d = 0.4 compared with late fusion. Interpretability analyses using saliency maps revealed that model attention aligned closely with physiologic ECG regions, while Mutual Information (MI) confirmed a strong statistical dependency between discretized ECG signals and their corresponding saliency distributions. We introduce the Explainable-AI Trustworthiness (EAT) theory, which defines the foundational principles of informational grounding, robustness, and architectural faithfulness as necessary conditions for trustworthy explanations in biomedical AI. Building on this theoretical foundation, we propose the EAT framework, which operationalizes these principles intoformal, measurable criteriafor ECG model interpretability. The framework quantifies (i) informational grounding to expert-annotated ST–T segments through adjusted/normalized MI (AMI/NMI); (ii) robustness to physiologic and adversarial perturbations via flip-rate, Δptrue, and saliency stability; and (iii) architectural faithfulness through branch concordance and ablation consistency. Under these criteria, EAT exhibits statistical soundness, monotonicity, and completeness, advancing explainability from subjective visualization toward falsifiable, auditable, and clinically trustworthy AI evaluation. The integration of EAT theory and framework establishes a unified foundation that bridges theoretical rigor with practical model validation, promoting reproducibility, clinical credibility, and cross-domain generalization in future biomedical AI research.
Förderung
- ASCEND Research Fellowship, Yale University
Zitieren
APA
Oladunni, T., & Aneni, E. (2025). Explainable Deep Neural Network for Multimodal ECG Signals: Intermediate Versus Late Fusion. IEEE Access, 13, 202700-202736. https://doi.org/10.1109/access.2025.3631544
Vancouver
Oladunni T, Aneni E. Explainable Deep Neural Network for Multimodal ECG Signals: Intermediate Versus Late Fusion. IEEE Access. 2025;13:202700-202736. doi:10.1109/access.2025.3631544
BibTeX
@article{Oladunni2025,
author = {Oladunni, Timothy and Aneni, Ehimen},
title = {Explainable Deep Neural Network for Multimodal ECG Signals: Intermediate Versus Late Fusion},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {202700--202736},
doi = {10.1109/access.2025.3631544}
}
EUVIMED