A Picture Tells a Thousand Words—, but ECG Signals Have More to Say

Author

Ashley N. Gomez, The University of Texas Rio Grande Valley

Date of Award

12-1-2025

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Li Zhang

Second Advisor

Pengfei Gu

Third Advisor

Yifeng Gao

Abstract

With the increasing adoption of deep learning classification models in the medical domain, a critical challenge remains: achieving high predictive accuracy while maintaining clinical Inter-pretability. This study examines how model architecture, dataset origin, and the use of full versus subset data affect both classification performance and Interpretability in Electrocardiogram (ECG) signal analysis. ResNet18 is evaluated using an open-source ECG Image Dataset, thus a custom dataset derived from digitized ECG images. Post-hoc explainability methods, such as Integrated Gradients, are applied to determine which time steps have the most significant influence on model decisions. The findings demonstrate that model architecture and dataset characteristics significantly shape both predictive performance and explanation quality, offering insights for the deployment of interpretable machine learning systems in clinical cardiology.

Comments

Copyright 2025 Ashley N. Gomez. All Rights Reserved. https://proquest.com/docview/3292420545

Recommended Citation

Gomez, A. N. (2025). A Picture Tells a Thousand Words—, but ECG Signals Have More to Say [Master's thesis, The University of Texas Rio Grande Valley]. ScholarWorks @ UTRGV. https://scholarworks.utrgv.edu/etd/1826