Date of Award

2025

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

Committee Chair and Members

Reda Nacif Elalaoui, Chair

Abla Bedoui

Keywords

AI diagnosis, Congenital Heart Disease, Deep learning, Image segmentation, Neural network, Pediatric ECG

Abstract

Congenital heart disease (CHD) stands as the leading congenital anomaly which affects pediatric populations throughout the world. The effectiveness of treatment depends on both early diagnosis and accurate identification but echocardiography requires manual interpretation which proves time-consuming and inconsistent especially when examining pediatric patients with their distinct cardiac systems. The research aims to create a deep learning-based diagnostic framework which uses ECG data to identify coronary artery disease subtypes in pediatric patients. The model uses high-quality datasets from Dr. Ignacio Lugones to extract R-R intervals and QRS durations through convolutional neural networks (CNNs). The system addresses pediatric-specific challenges while enhancing diagnostic accuracy for resource-constrained environments. The proposed approach demonstrates increased efficiency and accuracy through its scalable automated tool which detects disease early. The research advances pediatric cardiology by enabling earlier medical interventions which leads to better patient outcomes across the world.

Download

Share

COinS